# Qwen: Qwen3 235b A22b 2507

> Large Qwen3 instruction model with 22 billion active parameters that answers directly without a reasoning phase. Strong at multilingual chat, summaries and tool calling, text only, with a context of 250,000 tokens.

- Model ID: `qwen/qwen3-235b-a22b-2507`
- Maker: Qwen (`qwen`)
- Context length: 250,000 tokens
- Input: text
- Output: text
- Capabilities: tool calling and structured output
- Price (EUR per 1M tokens): input 0.75, output 2.25
- Page: https://tokenlane.de/models/qwen/qwen3-235b-a22b-2507

## Providers

| Providers | Data centers | Sovereign EU | Zero data retention |
|---|---|---|---|
| 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":"qwen/qwen3-235b-a22b-2507","messages":[{"role":"user","content":"Hello"}]}'
```

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