AIHubMixAIHubMix
Models
MiMo V2.5
Compare
Xiaomi logo

MiMo V2.5

mimo-v2.5llms.txt
Xiaomi
MiMo-V2.5 is a native, fully multimodal large model designed for agent scenarios; it can see, hear, and read, and translate understanding into action. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M context length. Built on a powerful model base, we continuously scale compute across broader agent scenarios, further expanding the agent’s action space and achieving an important generalization from coding to claw.

Pricing

PricingCache ReadWeb Search
$0.155$0.31
$0.0031/M tokens$0.005/request

Input Modalities

  • Text
  • Vision
  • Audio
  • Video

Output Modalities

  • Text

Capabilities

  • Web

Providers

Xiaomi xiaomi-mimo-v2.5
Pricing$0.155$0.31
Cache Read$0.0031/M tokens
Web Search$0.005/request
Context256K
Max output0
Latency12.6S
Throughput42.2TPS
Uptime
99.76% uptime 2 days ago
99.80% uptime yesterday
99.41% uptime today
Deepinfra deepinfra-mimo-v2.5
Pricing$0.44$2.2
Cache Read$0.088/M tokens
Web Search$0.005/request
Context256K
Max output0
Latency1.7S
Throughput41.3TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today

Performance for mimo-v2.5

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-v2.5",
    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 V2.5?

MiMo-V2.5 is a native, fully multimodal large model designed for agent scenarios; it can see, hear, and read, and translate understanding into action. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M context length. Built on a powerful model base, we continuously scale compute across broader agent scenarios, further expanding the agent’s action space and achieving an important generalization from coding to claw.
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect