xiaomi/mimo-v2.5
1,048,576 context · $0.40/M input tokens · $2.00/M output tokens
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.
Pay-per-use
No upfront costs, pay only for what you use
Use the following code examples to integrate with our API:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="xiaomi/mimo-v2.5",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)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...
This model is imported from OpenRouter metadata and exposed through the WaveSpeed AI OpenAI-compatible API for chat completions and compatible application workflows.
| Specification | Value |
|---|---|
| Provider | xiaomi |
| Model Type | Chat Completions model |
| Architecture | text+image+audio+video->text |
| Context Window | 1048576 tokens |
| Max Input | 917504 tokens |
| Max Output | 131072 tokens |
| Input | Text, Audio, Image, Video |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Structured Outputs | Supported |
| OpenRouter Created | April 22, 2026 |
| Token Type | Cost |
|---|---|
| Input | $0.4 per million tokens |
| Output | $2 per million tokens |
| Cached Input | $0.08 per million tokens |
Note: Pricing is generated from OpenRouter model metadata. If multiple upstream providers expose different endpoint prices, review and adjust the price before publishing.
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: xiaomi/mimo-v2.5
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="xiaomi/mimo-v2.5",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "xiaomi/mimo-v2.5",
"messages": [{"role": "user", "content": "Hello!"}]
}'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.
Input
$0.4 /M
Output
$2 /M
Context
1049K
Max Output
131K
Vision
Supported
Tool Use
Supported
Access Mimo V2.5 through our unified API — OpenAI-compatible, no cold starts, transparent pricing.
Pricing on WaveSpeedAI: $0.40 per million input tokens and $2.00 per million output tokens. Prompt caching and batch processing are billed separately and reduce effective cost on long, repetitive workloads.
Mimo V2.5 supports up to 1049K tokens of context with up to 131K tokens of output per request.
Yes. WaveSpeedAI exposes Mimo V2.5 through an OpenAI-compatible endpoint at https://llm.wavespeed.ai/v1. Point the official OpenAI SDK at this base URL with your WaveSpeedAI API key — no other code changes required.
Sign in to WaveSpeedAI, create an API key in Access Keys, then send a request to https://llm.wavespeed.ai/v1/chat/completions with model id set to the value shown above. New accounts receive free credits to evaluate Mimo V2.5 before paying per token.