> 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.

# MiMo V2.6 Pro UltraSpeed

> High-throughput build of the trillion-parameter flagship, matching its full-modality reasoning while generating output substantially faster.

![MiMo V2.6 Pro UltraSpeed](https://media.empiriolabs.ai/model-logos/mimo-v2-6-pro-ultraspeed.png)

[Xiaomi](/providers/xiaomi) · Text Generation

`POST /v1/chat/completions`

High-throughput build of the trillion-parameter flagship, matching its full-modality reasoning while generating output substantially faster.

## At a glance

| Field               | Value                                                                                     |
| ------------------- | ----------------------------------------------------------------------------------------- |
| Model id            | `mimo-v2-6-pro-ultraspeed`                                                                |
| Model release date  | 2026-09-22                                                                                |
| Input modalities    | Text, Image, Video, Audio                                                                 |
| Output modalities   | Text                                                                                      |
| Context window      | 1M                                                                                        |
| Weight precision    | -                                                                                         |
| Max output tokens   | 131,072                                                                                   |
| Region              | Singapore                                                                                 |
| Features            | reasoning, agentic, vision, audio_in, function_calling, structured_output                 |
| Native inference    | No                                                                                        |
| New                 | Yes                                                                                       |
| Structured output   | JSON Schema                                                                               |
| Supported endpoints | `POST /v1/chat/completions`                                                               |
| Alternate model ids | `mimo-v2.6-pro-ultraspeed`, `mimo/v2.6-pro-ultraspeed`, `xiaomi/mimo-v2.6-pro-ultraspeed` |

## Pricing

| Charge              | Spec                    | Rate    |
| ------------------- | ----------------------- | ------- |
| Input               | per 1M prompt tokens    | \$4.35  |
| Output              | per 1M generated tokens | \$8.70  |
| 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": "mimo-v2-6-pro-ultraspeed", "messages": [{"role":"user","content":"Hello"}]}'
```

## Parameters

| Parameter            | Type    | Required | Default | Description                                                                                                                                                                                                                                                                         |
| -------------------- | ------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `enable_thinking`    | boolean | no       | true    | Enable extended thinking mode. Slower but improves reasoning-heavy tasks.                                                                                                                                                                                                           |
| `temperature`        | number  | no       | `0.7`   | Sampling temperature. 0 = deterministic, 2 = maximum randomness. · Range: 0 – 2                                                                                                                                                                                                     |
| `top_p`              | number  | no       | `0.9`   | Nucleus sampling probability mass. Lower = more focused. · Range: 0 – 1                                                                                                                                                                                                             |
| `max_tokens`         | number  | no       | `4096`  | Maximum tokens in the response. · Range: 1 – 131072                                                                                                                                                                                                                                 |
| `stop`               | string  | no       | -       | Up to 4 strings where the model will stop generating further tokens.                                                                                                                                                                                                                |
| `response_format`    | enum    | no       | -       | Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape.                                                                                                                                                    |
| `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   | When enabled, the gateway will not append the "Sources" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.                                                                              |

## Notes

Accepts text, image, video, and audio input and returns text. Thinking is on by default and can be turned off. Optional Linkup web search is billed only when invoked.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/mimo-v2-6-pro-ultraspeed`.