GPT OSS 120B
Extremely capable general-purpose LLM with strong, controllable reasoning capabilities.
text → text · made by OpenAI
$0.03→$0.17per Mtok in / out
Nous Research · 29 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Offered at no charge, which is not the same as cheap: a free lane carries a rate limit and can be withdrawn.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.
- Cerebras
- Groq
Sold by 73 ways
| Seller | Lane | Rate |
|---|---|---|
| Writer api | standard | $0.04per Mtok in$0.18per Mtok outdev.writer.com · read 2026-08-25 |
| Google Vertex AI 0 ways | $0.045per Mtok in$0.18per Mtok out | |
| Google Vertex AI cloudnot on the seller's list today | batch | $0.045per Mtok in$0.18per Mtok outcloud.google.com · read 2026-08-24 |
| Crusoe cloud | standard | $0.05per Mtok in$0.2per Mtok out$0.05per Mtok cachedmodels.dev · read 2026-09-16 |
| DigitalOcean cloud | standard | $0.055per Mtok in$0.39per Mtok out$0.02per Mtok cachedmodels.dev · read 2026-09-16 |
| Databricks cloud | standard | $0.072per Mtok in$0.28per Mtok out$0.15per Mtok cached$0.15per Mtok cache writemodels.dev · read 2026-09-16 |
| Groq 0 ways | $0.075per Mtok in$0.3per Mtok out | |
| Groq apinot on the seller's list today | batch | $0.075per Mtok in$0.3per Mtok outconsole.groq.com · read 2026-08-25 |
| Google Vertex AI cloud | standard | $0.09per Mtok in$0.36per Mtok outcloud.google.com · read 2026-08-24 |
| AWS Bedrock cloud | standard | $0.15per Mtok in$0.6per Mtok outmodels.dev · read 2026-09-16 |
| Groq api | standard | $0.15per Mtok in$0.6per Mtok out$0.075per Mtok cachedconsole.groq.com · read 2026-08-25 |
| Microsoft Azure AI cloud | standard | $0.15per Mtok in$0.6per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| IBM watsonx cloud | standard | $0.16per Mtok in$0.64per Mtok outmodels.dev · read 2026-09-16 |
| IBM watsonx.ai cloud | standard | $0.16per Mtok in$0.64per Mtok outibm.com · read 2026-08-25 |
| Thinking Machines Lab api | training | $0.33per Mtok in$0.84per Mtok out$0.066per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25 |
| Thinking Machines Lab api | training-128k | $0.78per Mtok in$1.94per Mtok out$0.16per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25 |
| Cerebras 2 ways | $0.35per Mtok in$0.75per Mtok out | |
| Cerebras aggregator | free | $0per Mtok in$0per Mtok outinference-docs.cerebras.ai · read 2026-09-16 |
| Cerebras aggregator | standard | $0.35per Mtok in$0.75per Mtok outcerebras.ai · read 2026-08-25 |
| Groq aggregator | free | $0per Mtok in$0per Mtok outconsole.groq.com · read 2026-09-16 |
| Nous Research 2 ways | $0.03per Mtok in$0.17per Mtok out$0.03per Mtok cached | |
| Nous Research aggregator | standard | $0.03per Mtok in$0.17per Mtok out$0.03per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Nous Research aggregator | batch | $0.15per Mtok in$0.6per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 24 ways | $0.037per Mtok in$0.17per Mtok out | |
| OpenRouter aggregator | akashml/bf16 | $0.03per Mtok in$0.17per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-26 |
| OpenRouter aggregator | coreweave/fp4 | $0.03per Mtok in$0.17per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | dekallm/bf16 | $0.03per Mtok in$0.18per Mtok outopenrouter.ai · read 2026-09-12 |
| OpenRouter aggregator | standard | $0.037per Mtok in$0.17per Mtok outopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | crusoe/bf16 | $0.05per Mtok in$0.25per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | novita/fp4 | $0.05per Mtok in$0.25per Mtok outopenrouter.ai · read 2026-08-26 |
| OpenRouter aggregator | mancer/fp8 | $0.055per Mtok in$0.5per Mtok outopenrouter.ai · read 2026-09-09 |
| OpenRouter aggregator | digitalocean | $0.06per Mtok in$0.42per Mtok out$0.012per Mtok cachedopenrouter.ai · read 2026-09-15 |
| OpenRouter aggregator | google-vertex/global | $0.09per Mtok in$0.36per Mtok outopenrouter.ai · read 2026-09-06 |
| OpenRouter aggregator | baseten/fp4 | $0.1per Mtok in$0.5per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | parasail/fp4 | $0.1per Mtok in$0.75per Mtok out$0.055per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | sambanova | $0.14per Mtok in$0.95per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | amazon-bedrock | $0.15per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | amazon-bedrock/eu-west-1 | $0.15per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | batch | $0.15per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-08-29 |
| OpenRouter aggregator | deepinfra/turbo | $0.15per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | groq | $0.15per Mtok in$0.6per Mtok out$0.075per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | mara | $0.15per Mtok in$0.75per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | nebius/fp4 | $0.15per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | phala | $0.15per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | siliconflow/fp8 | $0.15per Mtok in$0.6per Mtok out$0.075per Mtok cachedopenrouter.ai · read 2026-09-11 |
| OpenRouter aggregator | together | $0.15per Mtok in$0.6per Mtok outopenrouter.ai · read 2026-08-27 |
| OpenRouter aggregator | deepinfra/fp8 | $0.2per Mtok in$0.95per Mtok outopenrouter.ai · read 2026-09-07 |
| OpenRouter aggregator | cerebras/fp16 | $0.35per Mtok in$0.75per Mtok out$0.35per Mtok cachedopenrouter.ai · read 2026-08-25 |
| DeepInfra aggregator | standard | $0.037per Mtok in$0.17per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 11 ways | $0.25per Mtok in$0.69per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.037per Mtok in$0.17per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | novita | $0.05per Mtok in$0.25per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | ovhcloud | $0.09per Mtok in$0.47per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | baseten | $0.1per Mtok in$0.5per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | nscale | $0.1per Mtok in$0.4per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | fireworks-ai | $0.15per Mtok in$0.6per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | groq | $0.15per Mtok in$0.75per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | together | $0.15per Mtok in$0.6per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | scaleway | $0.17per Mtok in$0.68per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.25per Mtok in$0.69per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregator | cerebras | $0.35per Mtok in$0.75per Mtok outrouter.huggingface.co · read 2026-08-25 |
| IO.NET aggregator | standard | $0.04per Mtok in$0.4per Mtok out$0.02per Mtok cached$0.08per Mtok cache writemodels.dev · read 2026-09-16 |
| Novita AI aggregator | standard | $0.05per Mtok in$0.25per Mtok outapi.novita.ai · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.05per Mtok in$0.45per Mtok outmodels.dev · read 2026-09-16 |
| Venice AI aggregator | standard | $0.07per Mtok in$0.3per Mtok outmodels.dev · read 2026-09-16 |
| Baseten aggregator | standard | $0.1per Mtok in$0.5per Mtok outbaseten.co · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.15per Mtok in$0.6per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Fireworks AI 2 ways | $0.15per Mtok in$0.6per Mtok out$0.015per Mtok cached | |
| Fireworks AI aggregator | standard | $0.15per Mtok in$0.6per Mtok out$0.015per Mtok cacheddocs.fireworks.ai · read 2026-08-24 |
| Fireworks AI aggregator | priority | $0.18per Mtok in$0.72per Mtok out$0.018per Mtok cachedraw.githubusercontent.com · read 2026-09-16 |
| Nebius Token Factory aggregator | standard | $0.15per Mtok in$0.6per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| Requesty 3 ways | $0.15per Mtok in$0.6per Mtok out$0.015per Mtok cached | |
| Requesty aggregator | fireworks | $0.15per Mtok in$0.6per Mtok out$0.015per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | groq | $0.15per Mtok in$0.75per Mtok out$0.15per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | nebius | $0.15per Mtok in$0.6per Mtok out$0.15per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Together AI aggregator | standard | $0.15per Mtok in$0.6per Mtok outdocs.together.ai · read 2026-08-24 |
| SambaNova Cloud aggregator | standard | $0.22per Mtok in$0.59per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Cloudflare aggregator | standard | $0.35per Mtok in$0.75per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Cloudflare aggregatornot on the seller's list today | sandbox | $0.35per Mtok in$0.75per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Vercel AI Gateway aggregator | standard | $0.35per Mtok in$0.75per Mtok outvercel.com · read 2026-08-25 |
| Vercel AI Gateway aggregatornot on the seller's list today | sandbox | $0.35per Mtok in$0.75per Mtok outvercel.com · read 2026-08-25 |
Measured 33 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 14thof 18 | Algotune — Epoch AI | Score (high) | 1.41 |
| 19thof 25 | SWE-Bench Pro (Public Dataset) | Resolve Rate | 16.2 |
| 20thof 61 | AIME 2025 | Accuracy (± 95% CI) (high) | 90 |
| 24thof 26 | Surface evolver bench — Epoch AI | Mean score | 0.25 |
| 26thof 49 | Lech mazur writing — Epoch AI | Mean score | 7.71 |
| 26thof 50 | Metr time horizons — Epoch AI | average_score | 0.566 |
| 43rdof 69 | Aider polyglot coding leaderboard | Percent correct (high) | 41.8 |
| 46thof 72 | Aider polyglot — Epoch AI | Percent correct (high) | 41.8 |
| 58thof 60 | Vending bench 2 — Epoch AI | Score | -21.532 |
| 59thof 65 | Apex agents — Epoch AI | Pass@1 score | 0.047 |
| 69thof 290 | OTIS Mock AIME 2024-2025 | mean_score (high) | 88.889 |
| 73rdof 170 | Weirdml — Epoch AI | Accuracy (high) | 48.17 |
| 78thof 161 | Dtbench — Epoch AI | Accuracy (high) | 76.27 |
| 85thof 123 | Lmca — Epoch AI | Score (high) | 22.14 |
| 86thof 112 | Ale bench — Epoch AI | Performance | 575.62 |
| 88thof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 14.2 |
| 91stof 222 | Chess puzzles — Epoch AI | mean_score (high) | 20 |
| 95thof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.221 |
| 103rdof 143 | Artificial Analysis · Agentic Index | Index | 6.2 |
| 110thof 177 | Critpt — Epoch AI | Accuracy (high) | 1.143 |
| 123rdof 168 | Scicode — Epoch AI | Score (high) | 38.889 |
| 126thof 127 | Mystery game puzzles — Epoch AI | mean_score (medium) | 2 |
| 130thof 184 | Artificial Analysis · Coding Index | Index | 30.4 |
| 136thof 147 | Design Arena · 3d (models) | Elo | 929 |
| 136thof 155 | Design Arena · gamedev (models) | Elo | 1015 |
| 140thof 152 | Design Arena · dataviz (models) | Elo | 1002 |
| 142ndof 150 | Design Arena · uicomponent (models) | Elo | 942 |
| 147thof 156 | Design Arena · codecategories (models) | Elo | 978 |
| 148thof 313 | GPQA Diamond | mean_score (high) | 75.758 |
| 151stof 162 | Design Arena · website (models) | Elo | 980 |
| 166thof 302 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index (high) | 12 |
| 172ndof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.187 |
| 435thof 656 | Epoch capabilities index — Epoch AI | ECI Score (high) | 140.13 |
About
GPT OSS 120B — a text model from OpenAI, sold by 29 companies from $0.03 in and $0.17 out per million tokens, placed 69th of 290 on OTIS Mock AIME 2024-2025.
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, code and agents. 29 companies sell it. The cheapest is $0.03 in and $0.17 out per million tokens at Nous Research. Beside the standard rate there are separately routed, faster, batch and regional lanes. It has been measured on 33 boards, and stands best at 69th of 290 on OTIS Mock AIME 2024-2025.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 131,072 tokens
- Published
- 1970
- Parameters
- 117 billion
- Licence
- not read
- Sellers
- 29
- Maker's own price
- not read
- Price
- $0.03 in and $0.17 out per million tokens — Nous Research
- Boards
- 33
- Best place
- 69th of 290 — OTIS Mock AIME 2024-2025
Known as 9 names
GPT OSS 120B (high)gpt-oss-120bOpenAI GPT OSS 120Bopenai/gpt-oss-120b@cf/openai/gpt-oss-120bfireworks/gpt-oss-120bgroq/openai/gpt-oss-120bnebius/openai/gpt-oss-120bopenai/gpt-oss-120b:peft:131072