GPT OSS 20B
A compact, open-weight language model optimized for low-latency and resource-constrained environments, including local and edge deployments.
text → text · made by OpenAI
$0.02→$0.1per Mtok in / out
Nous Research · 20 sellers
Free
Offered at no charge, which is not the same as cheap: a free lane carries a rate limit and can be withdrawn. The prices above are what you pay when it is not available to you.
- Groq
Sold by 48 ways
| Seller | Lane | Rate |
|---|---|---|
| Google Vertex AI 0 ways | $0.035per Mtok in$0.12per Mtok out | |
| Google Vertex AI cloudnot on the seller's list today | batch | $0.035per Mtok in$0.12per Mtok outcloud.google.com · read 2026-08-24 |
| Groq 0 ways | $0.037per Mtok in$0.15per Mtok out | |
| Groq apinot on the seller's list today | batch | $0.037per Mtok in$0.15per Mtok outconsole.groq.com · read 2026-08-25 |
| Databricks cloud | standard | $0.05per Mtok in$0.2per Mtok out$0.07per Mtok cached$0.07per Mtok cache writemodels.dev · read 2026-09-16 |
| DigitalOcean cloud | standard | $0.05per Mtok in$0.45per Mtok outmodels.dev · read 2026-09-16 |
| AWS Bedrock cloud | standard | $0.07per Mtok in$0.3per Mtok outmodels.dev · read 2026-09-16 |
| Google Vertex AI cloud | standard | $0.07per Mtok in$0.25per Mtok out$0.007per Mtok cachedcloud.google.com · read 2026-08-24 |
| Groq api | standard | $0.075per Mtok in$0.3per Mtok out$0.037per Mtok cachedconsole.groq.com · read 2026-08-25 |
| Thinking Machines Lab api | training | $0.18per Mtok in$0.45per Mtok out$0.036per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25 |
| Groq aggregator | free | $0per Mtok in$0per Mtok outconsole.groq.com · read 2026-09-16 |
| Nous Research aggregator | standard | $0.02per Mtok in$0.1per Mtok out$0.024per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 15 ways | $0.03per Mtok in$0.13per Mtok out$0.03per Mtok cached | |
| OpenRouter aggregatornot on the seller's list today | akashml/bf16 | $0.02per Mtok in$0.1per Mtok outopenrouter.ai · read 2026-09-02 |
| OpenRouter aggregator | akashml/fp4 | $0.02per Mtok in$0.1per Mtok outopenrouter.ai · read 2026-09-03 |
| OpenRouter aggregator | darkbloom/fp8 | $0.02per Mtok in$0.1per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | dekallm/bf16 | $0.029per Mtok in$0.14per Mtok outopenrouter.ai · read 2026-09-12 |
| OpenRouter aggregator | standard | $0.03per Mtok in$0.13per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | deepinfra/bf16 | $0.03per Mtok in$0.14per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | parasail/fp4 | $0.03per Mtok in$0.15per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | novita/fp4 | $0.04per Mtok in$0.15per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | phala | $0.04per Mtok in$0.15per Mtok outopenrouter.ai · read 2026-08-27 |
| OpenRouter aggregator | siliconflow/fp8 | $0.04per Mtok in$0.18per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | batch | $0.05per Mtok in$0.2per Mtok outopenrouter.ai · read 2026-08-29 |
| OpenRouter aggregator | together | $0.05per Mtok in$0.2per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | amazon-bedrock | $0.07per Mtok in$0.15per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | amazon-bedrock/eu-west-1 | $0.07per Mtok in$0.15per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregatornot on the seller's list today | fireworks | $0.07per Mtok in$0.3per Mtok out$0.035per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex/us-central1 | $0.07per Mtok in$0.25per Mtok outopenrouter.ai · read 2026-09-01 |
| OpenRouter aggregator | groq | $0.075per Mtok in$0.3per Mtok out$0.037per Mtok cachedopenrouter.ai · read 2026-08-25 |
| DeepInfra aggregator | standard | $0.03per Mtok in$0.14per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 7 ways | $0.1per Mtok in$0.5per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.03per Mtok in$0.14per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | novita | $0.04per Mtok in$0.15per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | nscale | $0.05per Mtok in$0.2per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | ovhcloud | $0.05per Mtok in$0.18per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | together | $0.05per Mtok in$0.2per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregatornot on the seller's list today | fireworks-ai | $0.07per Mtok in$0.3per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.1per Mtok in$0.5per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregator | groq | $0.1per Mtok in$0.5per Mtok outrouter.huggingface.co · read 2026-08-25 |
| IO.NET aggregator | standard | $0.03per Mtok in$0.14per Mtok out$0.015per Mtok cached$0.06per Mtok cache writemodels.dev · read 2026-09-16 |
| Novita AI aggregator | standard | $0.04per Mtok in$0.15per Mtok outapi.novita.ai · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.04per Mtok in$0.18per Mtok outmodels.dev · read 2026-09-16 |
| Clarifai aggregator | standard | $0.045per Mtok in$0.18per Mtok outmodels.dev · read 2026-09-16 |
| ElectronHub aggregator | standard | $0.05per Mtok in$0.2per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Together AI aggregator | standard | $0.05per Mtok in$0.2per Mtok outdocs.together.ai · read 2026-08-24 |
| Vercel AI Gateway aggregator | standard | $0.05per Mtok in$0.2per Mtok outai-gateway.vercel.sh · read 2026-08-25 |
| Fireworks AI aggregator | standard | $0.07per Mtok in$0.3per Mtok out$0.035per Mtok cacheddocs.fireworks.ai · read 2026-08-24 |
| Requesty 2 ways | $0.07per Mtok in$0.3per Mtok out$0.035per Mtok cached | |
| Requesty aggregator | fireworks | $0.07per Mtok in$0.3per Mtok out$0.035per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | groq | $0.1per Mtok in$0.5per Mtok out$0.1per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Cloudflare aggregator | standard | $0.2per Mtok in$0.3per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Cloudflare aggregatornot on the seller's list today | sandbox | $0.2per Mtok in$0.3per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
Measured 17 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 21stof 61 | AIME 2025 | Accuracy (± 95% CI) (high) | 89.17 |
| 87thof 112 | Ale bench — Epoch AI | Performance | 566.05 |
| 91stof 161 | Dtbench — Epoch AI | Accuracy (high) | 68 |
| 104thof 123 | Lmca — Epoch AI | Score (high) | 14.51 |
| 105thof 177 | Critpt — Epoch AI | Accuracy (high) | 1.429 |
| 108thof 170 | Weirdml — Epoch AI | Accuracy (high) | 40.93 |
| 124thof 143 | Artificial Analysis · Agentic Index | Index | 1.4 |
| 144thof 152 | Design Arena · dataviz (models) | Elo | 947 |
| 144thof 168 | Scicode — Epoch AI | Score (high) | 34.375 |
| 148thof 290 | OTIS Mock AIME 2024-2025 | mean_score (medium) | 65.278 |
| 149thof 184 | Artificial Analysis · Coding Index | Index | 20.7 |
| 157thof 162 | Design Arena · website (models) | Elo | 865 |
| 167thof 222 | Chess puzzles — Epoch AI | mean_score (medium) | 4 |
| 192ndof 302 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index (low) | 10 |
| 199thof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.034 |
| 202ndof 313 | GPQA Diamond | mean_score (medium) | 60.795 |
| 472ndof 656 | Epoch capabilities index — Epoch AI | ECI Score (high) | 137.82 |
About
GPT OSS 20B — a text model from OpenAI, sold by 20 companies from $0.02 in and $0.1 out per million tokens, placed 21st of 61 on AIME 2025.
It takes text and returns text, with a context window of 131,072 tokens. It was published in 1970. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning. Twenty companies sell it. The cheapest is $0.02 in and $0.1 out per million tokens at Nous Research. Beside the standard rate there are separately routed, regional and batch lanes. It has been measured on 17 boards, and stands best at 21st of 61 on AIME 2025.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 131,072 tokens
- Published
- 1970
- Parameters
- 21 billion
- Licence
- not read
- Sellers
- 20
- Maker's own price
- not read
- Price
- $0.02 in and $0.1 out per million tokens — Nous Research
- Boards
- 17
- Best place
- 21st of 61 — AIME 2025
Known as 7 names
GPT OSS 20B (high)OpenAI GPT OSS 20B@cf/openai/gpt-oss-20bopenai/gpt-oss-20bfireworks/gpt-oss-20bgroq/openai/gpt-oss-20bgpt-oss-20b