> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.beatapi.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.beatapi.io/_mcp/server.

# DeepSeek V4.1 Flash Free API

> DeepSeek V4.1 Flash Free exact free request reference.

# DeepSeek V4.1 Flash Free API

Use the exact free model ID `deepseek-v4.1-flash-free`. Input and output are \$0 in the public free price table. Select this ID explicitly: choosing a paid model is a separate, billable request.

Supported formats: `POST /v1/responses` / `POST /v1/chat/completions`. Other paid-family formats, context windows, media inputs and reasoning options are not free-route guarantees.

> **Note**
>
> Free access can be rate-limited or withdrawn; availability, duration and daily allowance are not guaranteed. The documented account limit is 1 successful request/minute before the first top-up and up to10/minute after. Check current model availability and account policy before relying on the route.

## First request

```typescript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.BEATAPI_API_KEY,
  baseURL: "https://api.beatapi.io/v1"
});

const completion = await client.chat.completions.create({
  model: "deepseek-v4.1-flash-free",
  messages: [
    { role: "user", content: "Design a resilient webhook retry strategy for a payments API." }
  ]
});

console.log(completion.choices[0].message.content);
```

```bash
curl https://api.beatapi.io/v1/responses \
  -H "Authorization: Bearer $BEATAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4.1-flash-free","input":"Explain this system clearly."}'
```

These code blocks are projected from the existing family reference, with the exact free ID and without paid-only options. Inspect returned usage and account limits; base-model benchmark results do not measure this free route.