Model•active
gpt-oss-120b
gpt-oss-120b is OpenAI's 117B-parameter open-weight reasoning model for agentic and coding workloads, released under the Apache 2.0 license.
Official siteVerified Oct 3, 2026
Overview
The model is text-only, supports up to a 128K context, configurable reasoning effort, function calling, structured outputs, web-search and Python-tool workflows, and can be self-hosted or served by third-party inference providers.
Model specifications
- Family
- gpt-oss
- Context
- 131,072 tokens
- Input
- Text
- Output
- Text
- Open weights
- Yes
- Capabilities
- Reasoning, Tool Use, Function Calling, Structured Output, Web Search, Code Execution