# GPT OSS 20B: AI model fact sheet

- **Provider:** openai
- **Released:** 2025-08-05
- **Context window:** 131,072 tokens
- **Parameters:** 21B total (3.6B active per forward pass)
- **API pricing:** $0.02 / 1M input, $0.10 / 1M output
- **OpenRouter ID:** openai/gpt-oss-20b
- **Capabilities:** conversation, reasoning, code-generation, analysis, function-calling, tool-use, planning

OpenAI's efficient open-weight model featuring 21B parameters with MoE architecture, optimized for edge deployment and consumer hardware. Matches o3-mini performance while requiring only 16GB memory, making it ideal for on-device AI applications.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| MMLU | Matches o3-mini |
| Competition Mathematics | Outperforms o3-mini |
| Memory Requirements | 16GB |
| Context Length | 128K tokens |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/gpt-oss-20b