gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
OpenAI: gpt-oss-120b — OpenAI. Context window 131,072 tokens. API pricing (per 1M tokens): Input $0.037, Output $0.17. License: Proprietary. LMArena 1,365. GPQA Diamond 75.8%.
| Provider | OpenAI |
|---|---|
| API model ID | openai/gpt-oss-120b |
| Tier | Mid |
| Context window | 131,072 tokens |
| Max output | 117,964 tokens |
| License | Proprietary |
| API pricing (per 1M tokens) · Input | $0.037 |
| API pricing (per 1M tokens) · Output | $0.17 |
| LMArena | 1,365 (gpt-oss-120b) |
| GPQA Diamond | 75.8% |
LMArena (CC-BY 4.0, best reasoning setting, 2026-10-02) · GPQA Diamond: Epoch AI (CC-BY 4.0)
Compare in the full catalog