gpt-oss-120b
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...
The figures
- Made by
- OpenAI
- Model ID
- openai/gpt-oss-120b
- Input
- $0.037 per million tokens
- Output
- $0.17 per million tokens
- Context window
- 131K tokens
- Longest answer
- 118K tokens
- Takes in
- text
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- No
- Open weights
- Yes
- Released
- 5 Aug 2025
Read on 3 Oct 2026.