GPT-OSS 120B by OpenAI demonstrates fast output speed, competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Artificial Analysis composite intelligence score across 10 sub-benchmarks
Artificial Analysis (via OpenRouter)Coding Benchmarks
Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Artificial Analysis composite coding score
Artificial Analysis (via OpenRouter)Reasoning Benchmarks
Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Artificial Analysis composite score for multi-step tool-using tasks
Artificial Analysis (via OpenRouter)Speed Benchmarks
Cost Benchmarks
Context Benchmarks
Available from 55 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 11 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Kenari | $0 | $0 | — | 131K | — |
| Nvidia | $0 | $0 | — | 128K | — |
| Pendra | $0 | $0 | — | 131K | — |
| QVAC | $0 | $0 | — | 131K | — |
| Kilo Gateway | $0.03 | $0.17 | $0.03 | 131K | — |
| OrcaRouter | $0.03 | $0.17 | — | 131K | — |
| Weights & Biases | $0.03 | $0.17 | $0.03 | 131K | — |
| DevPass (LLM Gateway) | $0.032 | $0.14 | $0.032 | 131K | — |
| LLM Gateway | $0.032 | $0.14 | $0.032 | 131K | — |
| Deep Infra | $0.037 | $0.17 | — | 131K | Supported |
| OpenRouter | $0.037 | $0.17 | — | 131K | Supported |
| IO.NET | $0.04 | $0.4 | $0.02 | 131K | — |
| TensorX | $0.04 | $0.2 | $0.01 | 131K | — |
| Crusoe | $0.05 | $0.2 | $0.05 | 131K | — |
| DInference | $0.0675 | $0.27 | — | 131K | — |
| Databricks | $0.072 | $0.28 | — | 131K | — |
| Abacus | $0.08 | $0.44 | — | 128K | — |
| Cortecs | $0.089 | $0.446 | $0.01 | 131K | — |
| Merge Gateway | $0.09 | $0.36 | — | 131K | — |
| OVHcloud AI Endpoints | $0.09 | $0.47 | — | 131K | — |
| Vertex | $0.09 | $0.36 | — | 131K | Supported |
| submodel | $0.1 | $0.5 | — | 131K | — |
| Synthetic | $0.1 | $0.1 | $0.1 | 131K | — |
| Vercel AI Gateway | $0.1 | $0.5 | — | 131K | Supported |
| OpenReason | $0.1055 | $0.422 | — | 131K | — |
| CoralBricks | $0.12 | $0.6 | $0 | 131K | — |
| ai& | $0.15 | $0.6 | — | 131K | — |
| AKI.IO | $0.15 | $0.55 | — | 128K | — |
| Amazon Bedrock | $0.15 | $0.6 | — | 128K | Supported |
| FastRouter | $0.15 | $0.6 | — | 131K | — |
| Fireworks AI | $0.15 | $0.6 | $0.015 | 131K | Supported |
| FrogBot | $0.15 | $0.6 | — | 131K | — |
| Groq | $0.15 | $0.6 | $0.075 | 131K | Supported |
| Nebius Token Factory | $0.15 | $0.6 | $0.015 | 131K | — |
| Neon | $0.15 | $0.6 | — | 131K | — |
| Pioneer | $0.15 | $0.6 | $0.015 | 131K | — |
| Scaleway | $0.15 | $0.6 | — | 128K | — |
| Tinfoil | $0.15 | $0.6 | — | 131K | — |
| Together AI | $0.15 | $0.6 | — | 131K | Supported |
| watsonx.ai | $0.159 | $0.636 | — | 131K | — |
| Charm Hyper | $0.168 | $0.66 | $0.084 | 128K | — |
| SCX.ai | $0.17 | $0.55 | — | 131K | — |
| Eden AI | $0.17388 | $0.75348 | — | 131K | — |
| GreenPT | $0.228 | $0.798 | — | 131K | — |
| evroc | $0.23 | $0.92 | — | 66K | — |
| Hugging Face | $0.25 | $0.69 | — | 131K | Supported |
| Cerebras | $0.35 | $0.75 | — | 131K | Supported |
| Cloudflare Workers AI | $0.35 | $0.75 | — | 128K | Supported |
| Impossibl | $0.35 | $0.75 | — | 131K | — |
| NanoGPT | $0.35 | $0.75 | — | 128K | — |
| Privatemode AI | $0.4969 | $1.9644 | $0.0462 | 128K | — |
| STACKIT | $0.53 | $0.76 | — | 131K | — |
| Regolo AI | $1 | $4.2 | — | 128K | — |
| Ollama Cloud | — | — | — | 131K | — |
| Qiniu | — | — | — | 128K | — |
GPT-OSS 120B — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare GPT-OSS 120B With
GPT-OSS 120B — Frequently Asked Questions
How much does GPT-OSS 120B cost?
GPT-OSS 120B costs $0.04 per 1M input tokens and $0.17 per 1M output tokens. This makes it one of the more affordable models.
How fast is GPT-OSS 120B?
GPT-OSS 120B generates output at 339 tokens per second, which is very fast compared to other models. The time to first token is 440 ms.
What is the context window of GPT-OSS 120B?
GPT-OSS 120B has a context window of 131K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created GPT-OSS 120B?
GPT-OSS 120B was created by OpenAI. It is classified as a open source model in our catalogue.
Is GPT-OSS 120B open source?
Yes, GPT-OSS 120B is an open-source model. The model weights are publicly available for download and self-hosting.