gpt-oss-120b
Hugging Face (openai) Open weights
The catch: Text only, needs a single 80GB GPU (H100 or MI300X class), and must be prompted in OpenAI's harmony format or it will not work correctly.
| Access | Open weights |
|---|---|
| Free limits | Free to download and self-host; you pay only for your own compute. Apache 2.0, so no user cap. 117B total parameters, 5.1B active (mixture of experts). |
| Modality | text, code |
| Credit card | Not required |
| Commercial use | Allowed |
| Trains on your data | – |
| Licence or terms | Apache-2.0 |
| Context window | 131,072 tokens |
| Model id | openai/gpt-oss-120b |
| Base URL | – |
| Last checked | 2 Oct 2026 |
How to use gpt-oss-120b
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Quickstart
vllm serve openai/gpt-oss-120b
Paste into Claude Code
I want to run the open-weight model "gpt-oss-120b" (openai/gpt-oss-120b) for my project. Please: 1. Check the model card and tell me the hardware it needs and the simplest way to serve it (vLLM, SGLang, Ollama or a hosted endpoint). 2. Give me a minimal working setup and a test request. 3. Tell me the licence terms for commercial use. 4. If a cheaper or smaller variant would do the job, mention it.
Before you ship on it
- Text only, needs a single 80GB GPU (H100 or MI300X class), and must be prompted in OpenAI's harmony format or it will not work correctly.
- Apache 2.0 (HF repo LICENSE; the card calls it ideal for commercial deployment). The repo's USAGE_POLICY only asks users to comply with all applicable law.
- Free to run means you pay for the GPUs, the serving stack and the on-call.
Questions
Is gpt-oss-120b free?
Yes. Open weights offers it as open weights, with these limits: Self-host free · Apache-2.0. No credit card is needed.
Can I use gpt-oss-120b commercially?
Yes, under Apache-2.0. Check the current terms before you ship.
How do I start with gpt-oss-120b?
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Source: huggingface.co/openai/gpt-oss-120b, checked 2 Oct 2026.