# GPT-OSS 120B

GPT-OSS 120B is a model from OpenAI with open weights, first recorded on 17 Sep 2026; its release date is not established. The context window is 131,072 tokens. The maximum output is 131,072 tokens. Pricing is $0.15 per million input tokens and $0.60 per million output tokens.

- Developer: OpenAI
- Id: openai/gpt-oss-120b
- Sighting: 2026-09-17T14:01:09.814Z
  - [evidence link](https://huggingface.co/openai/gpt-oss-120b)
- Status: Released
- Open weights: 2025-08-05
  - [evidence link](https://openai.com/index/introducing-gpt-oss)
  - [evidence link](https://help.openai.com/en/articles/9624314-model-release-notes)
  - [evidence link](https://openai.com/index/introducing-gpt-oss)
- Weights version: 2025-08-04
  - [evidence link](https://huggingface.co/api/models/openai/gpt-oss-120b/paths-info/b5c939de8f754692c1647ca79fbf85e8c1e70f8a)
- Canonical: https://alexgetman.com/models/openai/gpt-oss-120b-392/

## Questions

### What is the context window of GPT-OSS 120B?

The context window is 131,072 tokens. The maximum output is 131,072 tokens.

### How much does GPT-OSS 120B cost?

Pricing is $0.15 per million input tokens and $0.60 per million output tokens. Cached input is $0.075 per million.

### Are the weights of GPT-OSS 120B publicly available?

Yes. OpenAI publishes the weights.

### When was GPT-OSS 120B released?

Its release date is not established. Signal Forge first recorded it on 17 Sep 2026.

## Evidence links

- [review](https://developers.openai.com/api/docs/models/gpt-oss-120b)
- [openai-model-release-notes](https://help.openai.com/en/articles/9624314-model-release-notes)
- [hf-author-artifacts:openai](https://huggingface.co/api/models/openai/gpt-oss-120b/paths-info/b5c939de8f754692c1647ca79fbf85e8c1e70f8a)
- [huggingface-router](https://huggingface.co/openai/gpt-oss-120b)
- [openai-articles](https://openai.com/index/introducing-gpt-oss)
- [openrouter](https://openrouter.ai/openai/gpt-oss-120b)
- [openrouter](https://openrouter.ai/openai/gpt-oss-120b:batch)

## Signals