Prices per 1M tokens. A dash means no single price is listed.

API prices by model
ModelInputCache readOutputCapability (Epoch AI)
gpt-oss-120bCompare gpt-oss-120b across 6 providers$0.15No single price$0.60Capable · 140.2

Rates, billing conditions and sources

gpt-oss-120b

Context window: 128K tokens

All rates, conditions and sources

Conditions of every rate below:

  • Listed for model "gpt-oss-120b" (provider "OpenAI") in us-east-1 with service_tier "standard", as one USD price dimension from 0 to Inf.
  • AWS lists this price in USD per 1K tokens (unit "1K tokens"); it is multiplied by 1,000 exactly, by decimal arithmetic, to give USD per 1M tokens.
  • Only the standard on-demand tier in us-east-1 is published: flex, priority, batch and global cross-region tiers, other AWS Regions and provisioned throughput are excluded. The offer file lists no standard-tier cache price for this model; missing cache prices are unknown, not zero.

Input: $0.15 per 1M tokens · Standard tier · Region: us-east-1

  • AWS Price List Bulk API offer file for Amazon Bedrock in US East (N. Virginia) (pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json), on-demand (OnDemand) term of usagetype USE1-openai.gpt-oss-120b-mantle-input-tokens-standard.
  • Input tokens.

Output: $0.60 per 1M tokens · Standard tier · Region: us-east-1

  • AWS Price List Bulk API offer file for Amazon Bedrock in US East (N. Virginia) (pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json), on-demand (OnDemand) term of usagetype USE1-openai.gpt-oss-120b-mantle-output-tokens-standard.
  • Output tokens.

Capability (Epoch AI): ECI 140.2 (90% range 138.3–142.1) · range spans bands · Epoch AI score for gpt-oss-120b, model dated Aug 5, 2025

Price observed:

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

Collection record

Primary source ↗ · provider documentation · Claims: bedrock-gpt-oss-120b: specifications · Retrieved · Checked · Reviewed · Freshness: unknown · Confidence: A

  • Official Amazon Bedrock model card ("Models at a glance") for gpt-oss-120b, Model ID openai.gpt-oss-120b (the offer's price list usagetype stem), raw SHA-256 e8362d2487b7637bdd398b1115a3dcb257cb835c72934f0b981df6112b6e8316, read once on 2026-10-31 under the #837 AWS facts-plus-link basis: "Context window: 128K tokens".
  • Shorthand recorded as stated (#504); not converted to an exact token count. The value is AWS's statement for its Bedrock listing; another seller of the same model may state a different figure.
  • Specifications only: no pricing, availability, capability, lifecycle or release-date assertion.

Raw API evidence ↗ · provider API · Claims: bedrock-gpt-oss-120b: pricing · bedrock-gpt-oss-120b: availability · 122 more claims about 61 other catalog entries · Retrieved · Checked · Review due · Confidence: A

  • Raw SHA-256: f1ac6a175fb27b3ad80d2c5d8970be8c2e5f957906349e52d15ec11d43e97896; collector aws-bedrock-price-list-json-1.
  • AWS Price List Bulk API offer file for Amazon Bedrock (us-east-1): offer version 20261111013037, publicationDate 2026-11-11T01:30:37Z.
  • Reviewed on-demand token prices only: each curated model's exact usagetypes in us-east-1, with service_tier "standard" for standard-tier models and with no service_tier attribute for the reviewed untiered models, in US dollars as the offer file states them (hence confidence A). A hosted listing and pricing observation only: no checkpoint, developer, license, context-window, modality or release-date assertions, and the usagetype is not a documented Bedrock model ID.
  • No Anthropic Claude price is published from this offer file: prices are read only from curated usagetypes, and no curated entry is an Anthropic model. (When the collector was reviewed on 2026-10-29, the file listed only legacy Claude models, all without a service tier.)
  • Availability rests on AWS's own offer file listing an on-demand price for the model in us-east-1.
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 18, 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.