Baseten API listing

GLM-5.3 Fast API pricing on Baseten

Baseten's published API listing for GLM-5.3 Fast, with native prices and dated evidence. Check the official source for current availability and account eligibility.

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)
GLM-5.3 FastUSD 2.1 / 1M tokensstandardUSD 0.21 / 1M tokensstandardUSD 6.6 / 1M tokensstandardNo independent capability score

Rates, billing conditions and sources

GLM-5.3 Fast

Service ID: zai-org/GLM-5.3-Fast · Context window: Unknown · Listing status: active

All rates, conditions and sources

Input: USD 2.1 / 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

  • Baseten pricing page (www.baseten.co/pricing), "Token pricing ($ per 1M tokens)" table ("Pay for input, cached input, and output tokens."): Input, Cache input and Output per 1 million tokens.
  • Model "zai-org/GLM-5.3-Fast" (the Baseten Model APIs slug), the row "GLM-5.3 Fast"; Baseten's Model APIs overview, reviewed on 2026-11-08, lists this slug.
  • A Fast variant: Baseten's documentation says Fast variants use the same weights as their base models with dedicated capacity for higher sustained throughput, under separate slugs, pricing and rate limits, and that requests use base-model capacity when Fast capacity is unavailable.
  • Currency: the table heading writes "$" and the cells name no currency; Baseten's Model API cost documentation reports costs in USD.
  • Cache: Baseten states no cache duration, cache-write price or exact eligibility rule; they are unknown.
  • List prices: the table states no region, endpoint, service tier or account eligibility, and Baseten's documentation says the regions serving a Model API can change.
  • Input tokens (the row's "Input" column).

Cache read: USD 0.21 / 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

  • Baseten pricing page (www.baseten.co/pricing), "Token pricing ($ per 1M tokens)" table ("Pay for input, cached input, and output tokens."): Input, Cache input and Output per 1 million tokens.
  • Model "zai-org/GLM-5.3-Fast" (the Baseten Model APIs slug), the row "GLM-5.3 Fast"; Baseten's Model APIs overview, reviewed on 2026-11-08, lists this slug.
  • A Fast variant: Baseten's documentation says Fast variants use the same weights as their base models with dedicated capacity for higher sustained throughput, under separate slugs, pricing and rate limits, and that requests use base-model capacity when Fast capacity is unavailable.
  • Currency: the table heading writes "$" and the cells name no currency; Baseten's Model API cost documentation reports costs in USD.
  • Cache: Baseten states no cache duration, cache-write price or exact eligibility rule; they are unknown.
  • List prices: the table states no region, endpoint, service tier or account eligibility, and Baseten's documentation says the regions serving a Model API can change.
  • Cached input tokens (the row's "Cache input" column): Baseten's Model APIs documentation says prompt tokens served from the KV cache when a request reuses a cached prefix are billed at a discounted rate, with caching automatic.

Output: USD 6.6 / 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

  • Baseten pricing page (www.baseten.co/pricing), "Token pricing ($ per 1M tokens)" table ("Pay for input, cached input, and output tokens."): Input, Cache input and Output per 1 million tokens.
  • Model "zai-org/GLM-5.3-Fast" (the Baseten Model APIs slug), the row "GLM-5.3 Fast"; Baseten's Model APIs overview, reviewed on 2026-11-08, lists this slug.
  • A Fast variant: Baseten's documentation says Fast variants use the same weights as their base models with dedicated capacity for higher sustained throughput, under separate slugs, pricing and rate limits, and that requests use base-model capacity when Fast capacity is unavailable.
  • Currency: the table heading writes "$" and the cells name no currency; Baseten's Model API cost documentation reports costs in USD.
  • Cache: Baseten states no cache duration, cache-write price or exact eligibility rule; they are unknown.
  • List prices: the table states no region, endpoint, service tier or account eligibility, and Baseten's documentation says the regions serving a Model API can change.
  • Output tokens (the row's "Output" column).

Developer: Unknown / not verified · API seller: Baseten

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

Price observed: 2026-11-09T04:32:56.952Z · Price source checked: 2026-11-09T04:32:56.952Z · 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: baseten-beam-1-0: pricing · baseten-beam-1-0: availability · baseten-muse-spark-open: pricing · baseten-muse-spark-open: availability · baseten-glm-5-3-fast: pricing · baseten-glm-5-3-fast: availability · baseten-glm-5-3: pricing · baseten-glm-5-3: availability · baseten-glm-5-3-flash: pricing · baseten-glm-5-3-flash: availability · baseten-glm-5-2-fast: pricing · baseten-glm-5-2-fast: availability · baseten-glm-5-2: pricing · baseten-glm-5-2: availability · baseten-deepseek-v4-1-flash-1017-fast: pricing · baseten-deepseek-v4-1-flash-1017-fast: availability · baseten-deepseek-v4-1-flash-1017: pricing · baseten-deepseek-v4-1-flash-1017: availability · baseten-deepseek-v4-1-flash-fast: pricing · baseten-deepseek-v4-1-flash-fast: availability · baseten-deepseek-v4-1-flash: pricing · baseten-deepseek-v4-1-flash: availability · baseten-deepseek-v4-pro-0813: pricing · baseten-deepseek-v4-pro-0813: availability · baseten-deepseek-v4-flash-0731: pricing · baseten-deepseek-v4-flash-0731: availability · baseten-kimi-k3-1-pro: pricing · baseten-kimi-k3-1-pro: availability · baseten-kimi-k3: pricing · baseten-kimi-k3: availability · baseten-nemotron-3-5-super-vl: pricing · baseten-nemotron-3-5-super-vl: availability · baseten-nemotron-3-ultra: pricing · baseten-nemotron-3-ultra: availability · baseten-gpt-oss-120b: pricing · baseten-gpt-oss-120b: availability · Retrieved · Effective: Unknown · Checked: 2026-11-08T13:55:05.642Z · Reviewed: Unknown · Review after: 2026-11-18T13:55:05.642Z · Freshness: stale · Confidence: B

  • Raw SHA-256: dc5a6a1fb4c3842292b990c7697714f7cb787f9332124f9d376616d58fa03b73; collector baseten-token-pricing-table-1.
  • Hosted listing and pricing observation only: the reviewed rows of the token pricing table; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers, a listing is not proof of identical weights or behavior.
  • The page writes "$" and names no currency; US dollars rest on Baseten's Model API cost documentation, which reports costs in USD, hence confidence B. Availability rests on Baseten listing the model in its own price table.

Primary source ↗ · vendor-docs · Claims: baseten-beam-1-0: pricing · baseten-beam-1-0: availability · baseten-muse-spark-open: pricing · baseten-muse-spark-open: availability · baseten-glm-5-3-fast: pricing · baseten-glm-5-3-fast: availability · baseten-glm-5-3: pricing · baseten-glm-5-3: availability · baseten-glm-5-3-flash: pricing · baseten-glm-5-3-flash: availability · baseten-glm-5-2-fast: pricing · baseten-glm-5-2-fast: availability · baseten-glm-5-2: pricing · baseten-glm-5-2: availability · baseten-deepseek-v4-1-flash-1017-fast: pricing · baseten-deepseek-v4-1-flash-1017-fast: availability · baseten-deepseek-v4-1-flash-1017: pricing · baseten-deepseek-v4-1-flash-1017: availability · baseten-deepseek-v4-1-flash-fast: pricing · baseten-deepseek-v4-1-flash-fast: availability · baseten-deepseek-v4-1-flash: pricing · baseten-deepseek-v4-1-flash: availability · baseten-deepseek-v4-pro-0813: pricing · baseten-deepseek-v4-pro-0813: availability · baseten-deepseek-v4-flash-0731: pricing · baseten-deepseek-v4-flash-0731: availability · baseten-kimi-k3-1-pro: pricing · baseten-kimi-k3-1-pro: availability · baseten-kimi-k3: pricing · baseten-kimi-k3: availability · baseten-nemotron-3-5-super-vl: pricing · baseten-nemotron-3-5-super-vl: availability · baseten-nemotron-3-ultra: pricing · baseten-nemotron-3-ultra: availability · baseten-gpt-oss-120b: pricing · baseten-gpt-oss-120b: availability · Retrieved · Effective: Unknown · Checked: 2026-11-09T04:32:56.952Z · Reviewed: Unknown · Review after: 2026-11-19T04:32:56.952Z · Freshness: fresh · Confidence: B

  • Raw SHA-256: 3be79daba53c8024d676c6c85fd78115b34f95742cd9af68f595a5abe5a53284; collector baseten-token-pricing-table-1.
  • Hosted listing and pricing observation only: the reviewed rows of the token pricing table; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers, a listing is not proof of identical weights or behavior.
  • The page writes "$" and names no currency; US dollars rest on Baseten's Model API cost documentation, which reports costs in USD, hence confidence B. Availability rests on Baseten listing the model in its own price table.
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 2026-11-06. 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.