# DeepSeek: DeepSeek V4 PRO 0813

> DeepSeek's large flagship model for demanding reasoning, coding and agentic work. Supports tool calling, adjustable reasoning effort and a context of up to one million tokens.

- Model ID: `deepseek/deepseek-v4-pro-0813`
- Maker: DeepSeek (`deepseek`)
- Context length: 1,048,576 tokens
- Input: text
- Output: text
- Capabilities: tool calling, structured output, and reasoning
- Price (EUR per 1M tokens): input 1.823487, output 3.646974
- Page: https://tokenlane.de/models/deepseek/deepseek-v4-pro-0813

## Providers

| Providers | Data centers | Sovereign EU | Zero data retention |
|---|---|---|---|
| TensorX | IE, FI | no | yes |
| Lyceum | FR, FI, DE | no | yes |

## 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":"deepseek/deepseek-v4-pro-0813","messages":[{"role":"user","content":"Hello"}]}'
```

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