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

# DeepReasoning

> Pairs DeepSeek R1 chain-of-thought reasoning with Anthropic Claude creative and code generation behind a unified, data-controlled interface.

![DeepReasoning](https://media.empiriolabs.ai/model-logos/deepreasoning.png)

[WinFunc](/providers/winfunc) · Text Generation

`POST /v1/chat/completions`

Pairs DeepSeek R1 chain-of-thought reasoning with Anthropic Claude creative and code generation behind a unified, data-controlled interface.

## At a glance

| Field               | Value                                                                                                                       |
| ------------------- | --------------------------------------------------------------------------------------------------------------------------- |
| Model id            | `deepreasoning`                                                                                                             |
| Model release date  | 2025-01-26                                                                                                                  |
| Input modalities    | Text                                                                                                                        |
| Output modalities   | Text                                                                                                                        |
| Context window      | -                                                                                                                           |
| Weight precision    | -                                                                                                                           |
| Max output tokens   | 32,000                                                                                                                      |
| Features            | reasoning, thinking                                                                                                         |
| Native inference    | No                                                                                                                          |
| New                 | No                                                                                                                          |
| Structured output   | Not supported                                                                                                               |
| Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/deepreasoning:generateContent` |

## Pricing

| Charge                                | Spec                  | Rate                      |
| ------------------------------------- | --------------------- | ------------------------- |
| R1-0528 + Claude Sonnet 5.5 (Default) | per 1K tokens         | In \$0.012 / Out \$0.058  |
| R1-0528 + Claude Haiku 5.5            | per 1K tokens         | In \$0.0048 / Out \$0.023 |
| R1-0528 + Claude Opus 5.5             | per 1K tokens         | In \$0.019 / Out \$0.092  |
| Web Search (Linkup)                   | per call when invoked | \$0.013                   |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "deepreasoning", "messages": [{"role":"user","content":"Hello"}]}'
```

## Parameters

| Parameter            | Type    | Required | Default               | Description                                                                                                                                                                                                                                                                                                                                                                                                    |
| -------------------- | ------- | -------- | --------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `temperature`        | number  | no       | `0.7`                 | Sampling temperature. Applies to the R1 reasoning stage. · Range: 0 – 2                                                                                                                                                                                                                                                                                                                                        |
| `top_p`              | number  | no       | `0.9`                 | Nucleus sampling. Applies to the R1 reasoning stage. · Range: 0 – 1                                                                                                                                                                                                                                                                                                                                            |
| `max_tokens`         | number  | no       | `8192`                | Maximum output tokens for the Claude synthesis stage. · Range: 1 – 32000                                                                                                                                                                                                                                                                                                                                       |
| `anthropic_model`    | enum    | no       | `"claude-sonnet-5-5"` | Choose the Claude model to pair with DeepSeek R1 0528 reasoning. The R1 model produces the chain-of-thought; the Claude model synthesizes the final answer. Claude Opus 5.5 also thinks before it answers, and its thinking counts toward max_tokens. An unknown or retired model returns a 400 error that lists the models you can use. · Allowed: `claude-sonnet-5-5`, `claude-haiku-5-5`, `claude-opus-5-5` |
| `web_search_linkup`  | boolean | no       | false                 | Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds \$0.013 per call when invoked on top of the model's normal token cost. Disabled by default.                                                                                                                            |
| `disable_formatting` | boolean | no       | false                 | Return the answer without the Sources list that web search adds.                                                                                                                                                                                                                                                                                                                                               |

## Notes

R1-0528 reasoning paired with one of: Claude Sonnet 5.5 (default), Haiku 5.5, Opus 5.5.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/deepreasoning`.