Prices per 1M tokens.

API prices by model
ModelInputCache readOutputCapability (Epoch AI)
GLM 5.3 Flash (US)Compare GLM-5.3 Flash across 7 providers$0.225$0.045$0.75Strong · 153.8

Rates, billing conditions and sources

GLM 5.3 Flash (US)

All rates, conditions and sources

Conditions of every rate below:

  • 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 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.

Input: $0.225 per 1M tokens · Standard tier · Region: us

  • "Standard" column: the Standard serverless mode.
  • Input tokens (the first price, "input").

Cache read: $0.045 per 1M tokens · Standard tier · Region: us

  • "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: $0.75 per 1M tokens · Standard tier · Region: us

  • "Standard" column: the Standard serverless mode.
  • Output tokens (the third price, "output").

Input: $0.28125 per 1M tokens · Priority tier · Region: us

  • "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: $0.05625 per 1M tokens · Priority tier · Region: us

  • "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: $0.9375 per 1M tokens · Priority tier · Region: us

  • "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").

Capability (Epoch AI): ECI 153.8 (90% range 152.0–155.8) · Epoch AI score for GLM-5.3-Flash, model dated Aug 20, 2026

Price observed:

API availability: listed as available when checked (not a live service check)

Collection record

Primary source ↗ · provider documentation · Claims: fireworks-glm-5-3-flash-us: pricing · fireworks-glm-5-3-flash-us: availability · 36 more claims about 18 other catalog entries · Retrieved · Checked · Review due · Confidence: A

  • Raw SHA-256: 92fc48fa95a467d8dbef610486c3985810f791301713d7f73361a74f4edb1b05; 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 Nov 12, 2026. 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, listed with each model's rates and sources; a range that crosses a band boundary is flagged there. 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. Every price is a listed price, not a service guarantee; each offer's details say what its source states about availability. Batch, off-peak and other variants remain in the details; where no single rate is the default, the table shows a dash.

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.