GPT-OSS 20B 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
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 34 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 9 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Kenari | $0 | $0 | — | 131K | — |
| LMStudio | $0 | $0 | — | 131K | — |
| Nvidia | $0 | $0 | — | 131K | — |
| QVAC | $0 | $0 | — | 131K | — |
| Kilo Gateway | $0.02 | $0.1 | — | 131K | — |
| Deep Infra | $0.03 | $0.14 | — | 131K | Supported |
| IO.NET | $0.03 | $0.14 | $0.015 | 64K | — |
| OpenRouter | $0.03 | $0.13 | $0.03 | 131K | Supported |
| Weights & Biases | $0.03 | $0.13 | $0.03 | 131K | — |
| DevPass (LLM Gateway) | $0.04 | $0.19 | $0.01 | 131K | — |
| LLM Gateway | $0.04 | $0.19 | $0.01 | 66K | — |
| Merge Gateway | $0.04 | $0.2 | $0.02 | 131K | — |
| Clarifai | $0.045 | $0.18 | — | 131K | — |
| Cortecs | $0.045 | $0.167 | — | 131K | — |
| Databricks | $0.05 | $0.2 | — | 131K | — |
| Eden AI | $0.05 | $0.2 | — | 131K | — |
| FastRouter | $0.05 | $0.2 | — | 131K | — |
| OVHcloud AI Endpoints | $0.05 | $0.18 | — | 131K | — |
| Together AI | $0.05 | $0.2 | — | 131K | Supported |
| Vercel AI Gateway | $0.05 | $0.2 | — | 131K | Supported |
| Amazon Bedrock | $0.07 | $0.3 | — | 128K | Supported |
| FrogBot | $0.07 | $0.2 | — | 131K | — |
| Impossibl | $0.07 | $0.3 | $0.035 | 131K | — |
| Neon | $0.07 | $0.3 | — | 131K | — |
| Pioneer | $0.07 | $0.3 | $0.035 | 131K | — |
| Vertex | $0.07 | $0.25 | $0.007 | 131K | Supported |
| Groq | $0.075 | $0.3 | $0.0375 | 131K | Supported |
| Hugging Face | $0.1 | $0.5 | — | 131K | Supported |
| STACKIT | $0.18 | $0.29 | — | 131K | — |
| Cloudflare Workers AI | $0.2 | $0.3 | — | 128K | Supported |
| NanoGPT | $0.2 | $0.3 | — | 128K | — |
| Regolo AI | $0.4 | $1.8 | — | 128K | — |
| Ollama Cloud | — | — | — | 131K | — |
| Qiniu | — | — | — | 128K | — |
GPT-OSS 20B — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare GPT-OSS 20B With
GPT-OSS 20B — Frequently Asked Questions
How much does GPT-OSS 20B cost?
GPT-OSS 20B costs $0.03 per 1M input tokens and $0.13 per 1M output tokens. This makes it one of the more affordable models.
How fast is GPT-OSS 20B?
GPT-OSS 20B generates output at 312 tokens per second, which is very fast compared to other models. The time to first token is 470 ms.
What is the context window of GPT-OSS 20B?
GPT-OSS 20B 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 20B?
GPT-OSS 20B was created by OpenAI. It is classified as a open source model in our catalogue.
Is GPT-OSS 20B open source?
Yes, GPT-OSS 20B is an open-source model. The model weights are publicly available for download and self-hosting.