Models
MiMo V2 Pro
Compare
Xiaomi logo

MiMo V2 Pro

mimo-v2-prollms.txt
Xiaomi
Xiaomi MiMo-V2-Pro is built for high-intensity agent work scenarios in the real world. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M-token context length. On top of a powerful model foundation, we continuously scale compute across broader agent scenarios, further expanding the intelligent action space and achieving significant generalization from Coding to Claw.
This model has been retired.
Requests return 404 model_retired. All model retirements

Pricing

TierPricingCache ReadWeb Search
Input<=256K
$1.1$3.3
$0.22/M tokens$0.005/request
256K<Input
$2.2$6.6
$0.44/M tokens$0.005/request

Input Modalities

  • Text
  • Vision
  • Audio
  • Video

Output Modalities

  • Text

Context length

  • 1.05M tokens

Max output

  • 131K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Structured outputs
  • Structured decision
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Providers

Xiaomi xiaomi-mimo-v2-pro
TierInput<=256K
Pricing$1.1$3.3
Cache Read$0.22/M tokens
Web Search$0.005/request
Tier256K<Input
Pricing$2.2$6.6
Cache Read$0.44/M tokens
Web Search$0.005/request
Latency1.7S
Throughput41.3TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today

Performance for mimo-v2-pro

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="mimo-v2-pro",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is MiMo V2 Pro?

Xiaomi MiMo-V2-Pro is built for high-intensity agent work scenarios in the real world. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M-token context length. On top of a powerful model foundation, we continuously scale compute across broader agent scenarios, further expanding the intelligent action space and achieving significant generalization from Coding to Claw.

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Company

Terms & Policies