Xiaomi: MiMo-V2.5-Pro-UltraSpeed

MiMo pro model for strong multimodal reasoning and agent execution

Model lab: Xiaomi
Model family: mimo

Model resources

Hugging Face

Modalitiestext → text

Context window1,048,576

Maximum output131,072

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to xiaomi/mimo-v2.5-pro-ultraspeed.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "xiaomi/mimo-v2.5-pro-ultraspeed"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

MiMo-V2.5-Pro-UltraSpeed API Pricing

Price under review

Performance

Performance trends

Throughput91.8 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency7.0 sCurrent

Throughput

Current91.8 tok/s

Window average90.1 tok/s

Time to first token

Current1.4 s

Window average1.5 s

End-to-end latency

Current7.0 s

Window average7.5 s

Tail latency (P99)

Current13.0 s

Window average16.3 s

Prompt cache hit rate

Current26.0%

Window average23.3%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

MiMo-V2.5-Pro-UltraSpeed Compare models

Model	Input price	Output price	Context window	Capabilities
MiMo-V2.5-Pro-UltraSpeedThis page	Price under review	Price under review	1,048,576	Text output · Reasoning · Tool calling
MiMo-V2.5-Pro	USD 0.16 / 1M tokens · Base context tier (boundary 256000 tokens)	USD 0.48 / 1M tokens · Base context tier (boundary 256000 tokens)	1,048,576	Text output · Reasoning · Tool calling
MiMo-V2-Pro	USD 0.8 / 1M tokens	USD 2.4 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
MiMo-V2-Flash	USD 0.08 / 1M tokens	USD 0.24 / 1M tokens	262,144	Text output · Reasoning · Tool calling
MiMo-V2.6-Flash	USD 0.08 / 1M tokens	USD 0.2 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling

Model specifications

Input: text
Output: text
Context window: 1,048,576
Maximum output: 131,072
Release date: 2026-06-08
Attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is MiMo-V2.5-Pro-UltraSpeed for?

MiMo pro model for strong multimodal reasoning and agent execution

What inputs and outputs does MiMo-V2.5-Pro-UltraSpeed support?

Recorded inputs: text; outputs: text.

How is MiMo-V2.5-Pro-UltraSpeed priced?

This page does not list a price for this model yet.

What specifications are recorded for MiMo-V2.5-Pro-UltraSpeed?

Current model records list Context window 1,048,576 tokens; Maximum output 131,072 tokens.

What model parameter does the Quickstart use?

The example uses xiaomi/mimo-v2.5-pro-ultraspeed. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.