# Xiaomi: MiMo-V2.5

xiaomi/mimo-v2.5

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.

by [Xiaomi](/content/xiaomi/index.html)  
Input type  Output type  Publish time  
2026-04-23

## Recent activity on MiMo-V2.5

### Tokens processed per day

## Throughput
(tokens/s)

| Providers | Min (tokens/s) | Max (tokens/s) | Avg (tokens/s) |
| --- | --- | --- | --- |
| Xiaomi | 19.81 | 54.49 | 44.48 |

## First Token Latency

(ms)

| Providers | Min (ms) | Max (ms) | Avg (ms) |
| --- | --- | --- | --- |
| Xiaomi | 1677 | 4567 | 2972.86 |

## Uptime stats for MiMo-V2.5

Uptime stats for MiMo-V2.5 across all providers

Uptime

Xiaomi  
( Percent )

Providers for MiMo-V2.5

ZenMux Provider to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

[**Xiaomi**](/content/provider/xiaomi/index.html)

Latency

2.24

s

Throughput

50.54
tps

Uptime

100.00
%

Recent uptime
Apr 30, 2026 6:00 PM-

## Price

**Tiered Pricing**  
0 ≤ Input < 256k

| Input | Price |
| --- | --- |
| $ 0.4/ M tokens | Output |
| $ 2/ M tokens | Cache read |
| $ 0.08/ M tokens | Cache write 5m |
| - | Cache write 1h |
| - | Cache write |
| - | Web search |
| $ 0.005/ counts | Image |
| - | Image input |
| - | Image output |
| - | Image cache |
| - | reasoning |
| - | Video |
| - | Audio |
| - | Audio cache read |
| - | Audio input |
| - | Audio & Video |
| - | Image search |
| - | Web search image |

## Model limitation

**Context**  
1.05M

**Max output**  
131.07K

**Supported Parameters**
- max_completion_tokens
- temperature
- top_p
- frequency_penalty
- presence_penalty
- seed
- logit_bias
- logprobs
- top_logprobs
- response_format
- stop
- tools
- tool_choice
- parallel_tool_calls

## Model Protocol Compatibility

- OpenAI Chat Completions
- OpenAI Responses
- OpenAI Embeddings
- Anthropic Messages
- Google Gemini
- Google Imagen
- Google Video

## Sample code and API for MiMo-V2.5

ZenMux normalizes requests and responses across providers for you.

[Create API Key](/content/platform/pay-as-you-go/index.html)

### OpenAI: Python-SDK

```python
from openai import OpenAI

client = OpenAI(
  base_url="https://zenmux.ai/api/v1",
  api_key="<ZENMUX_API_KEY>",
)

# Chat Completion
completion = client.chat.completions.create(
  model="xiaomi/mimo-v2.5",
  messages=[
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
)
print(completion.choices[0].message.content)

# Responses API
responses = client.responses.create(
  model="xiaomi/mimo-v2.5",
  input="What is the meaning of life?"
)
print(responses)
```