gpt-oss-120b
Language modelOpen weightsCard summarizedMost powerful open-weight model, fits into an H100 GPU
● Re-checked 12 Oct 2026 · 113 facts · 0 correctionsSource: gpt-oss-120b & gpt-oss-20b Model Card (35 pp)
Use it via API
Where to call it
- Self-host (weights)
openai/gpt-oss-120b - OpenAI API docs
gpt-oss-120b
Supports
- Streaming
- Structured outputs
- Reasoning control
- Tool calling
- Web search
- Fine-tuning
Good for
- Agentic workflows with strong instruction following
- Web browsing (search/open), Python in a stateful Jupyter environment, and developer-defined functions
- Adjustable reasoning effort for tasks that don't need deep reasoning
Overview
gpt-oss-120b
Most powerful open-weight model, fits into an H100 GPU
- Cost
- $0.037 host
- Context
- 128K
- Cheapest host
- $0.037 / $0.17
- Max output
- 128K
- Knows up to
- June 2024
- Released
- 5 Aug 2025
gpt-oss-120b is the larger of OpenAI's two open-weight reasoning models: a text-only Mixture-of-Experts transformer with 116.8B total and 5.1B active parameters, released under Apache 2.0. It is built for agentic workflows with tool use, Structured Outputs, adjustable reasoning effort and full chain-of-thought. OpenAI reports it beats o3-mini and approaches o4-mini on its main benchmarks, and that even adversarially fine-tuned it did not reach High capability in biology/chemistry or cyber. §1, §2
openai/gpt-oss-120b- Input / output per 1M
- $0.037 / $0.17 via DeepInfra
- Context window
- 128K
- Max output
- 128K
- Knows up to
- June 2024
- Reasoning
- Configurable (low / medium / high)
- Weights
- Open · Apache 2.0 (plus gpt-oss usage policy)
About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses OpenAI's gpt-oss-120b & gpt-oss-20b Model Card. Every claim carries its source page.