# GPT OSS 120B: AI model fact sheet

- **Provider:** openai
- **Released:** 2025-08-05
- **Context window:** 131,072 tokens
- **Parameters:** 117B total (5.1B active per forward pass)
- **API pricing:** $0.18 / 1M input, $0.80 / 1M output
- **OpenRouter ID:** openai/gpt-oss-120b
- **Capabilities:** conversation, reasoning, code-generation, analysis, tool-use, function-calling

OpenAI's first open-weight model since GPT-2, featuring 117B parameters with MoE architecture. Designed for high-reasoning, agentic, and general-purpose production use cases with configurable reasoning depth and native tool use.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| Codeforces | Outperforms o3-mini |
| MMLU | Matches/exceeds o4-mini |
| HLE | Matches/exceeds o4-mini |
| TauBench | Matches/exceeds o4-mini (tool calling) |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/gpt-oss-120b