gpt-oss-20b

OpenAI · On OpenRouter since August 5, 2025 · Pinned version id: openai/gpt-oss-20b

Price

$0.034

mixed / 1M tokens

Mixed price per 1M tokens: 3 input tokens to 1 output token.

in $0.017 · out $0.085 · Cached input $0.0085

via Darkbloom

Models that think before they answer can use many more output tokens, so your real cost can be higher than the figure shown.

US dollars per million tokens, converted to your currency at the NBP rate.

Tasks, with the evidence

Each line names the measurement it rests on. A task that is not listed has no measurement or declared feature we can show.

Writing code

Measured by a third party

Coding Index: 20.7 · Rank 65 of 86, among scored models · Artificial Analysis, read November 18, 2026

Cost of this job: $0.02

Models that score at least as high for less in this scenario: 2

Agents that use tools

Measured by a third party

Agentic Index: 1.2 · Rank 50 of 64, among scored models · Artificial Analysis, read November 18, 2026

Cost of this job: $0.14

Models that score at least as high for less in this scenario: 2

Websites and apps

Measured by a third party

Websites: 840 · Rank 123 of 127, among scored models · Design Arena, read November 21, 2026

Cost of this job: <$0.01

Charts and graphics

Measured by a third party

Data visualization: 933 · Rank 107 of 112, among scored models · Design Arena, read November 21, 2026

Cost of this job: <$0.01

The size of each job is our assumption; the prices are real.

  • Writing code: Requests: 40. Input tokens per request: 30,000. Output tokens per request: 1,500. Share of input served from cache: 70%.
  • Agents that use tools: Requests: 200. Input tokens per request: 45,000. Output tokens per request: 2,500. Share of input served from cache: 75%.
  • Websites and apps; Charts and graphics: Requests: 8. Input tokens per request: 12,000. Output tokens per request: 10,000. Share of input served from cache: 30%.

Thinking is billed as output tokens; a model that thinks longer costs more than this estimate. Ranks are among all models we list, including older ones.

Price by provider

The price used in the catalog is the vendor's own; when the vendor has no API of its own, it is the cheapest regular host.

ProviderInputOutputCached inputMixedNotes
Darkbloom Price used here $0.017$0.085 $0.0085 $0.034 fp8
AkashML $0.018$0.09 $0.009 $0.036 fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
CoreWeave $0.03$0.13 $0.03 $0.055 fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
DekaLLM $0.029$0.14 $0.029 $0.0568 bf16
DeepInfra $0.03$0.14 $0.015 $0.0575 bf16
Parasail $0.03$0.15 $0.02 $0.06 fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
SiliconFlow $0.04$0.18 No data $0.075 fp8
Amazon Bedrock $0.07$0.15 No data $0.09 EU
Show all providers: 11
  • Amazon Bedrock: $0.07 / $0.15 · $0.09
  • Groq: $0.075 / $0.30 · $0.1312
  • PrimeIntellect: $0.20 / $0.30 · $0.225

Other pricing modes

Specifications

Context window
131k
Max output
118k
Accepts
text
Answers with
text
Tools
Yes
Structured output
Yes
Reasoning
Always on
Thinking effort levels: low, medium, and high
Weights on Hugging Face
Hugging Face A Hugging Face repository is linked. We did not check the licence; read it before you build on it.
Knowledge cutoff
June 30, 2024
On OpenRouter since
August 5, 2025
Price check
one source

As listed by OpenRouter. "Not listed" means OpenRouter does not list it for this model.

Benchmark scores

Scores come from third parties and are relayed by OpenRouter. We do not run the tests. Higher is better.

SourceScoreRank among scored
Coding Index
Artificial Analysis, read November 18, 2026
20.7Rank 65 of 86, among scored models
Agentic Index
Artificial Analysis, read November 18, 2026
1.2Rank 50 of 64, among scored models
Websites
Design Arena, read November 21, 2026
840Rank 123 of 127, among scored models
Data visualization
Design Arena, read November 21, 2026
933Rank 107 of 112, among scored models

Intelligence, Coding and Agentic indices: Artificial Analysis (artificialanalysis.ai). Design categories: Design Arena (designarena.ai). Both are relayed by the OpenRouter public model list and were read on November 21, 2026. We compute ranks, tiers and costs from these numbers; the sources have not reviewed them. Scores belong to the model, not to the route it is served on.

Artificial Analysis · Design Arena · Relayed by OpenRouter. opens in a new tab

Sources and dates

Prices: OpenRouter routes and a second price table, checked November 21, 2026. Specifications: OpenRouter, November 21, 2026. Exchange rate: NBP, November 20, 2026. Benchmarks: Artificial Analysis and Design Arena via OpenRouter.