Provider pricing

Fireworks AI API pricing

Published API listings with native prices and dated evidence. Check the official source for current availability and account eligibility.

Fireworks AI input and output pricesUSD per 1M tokens · headline rates · log scale
$0.01$0.10$1.00$10.00$100.00NVIDIA Nemotron 3.5 Lightning 30B A…NVIDIA Nemotron 3.5 Lightning 30B A3BNVIDIA Nemotron 3.5 Lightning 30B A3B · Input: $0.05NVIDIA Nemotron 3.5 Lightning 30B A3B · Output: $0.20GLM 5.3 FlashGLM 5.3 Flash · Input: $0.15GLM 5.3 Flash · Output: $0.50OpenAI GPT OSS 120BOpenAI GPT OSS 120B · Input: $0.15OpenAI GPT OSS 120B · Output: $0.60GLM 5.3 Flash (US)GLM 5.3 Flash (US) · Input: $0.225GLM 5.3 Flash (US) · Output: $0.75Ultramarine 1 Flash (US)Ultramarine 1 Flash (US) · Input: $0.225Ultramarine 1 Flash (US) · Output: $0.75DeepSeek V4.1 FlashDeepSeek V4.1 Flash · Input: $0.30DeepSeek V4.1 Flash · Output: $1.20DeepSeek V4.1 Flash 1017DeepSeek V4.1 Flash 1017 · Input: $0.30DeepSeek V4.1 Flash 1017 · Output: $1.20MiniMax M3MiniMax M3 · Input: $0.30MiniMax M3 · Output: $1.20DeepSeek V4.1 Flash (US)DeepSeek V4.1 Flash (US) · Input: $0.45DeepSeek V4.1 Flash (US) · Output: $1.80DeepSeek V4.1 Flash 1017 (US)DeepSeek V4.1 Flash 1017 (US) · Input: $0.45DeepSeek V4.1 Flash 1017 (US) · Output: $1.80NVIDIA Nemotron 3 Ultra (Preview)NVIDIA Nemotron 3 Ultra (Preview) · Input: $0.60NVIDIA Nemotron 3 Ultra (Preview) · Output: $2.40Muse Spark OpenMuse Spark Open · Input: $1.25Muse Spark Open · Output: $4.25GLM 5.3GLM 5.3 · Input: $1.40GLM 5.3 · Output: $4.40Qwen 3.8 MaxQwen 3.8 Max · Input: $2.00Qwen 3.8 Max · Output: $6.00GLM 5.3 (US)GLM 5.3 (US) · Input: $2.10GLM 5.3 (US) · Output: $6.60Ember-1Ember-1 · Input: $3.00Ember-1 · Output: $15.00Kimi K3Kimi K3 · Input: $3.00Kimi K3 · Output: $15.00Kimi K3 (US)Kimi K3 (US) · Input: $4.50Kimi K3 (US) · Output: $22.50$0.01$0.10$1.00$10.00$100.00NVIDIA Nemotron 3.5 Lightning 30B…NVIDIA Nemotron 3.5 Lightning 30B A3BNVIDIA Nemotron 3.5 Lightning 30B A3B · Input: $0.05NVIDIA Nemotron 3.5 Lightning 30B A3B · Output: $0.20GLM 5.3 FlashGLM 5.3 Flash · Input: $0.15GLM 5.3 Flash · Output: $0.50OpenAI GPT OSS 120BOpenAI GPT OSS 120B · Input: $0.15OpenAI GPT OSS 120B · Output: $0.60GLM 5.3 Flash (US)GLM 5.3 Flash (US) · Input: $0.225GLM 5.3 Flash (US) · Output: $0.75Ultramarine 1 Flash (US)Ultramarine 1 Flash (US) · Input: $0.225Ultramarine 1 Flash (US) · Output: $0.75DeepSeek V4.1 FlashDeepSeek V4.1 Flash · Input: $0.30DeepSeek V4.1 Flash · Output: $1.20DeepSeek V4.1 Flash 1017DeepSeek V4.1 Flash 1017 · Input: $0.30DeepSeek V4.1 Flash 1017 · Output: $1.20MiniMax M3MiniMax M3 · Input: $0.30MiniMax M3 · Output: $1.20DeepSeek V4.1 Flash (US)DeepSeek V4.1 Flash (US) · Input: $0.45DeepSeek V4.1 Flash (US) · Output: $1.80DeepSeek V4.1 Flash 1017 (US)DeepSeek V4.1 Flash 1017 (US) · Input: $0.45DeepSeek V4.1 Flash 1017 (US) · Output: $1.80NVIDIA Nemotron 3 Ultra (Preview)NVIDIA Nemotron 3 Ultra (Preview) · Input: $0.60NVIDIA Nemotron 3 Ultra (Preview) · Output: $2.40Muse Spark OpenMuse Spark Open · Input: $1.25Muse Spark Open · Output: $4.25GLM 5.3GLM 5.3 · Input: $1.40GLM 5.3 · Output: $4.40Qwen 3.8 MaxQwen 3.8 Max · Input: $2.00Qwen 3.8 Max · Output: $6.00GLM 5.3 (US)GLM 5.3 (US) · Input: $2.10GLM 5.3 (US) · Output: $6.60Ember-1Ember-1 · Input: $3.00Ember-1 · Output: $15.00Kimi K3Kimi K3 · Input: $3.00Kimi K3 · Output: $15.00Kimi K3 (US)Kimi K3 (US) · Input: $4.50Kimi K3 (US) · Output: $22.50
Fireworks AI input and output prices
CategoryItemUSD per 1M tokens
NVIDIA Nemotron 3.5 Lightning 30B A3BInput$0.05
NVIDIA Nemotron 3.5 Lightning 30B A3BOutput$0.20
GLM 5.3 FlashInput$0.15
GLM 5.3 FlashOutput$0.50
OpenAI GPT OSS 120BInput$0.15
OpenAI GPT OSS 120BOutput$0.60
GLM 5.3 Flash (US)Input$0.225
GLM 5.3 Flash (US)Output$0.75
Ultramarine 1 Flash (US)Input$0.225
Ultramarine 1 Flash (US)Output$0.75
DeepSeek V4.1 FlashInput$0.30
DeepSeek V4.1 FlashOutput$1.20
DeepSeek V4.1 Flash 1017Input$0.30
DeepSeek V4.1 Flash 1017Output$1.20
MiniMax M3Input$0.30
MiniMax M3Output$1.20
DeepSeek V4.1 Flash (US)Input$0.45
DeepSeek V4.1 Flash (US)Output$1.80
DeepSeek V4.1 Flash 1017 (US)Input$0.45
DeepSeek V4.1 Flash 1017 (US)Output$1.80
NVIDIA Nemotron 3 Ultra (Preview)Input$0.60
NVIDIA Nemotron 3 Ultra (Preview)Output$2.40
Muse Spark OpenInput$1.25
Muse Spark OpenOutput$4.25
GLM 5.3Input$1.40
GLM 5.3Output$4.40
Qwen 3.8 MaxInput$2.00
Qwen 3.8 MaxOutput$6.00
GLM 5.3 (US)Input$2.10
GLM 5.3 (US)Output$6.60
Ember-1Input$3.00
Ember-1Output$15.00
Kimi K3Input$3.00
Kimi K3Output$15.00
Kimi K3 (US)Input$4.50
Kimi K3 (US)Output$22.50
Headline USD token rates per 1M; other currencies and units remain native. Original rates are below. Unknown means no unambiguous headline; inspect all rates and conditions below.
API listingInputCache readOutputCapability (Epoch AI)
DeepSeek V4.1 FlashCompare DeepSeek V4.1 Flash across 4 providersUSD 0.30 / 1M tokensstandardUSD 0.006 / 1M tokensstandardUSD 1.20 / 1M tokensstandardStrong · ECI 156.1 (90% range 153.7–158.3) · Epoch AI score for DeepSeek V4.1 Flash, model dated 2026-09-09
DeepSeek V4.1 Flash (US)Compare DeepSeek V4.1 Flash across 4 providersUSD 0.45 / 1M tokensstandardUSD 0.009 / 1M tokensstandardUSD 1.80 / 1M tokensstandardStrong · ECI 156.1 (90% range 153.7–158.3) · Epoch AI score for DeepSeek V4.1 Flash, model dated 2026-09-09
DeepSeek V4.1 Flash 1017USD 0.30 / 1M tokensstandardUSD 0.006 / 1M tokensstandardUSD 1.20 / 1M tokensstandardNo independent capability score
DeepSeek V4.1 Flash 1017 (US)USD 0.45 / 1M tokensstandardUSD 0.009 / 1M tokensstandardUSD 1.80 / 1M tokensstandardNo independent capability score
Ember-1USD 3.00 / 1M tokensstandardUSD 0.30 / 1M tokensstandardUSD 15.00 / 1M tokensstandardNo independent capability score
GLM 5.3Compare GLM-5.3 across 5 providersUSD 1.40 / 1M tokensstandardUSD 0.26 / 1M tokensstandardUSD 4.40 / 1M tokensstandardStrong · ECI 156.2 (90% range 154.3–158.5) · Epoch AI score for GLM-5.3, model dated 2026-08-14
GLM 5.3 (US)Compare GLM-5.3 across 5 providersUSD 2.10 / 1M tokensstandardUSD 0.39 / 1M tokensstandardUSD 6.60 / 1M tokensstandardStrong · ECI 156.2 (90% range 154.3–158.5) · Epoch AI score for GLM-5.3, model dated 2026-08-14
GLM 5.3 FlashCompare GLM-5.3 Flash across 5 providersUSD 0.15 / 1M tokensstandardUSD 0.03 / 1M tokensstandardUSD 0.50 / 1M tokensstandardStrong · ECI 153.2 (90% range 150.9–155.4) · Epoch AI score for GLM-5.3-Flash, model dated 2026-08-20
GLM 5.3 Flash (US)Compare GLM-5.3 Flash across 5 providersUSD 0.225 / 1M tokensstandardUSD 0.045 / 1M tokensstandardUSD 0.75 / 1M tokensstandardStrong · ECI 153.2 (90% range 150.9–155.4) · Epoch AI score for GLM-5.3-Flash, model dated 2026-08-20
Kimi K3Compare Kimi K3 across 6 providersUSD 3.00 / 1M tokensstandardUSD 0.30 / 1M tokensstandardUSD 15.00 / 1M tokensstandardStrong · ECI 158.3 (90% range 155.8–161.4) · range spans bands · Epoch AI score for Kimi K3, model dated 2026-07-16
Kimi K3 (US)Compare Kimi K3 across 6 providersUSD 4.50 / 1M tokensstandardUSD 0.45 / 1M tokensstandardUSD 22.50 / 1M tokensstandardStrong · ECI 158.3 (90% range 155.8–161.4) · range spans bands · Epoch AI score for Kimi K3, model dated 2026-07-16
MiniMax M3Compare MiniMax M3 across 5 providersUSD 0.30 / 1M tokensstandardUSD 0.06 / 1M tokensstandardUSD 1.20 / 1M tokensstandardCapable · ECI 146.9 (90% range 142.4–150.3) · range spans bands · Epoch AI score for MiniMax-M3, model dated 2026-06-01
Muse Spark OpenUSD 1.25 / 1M tokensstandardUSD 0.15 / 1M tokensstandardUSD 4.25 / 1M tokensstandardNo independent capability score
NVIDIA Nemotron 3 Ultra (Preview)USD 0.60 / 1M tokensstandardUSD 0.12 / 1M tokensstandardUSD 2.40 / 1M tokensstandardNo independent capability score
NVIDIA Nemotron 3.5 Lightning 30B A3BUSD 0.05 / 1M tokensstandardUSD 0.01 / 1M tokensstandardUSD 0.20 / 1M tokensstandardNo independent capability score
OpenAI GPT OSS 120BCompare gpt-oss-120b across 5 providersUSD 0.15 / 1M tokensstandardUSD 0.015 / 1M tokensstandardUSD 0.60 / 1M tokensstandardEntry · ECI 139.8 (90% range 135.6–142.2) · range spans bands · Epoch AI score for gpt-oss-120b, model dated 2025-08-05
Qwen 3.8 MaxCompare Qwen3.8-Max across 2 providersUSD 2.00 / 1M tokensstandardUSD 0.25 / 1M tokensstandardUSD 6.00 / 1M tokensstandardNo independent capability score
Ultramarine 1 Flash (US)USD 0.225 / 1M tokensstandardUSD 0.045 / 1M tokensstandardUSD 0.75 / 1M tokensstandardNo independent capability score

Rates, billing conditions and sources

DeepSeek V4.1 Flash

Service ID: Unknown · Context window: 1M tokens · Listing status: active

All rates, conditions and sources

Input: USD 0.30 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.006 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 1.20 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.375 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.0075 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 1.50 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-deepseek-v4-1-flash: specifications · Retrieved · Effective: Unknown · Checked: 2026-10-14T01:50:41Z · Reviewed: 2026-10-17T19:45:45Z · Review after: Unknown · Freshness: unknown · Confidence: A

  • Official Fireworks AI model page for DeepSeek V4.1 Flash, "Context Length" row, raw SHA-256 5d4a606d81c58b35374efc0eb96af7c83a4b85e4ab0d0554658131d4fe564874: "Context Length 1M tokens".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

DeepSeek V4.1 Flash (US)

Service ID: Unknown · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 0.45 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.009 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 1.80 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.5625 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.01125 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 2.25 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

DeepSeek V4.1 Flash 1017

Service ID: Unknown · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 0.30 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.006 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 1.20 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.375 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.0075 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 1.50 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

DeepSeek V4.1 Flash 1017 (US)

Service ID: Unknown · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 0.45 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.009 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 1.80 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.5625 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.01125 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 2.25 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "DeepSeek V4.1 Flash 1017 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Ember-1

Service ID: Unknown · Context window: 1M tokens · Listing status: active

All rates, conditions and sources

Input: USD 3.00 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ember-1". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ember-1; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.30 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ember-1". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ember-1; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 15.00 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ember-1". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ember-1; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 3.75 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ember-1". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ember-1; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.375 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ember-1". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ember-1; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 18.75 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ember-1". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ember-1; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: specifications · Retrieved · Effective: Unknown · Checked: 2026-10-14T01:50:41Z · Reviewed: 2026-10-17T19:45:45Z · Review after: Unknown · Freshness: unknown · Confidence: A

  • Official Fireworks AI model page for Ember-1, "Context Length" row, raw SHA-256 a6fe1d796c0ae43e5b62ff9e130cfee215aad601893dc20504c6638680b7ff01: "Context Length 1M tokens".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

GLM 5.3

Service ID: Unknown · Context window: 1M tokens · Listing status: active

All rates, conditions and sources

Input: USD 1.40 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.26 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 4.40 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 1.75 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.325 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 5.50 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Input: USD 2.10 / 1M tokens · Fast · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: fast · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • The Fast serverless mode, priced in the "Standard" column of the adjacent Fast row ("Fast variants appear as adjacent rows"); that row's Priority cell is "—", so the page offers no Priority price for Fast.
  • Input tokens (the first price, "input").

Cache read: USD 0.39 / 1M tokens · Fast · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: fast · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • The Fast serverless mode, priced in the "Standard" column of the adjacent Fast row ("Fast variants appear as adjacent rows"); that row's Priority cell is "—", so the page offers no Priority price for Fast.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 6.60 / 1M tokens · Fast · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: fast · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • The Fast serverless mode, priced in the "Standard" column of the adjacent Fast row ("Fast variants appear as adjacent rows"); that row's Priority cell is "—", so the page offers no Priority price for Fast.
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-glm-5-3: specifications · Retrieved · Effective: Unknown · Checked: 2026-10-14T01:50:43Z · Reviewed: 2026-10-17T19:45:45Z · Review after: Unknown · Freshness: unknown · Confidence: A

  • Official Fireworks AI model page for GLM 5.3, "Context Length" row, raw SHA-256 e336ba256b781b4946b0e350a89be86ade2ad4ddfb516f69a86379d71e30343b: "Context Length 1M tokens".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

GLM 5.3 (US)

Service ID: Unknown · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 2.10 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.39 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 6.60 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 2.625 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.4875 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 8.25 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

GLM 5.3 Flash

Service ID: Unknown · Context window: 1M tokens · Listing status: active

All rates, conditions and sources

Input: USD 0.15 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.03 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.50 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.1875 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.0375 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.625 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-glm-5-3-flash: specifications · Retrieved · Effective: Unknown · Checked: 2026-10-14T01:50:42Z · Reviewed: 2026-10-17T19:45:45Z · Review after: Unknown · Freshness: unknown · Confidence: A

  • Official Fireworks AI model page for GLM 5.3 Flash, "Context Length" row, raw SHA-256 599c14ad7086cc60a231a5cb943d4ec58f50c77548bbed16b390c170ad0f884d: "Context Length 1M tokens".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

GLM 5.3 Flash (US)

Service ID: Unknown · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 0.225 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.045 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.75 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.28125 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.05625 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.9375 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "GLM 5.3 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/glm-5p3-flash; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Kimi K3

Service ID: Unknown · Context window: 1M tokens · Listing status: active

All rates, conditions and sources

Input: USD 3.00 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.30 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 15.00 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 3.75 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.375 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 18.75 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Input: USD 4.50 / 1M tokens · Fast · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: fast · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • The Fast serverless mode, priced in the "Standard" column of the adjacent Fast row ("Fast variants appear as adjacent rows"); that row's Priority cell is "—", so the page offers no Priority price for Fast.
  • Input tokens (the first price, "input").

Cache read: USD 0.45 / 1M tokens · Fast · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: fast · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • The Fast serverless mode, priced in the "Standard" column of the adjacent Fast row ("Fast variants appear as adjacent rows"); that row's Priority cell is "—", so the page offers no Priority price for Fast.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 22.50 / 1M tokens · Fast · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: fast · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • The Fast serverless mode, priced in the "Standard" column of the adjacent Fast row ("Fast variants appear as adjacent rows"); that row's Priority cell is "—", so the page offers no Priority price for Fast.
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-kimi-k3: specifications · Retrieved · Effective: Unknown · Checked: 2026-10-14T01:50:41Z · Reviewed: 2026-10-17T19:45:45Z · Review after: Unknown · Freshness: unknown · Confidence: A

  • Official Fireworks AI model page for Kimi K3, "Context Length" row, raw SHA-256 d922b6c5fe0a8721a5b9032358a7dfde6670d16ea0edb6c719d8e441bbac7b12: "Context Length 1M tokens".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Kimi K3 (US)

Service ID: Unknown · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 4.50 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.45 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 22.50 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 5.625 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.5625 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 28.125 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Kimi K3 (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/kimi-k3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

MiniMax M3

Service ID: Unknown · Context window: 512K tokens · Listing status: active

All rates, conditions and sources

Input: USD 0.30 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "MiniMax M3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/minimax-m3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.06 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "MiniMax M3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/minimax-m3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 1.20 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "MiniMax M3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/minimax-m3; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.45 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "MiniMax M3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/minimax-m3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.09 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "MiniMax M3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/minimax-m3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 1.80 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "MiniMax M3". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/minimax-m3; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-minimax-m3: specifications · Retrieved · Effective: Unknown · Checked: 2026-10-14T01:50:44Z · Reviewed: 2026-10-17T19:45:45Z · Review after: Unknown · Freshness: unknown · Confidence: A

  • Official Fireworks AI model page for MiniMax M3, "Context Length" row, raw SHA-256 a8eebfa70fadee8084d7f00c6e64d7f7044fa2b10e710af8912eb26b6c1c7b41: "Context Length 512k tokens".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Muse Spark Open

Service ID: Unknown · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 1.25 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Muse Spark Open". The source states: "Muse Spark Open runs on US-only capacity. The 50% US-only premium is waived, so the rates in that row are what you pay." Region "us" is recorded from that note only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/muse-spark-open; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.15 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Muse Spark Open". The source states: "Muse Spark Open runs on US-only capacity. The 50% US-only premium is waived, so the rates in that row are what you pay." Region "us" is recorded from that note only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/muse-spark-open; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 4.25 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Muse Spark Open". The source states: "Muse Spark Open runs on US-only capacity. The 50% US-only premium is waived, so the rates in that row are what you pay." Region "us" is recorded from that note only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/muse-spark-open; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 1.875 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Muse Spark Open". The source states: "Muse Spark Open runs on US-only capacity. The 50% US-only premium is waived, so the rates in that row are what you pay." Region "us" is recorded from that note only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/muse-spark-open; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.225 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Muse Spark Open". The source states: "Muse Spark Open runs on US-only capacity. The 50% US-only premium is waived, so the rates in that row are what you pay." Region "us" is recorded from that note only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/muse-spark-open; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 6.375 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Muse Spark Open". The source states: "Muse Spark Open runs on US-only capacity. The 50% US-only premium is waived, so the rates in that row are what you pay." Region "us" is recorded from that note only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/muse-spark-open; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

NVIDIA Nemotron 3 Ultra (Preview)

Service ID: Unknown · Context window: 262K tokens · Listing status: active

All rates, conditions and sources

Input: USD 0.60 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3 Ultra (Preview)". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.12 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3 Ultra (Preview)". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 2.40 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3 Ultra (Preview)". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.75 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3 Ultra (Preview)". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.15 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3 Ultra (Preview)". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 3.00 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3 Ultra (Preview)". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-nemotron-3-ultra-preview: specifications · Retrieved · Effective: Unknown · Checked: 2026-10-14T01:50:48Z · Reviewed: 2026-10-17T19:45:45Z · Review after: Unknown · Freshness: unknown · Confidence: A

  • Official Fireworks AI model page for NVIDIA Nemotron 3 Ultra (Preview), "Context Length" row, raw SHA-256 9425b14fec7f7fbad890c7080eb161cda7f2a36b7ca9718a2e46a20019562abf: "Context Length 262k tokens".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

NVIDIA Nemotron 3.5 Lightning 30B A3B

Service ID: Unknown · Context window: 262K tokens · Listing status: active

All rates, conditions and sources

Input: USD 0.05 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3.5 Lightning 30B A3B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.01 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3.5 Lightning 30B A3B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.20 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3.5 Lightning 30B A3B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.0625 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3.5 Lightning 30B A3B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.0125 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3.5 Lightning 30B A3B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.25 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "NVIDIA Nemotron 3.5 Lightning 30B A3B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-nemotron-3-5-lightning-30b-a3b: specifications · Retrieved · Effective: Unknown · Checked: 2026-10-14T01:50:47Z · Reviewed: 2026-10-17T19:45:45Z · Review after: Unknown · Freshness: unknown · Confidence: A

  • Official Fireworks AI model page for NVIDIA Nemotron 3.5 Lightning 30B A3B, "Context Length" row, raw SHA-256 2520b4a8fda7a532237e0f6fbb39d8776595b36ba6b667633bab2313c61f8f88: "Context Length 262k tokens".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

OpenAI GPT OSS 120B

Service ID: Unknown · Context window: 131K tokens · Listing status: active

All rates, conditions and sources

Input: USD 0.15 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "OpenAI GPT OSS 120B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/gpt-oss-120b; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.015 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "OpenAI GPT OSS 120B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/gpt-oss-120b; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.60 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "OpenAI GPT OSS 120B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/gpt-oss-120b; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.18 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "OpenAI GPT OSS 120B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/gpt-oss-120b; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.018 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "OpenAI GPT OSS 120B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/gpt-oss-120b; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.72 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "OpenAI GPT OSS 120B". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/gpt-oss-120b; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-gpt-oss-120b: specifications · Retrieved · Effective: Unknown · Checked: 2026-10-14T01:50:46Z · Reviewed: 2026-10-17T19:45:45Z · Review after: Unknown · Freshness: unknown · Confidence: A

  • Official Fireworks AI model page for OpenAI GPT OSS 120B, "Context Length" row, raw SHA-256 f3d85d9a5a0b473f105399736123e807f81da77826825bb4a75937fa7eb53eeb: "Context Length 131k tokens".
  • Visible shorthand recorded as stated (#504); not converted to an exact token count.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Qwen 3.8 Max

Service ID: Unknown · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 2.00 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Qwen 3.8 Max". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/qwen3p8-max; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.25 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Qwen 3.8 Max". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/qwen3p8-max; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 6.00 / 1M tokens · Standard · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Qwen 3.8 Max". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/qwen3p8-max; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 3.00 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Qwen 3.8 Max". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/qwen3p8-max; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.375 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Qwen 3.8 Max". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/qwen3p8-max; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 9.00 / 1M tokens · Priority · Modality: unspecified

Region: unknown · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Qwen 3.8 Max". The page states no region or endpoint for this row. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/qwen3p8-max; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-09T20:15:25.930Z · Reviewed: Unknown · Review after: 2026-10-19T20:15:25.930Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 51f7f677cc9913ee569fb563c517530a65380534ec6a558d7cb92ef2a2166179; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · Retrieved · Effective: Unknown · Checked: 2026-10-26T01:02:28.541Z · Reviewed: Unknown · Review after: 2026-11-05T01:02:28.541Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-27T01:27:07.784Z · Reviewed: Unknown · Review after: 2026-11-06T01:27:07.784Z · Freshness: stale · Confidence: A

  • Raw SHA-256: dc3e015d2559b21a6bd549bdb0ac09f1bb1c33e513363b98ea3441001e784b3b; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · Retrieved · Effective: Unknown · Checked: 2026-10-30T04:31:13.710Z · Reviewed: Unknown · Review after: 2026-11-09T04:31:13.710Z · Freshness: stale · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.

Ultramarine 1 Flash (US)

Service ID: Unknown · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 0.225 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ultramarine 1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ultramarine-1-flash-us; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: USD 0.045 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ultramarine 1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ultramarine-1-flash-us; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.75 / 1M tokens · Standard · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: standard · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ultramarine 1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ultramarine-1-flash-us; the pricing page states no API model ID.
  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: USD 0.28125 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ultramarine 1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ultramarine-1-flash-us; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Input tokens (the first price, "input").

Cache read: USD 0.05625 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ultramarine 1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ultramarine-1-flash-us; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Cached input tokens served from prompt cache (the second price, "cached input"). The source states no cache-write price or cache TTL.

Output: USD 0.9375 / 1M tokens · Priority · Modality: unspecified

Region: us · Endpoint scope: unknown · Tier: priority · Billing: Unknown · Prompt bracket: none stated · Cache TTL: Unknown seconds · Valid through: Unknown

  • Fireworks AI serverless per-token price from the "Text and vision models" table, USD per 1M tokens ("Prices below are per 1 million tokens in US dollars"). Batch inference (the page states it "is billed at 50% of serverless pricing on both input and output"), the size-based "Other base models" prices, embeddings, on-demand GPU deployments and training are out of scope.
  • Price row "Ultramarine 1 Flash (US)". The page does not define the "(US)" label; region "us" is recorded from the row label only, with no data-residency, endpoint or eligibility claim. The row links the Fireworks model page https://app.fireworks.ai/models/fireworks/ultramarine-1-flash-us; the pricing page states no API model ID.
  • "Priority" column: the Priority serverless mode, priced on the same row. The source states: "— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability."
  • Output tokens (the third price, "output").

Developer: Unknown / not verified · API seller: Fireworks AI

Checkpoint: Unknown / not verified · Lineage: Unknown / not verified

Official pricing ↗

Price observed: 2026-11-02T04:29:30.573Z · Price source checked: 2026-11-02T04:29:30.573Z · Price freshness: fresh

Weight-license reviewed: Unknown. Open weights do not establish permission for every commercial use; consult the linked terms.

Gating: unknown · Code license: Unknown / not verified · API availability: available (dated observation, not a live service check)

Source, conditions and dates

Primary source ↗ · vendor-docs · Claims: fireworks-ember-1: pricing · fireworks-ember-1: availability · fireworks-kimi-k3: pricing · fireworks-kimi-k3: availability · fireworks-kimi-k3-us: pricing · fireworks-kimi-k3-us: availability · fireworks-deepseek-v4-1-flash: pricing · fireworks-deepseek-v4-1-flash: availability · fireworks-deepseek-v4-1-flash-us: pricing · fireworks-deepseek-v4-1-flash-us: availability · fireworks-deepseek-v4-1-flash-1017: pricing · fireworks-deepseek-v4-1-flash-1017: availability · fireworks-deepseek-v4-1-flash-1017-us: pricing · fireworks-deepseek-v4-1-flash-1017-us: availability · fireworks-glm-5-3-flash: pricing · fireworks-glm-5-3-flash: availability · fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · fireworks-glm-5-3: pricing · fireworks-glm-5-3: availability · fireworks-glm-5-3-us: pricing · fireworks-glm-5-3-us: availability · fireworks-qwen-3-8-max: pricing · fireworks-qwen-3-8-max: availability · fireworks-minimax-m3: pricing · fireworks-minimax-m3: availability · fireworks-gpt-oss-120b: pricing · fireworks-gpt-oss-120b: availability · fireworks-nemotron-3-5-lightning-30b-a3b: pricing · fireworks-nemotron-3-5-lightning-30b-a3b: availability · fireworks-nemotron-3-ultra-preview: pricing · fireworks-nemotron-3-ultra-preview: availability · fireworks-muse-spark-open: pricing · fireworks-muse-spark-open: availability · fireworks-ultramarine-1-flash-us: pricing · fireworks-ultramarine-1-flash-us: availability · Retrieved · Effective: Unknown · Checked: 2026-11-02T04:29:30.573Z · Reviewed: Unknown · Review after: 2026-11-12T04:29:30.573Z · Freshness: fresh · Confidence: A

  • Raw SHA-256: 46b0511a91d18ef0dd17f7b418d78b9b920307a2822e6ace7e7e7bb5d97386d4; collector fireworks-markdown-1.
  • Hosted serverless pricing and listing observation only; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO), offers are not linked to checkpoints. Availability rests on this official Fireworks pricing page listing the row, as for the direct providers (xAI, Mistral AI).
  • The pricing page names models and links their Fireworks model pages but states no API model IDs, so offers record none. No account or regional eligibility claim.
About capability scores (Epoch AI)

Capability scores: Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource], epoch.ai/benchmarks. Accessed 2026-10-31. Licensed CC BY 4.0; values here are rounded to one decimal place and grouped into bands.

The Epoch Capabilities Index (ECI) combines many benchmarks on a scale where Claude 3.5 Sonnet is 130 and GPT-5 is 150. Bands, on the displayed one-decimal score: Frontier 160+, Strong 150–159.9, Capable 140–149.9, Entry below 140. Each score has a 90% range; a range that crosses a band boundary is flagged. Models are not ranked: neighbouring scores often overlap.

A benchmark is not your workload. Epoch's scores mostly reflect runs at the highest reasoning effort, which use more output tokens than default settings. Scores are dated and can shift between Epoch releases. A score belongs to the developer's model; a host listing shows the same model's score, but hosts may serve different versions or quantizations.

How headline rates are chosen

Headline rates use the directory's shared rule: the rate a buyer meets by default, chosen by billing, tier and context dimensions and never by price. Context caps, the bracket starting at zero and short-context variants are labeled; unverified availability is flagged and is not a service guarantee. Batch, off-peak and other variants remain in the details; ambiguous headlines stay unknown.

No currency conversion is performed. Missing cache prices are unknown, not zero. Equal units do not establish equivalent models or service conditions. See the methodology and source register.