> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mixroute.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepSeek V3.2 Speciale

> A reasoning-intensive DeepSeek V3.2 variant for difficult text, mathematical, and analytical tasks.

A reasoning-intensive DeepSeek V3.2 variant for difficult text, mathematical, and analytical tasks.

## Model Information

| Field      | Description               |
| ---------- | ------------------------- |
| `model`    | deepseek-v3.2-speciale    |
| `endpoint` | POST /v1/chat/completions |

## Capabilities and Usage

* Speciale is a distinct reasoning variant, not the current DeepSeek Flash model.
* Do not assume the tool-calling support of standard V3.2 applies to Speciale. Use text requests without tools.

## Request Example

Set `MIXROUTE_API_KEY` before making the request.

```bash theme={null}
curl --request POST "https://api.mixroute.ai/v1/chat/completions" \
  --header "Authorization: Bearer $MIXROUTE_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "deepseek-v3.2-speciale",
  "messages": [
    {
      "role": "user",
      "content": "Explain the tradeoffs of database indexes."
    }
  ],
  "max_tokens": 1024
}'
```

## Request Fields

| Field        | Description                                           |
| ------------ | ----------------------------------------------------- |
| `model`      | Required. Use the exact model ID above.               |
| `messages`   | Required conversation messages with role and content. |
| `max_tokens` | Optional output-token budget.                         |

Complete request format: [chat-openai](/en/api-reference/endpoint/chat-openai).