MiMo V2.6 Pro UltraSpeed API

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

Xiaomi Text Generation 1M context Released Sep 22, 2026 Singapore Proprietary Endpoint

About MiMo V2.6 Pro UltraSpeed

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

Also known as MiMo Pro UltraSpeed, MiMo UltraSpeed, Xiaomi MiMo V2.6 Pro UltraSpeed

reasoning agentic vision audio in function calling structured output

MiMo V2.6 Pro UltraSpeed specs

Model ID
mimo-v2-6-pro-ultraspeed
Author
Xiaomi
Category
Text Generation
Released
Sep 22, 2026
Context window
1M tokens
Max output
131,072 tokens
Input
TextImageVideoAudio
Output
Text
Structured output
JSON Schema
Region
Singapore
Endpoints
POST/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/mimo-v2-6-pro-ultraspeed:generateContent
Alternate model IDs
mimo-v2.6-pro-ultraspeedmimo/v2.6-pro-ultraspeedxiaomi/mimo-v2.6-pro-ultraspeed

MiMo V2.6 Pro UltraSpeed API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.

Type
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
Compare on the full pricing page

How to call the MiMo V2.6 Pro UltraSpeed API

MiMo V2.6 Pro UltraSpeed serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id mimo-v2-6-pro-ultraspeed. Get an API key from the EmpirioLabs dashboard.

cURL
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": "Write a haiku about the ocean."}
    ]
  }'
Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://api.empiriolabs.ai/v1",
    api_key="YOUR_EMPIRIOLABS_API_KEY",
)

response = client.chat.completions.create(
    model="mimo-v2-6-pro-ultraspeed",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)
Full MiMo V2.6 Pro UltraSpeed API reference

MiMo V2.6 Pro UltraSpeed API parameters

Request parameters supported by the MiMo V2.6 Pro UltraSpeed API on EmpirioLabs. Defaults apply when a field is omitted.

ParameterTypeDefaultRange / valuesDescription
enable_thinkingbooleantrue-Enable extended thinking mode. Slower but improves reasoning-heavy tasks. A request that forces a tool call runs without reasoning unless it sets enable_thinking.
video_fpsnumber-0.1 to 10Frames per second to sample from video inputs. When omitted, the model's own default applies.
media_resolutionenumdefaultdefault, maxResolution at which video inputs are read. max reads finer detail and uses more input tokens.
temperaturenumber10 to 1.5Sampling temperature. 0 = deterministic, 1.5 = maximum randomness.
top_pnumber0.950.01 to 1Nucleus sampling probability mass. Lower = more focused.
max_tokensnumber81921 to 131072Maximum tokens in the response.
stopstring--Up to 4 strings where the model will stop generating further tokens.
response_formatenum--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_linkupbooleanfalse-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_formattingbooleanfalse-Return the answer without the Sources list that web search adds.

Good to know

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.

MiMo V2.6 Pro UltraSpeed API: common questions

How much does the MiMo V2.6 Pro UltraSpeed API cost?

On EmpirioLabs, MiMo V2.6 Pro UltraSpeed is billed pay as you go: Input $4.35 per 1M prompt tokens; Output $8.70 per 1M generated tokens; Web Search (Linkup) $0.013 per call when invoked. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.

What inputs and outputs does MiMo V2.6 Pro UltraSpeed support?

MiMo V2.6 Pro UltraSpeed takes Text, Image, Video, Audio as input and returns Text.

What is the context window of MiMo V2.6 Pro UltraSpeed?

MiMo V2.6 Pro UltraSpeed supports a 1M-token context window with up to 131,072 output tokens per response.

Is the MiMo V2.6 Pro UltraSpeed API OpenAI-compatible?

Yes. MiMo V2.6 Pro UltraSpeed serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to mimo-v2-6-pro-ultraspeed.

What is the model ID for MiMo V2.6 Pro UltraSpeed?

Send mimo-v2-6-pro-ultraspeed as the model in your request. The alternate IDs mimo-v2.6-pro-ultraspeed, mimo/v2.6-pro-ultraspeed, xiaomi/mimo-v2.6-pro-ultraspeed also work.

When was MiMo V2.6 Pro UltraSpeed released?

Xiaomi released MiMo V2.6 Pro UltraSpeed on Sep 22, 2026.

Where is MiMo V2.6 Pro UltraSpeed served from?

MiMo V2.6 Pro UltraSpeed on EmpirioLabs is served from Singapore.

Can I try MiMo V2.6 Pro UltraSpeed in the browser before integrating?

Yes. The EmpirioLabs playground runs MiMo V2.6 Pro UltraSpeed in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a MiMo V2.6 Pro UltraSpeed API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.

Compare MiMo V2.6 Pro UltraSpeed with other models

All model comparisons

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.