# OpenAI: GPT OSS 120b

> OpenAI's open-weight 120B reasoning model, hosted by European providers. Good at step-by-step problem solving and tool use, with three reasoning levels and a 128k context.

- Model ID: `openai/gpt-oss-120b`
- Maker: OpenAI (`openai`)
- Context length: 131,072 tokens
- Input: text
- Output: text
- Capabilities: tool calling, structured output, and reasoning
- Page: https://tokenlane.de/models/openai/gpt-oss-120b

## Providers

| Providers | Data centers | Sovereign EU | Zero data retention |
|---|---|---|---|
| OVHcloud | FR | yes | yes |
| IONOS | DE | yes | yes |
| Scaleway | FR | yes | no |

## Usage

- Base URL: `https://api.tokenlane.de/v1` (OpenAI- and OpenRouter-compatible)
- Authentication: `Authorization: Bearer $TOKENLANE_API_KEY`
- Guide: https://tokenlane.de/docs/guides/text-and-chat.md?lang=en
- Machine-readable catalogue: `GET https://api.tokenlane.de/v1/models?output_modalities=all` (public, no key)
- Documentation index for agents: https://tokenlane.de/llms.txt

```bash
curl https://api.tokenlane.de/v1/chat/completions \
  -H "Authorization: Bearer $TOKENLANE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-oss-120b","messages":[{"role":"user","content":"Hello"}]}'
```

_Catalogue snapshot: 2026-11-19T13:10:34.963Z_
