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.
Bayar sesuai pemakaian
Tanpa biaya di muka, bayar hanya sesuai penggunaan
Gunakan contoh kode berikut untuk integrasi dengan API kami:
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
Konteks
1049K
Output Maks.
131K
Vision
Didukung
Penggunaan Tool
Didukung
Akses Mimo V2.5 melalui API terpadu kami — kompatibel dengan OpenAI, tanpa cold start, harga transparan.
Harga di WaveSpeedAI: $0.40 per juta token input dan $2.00 per juta token output. Prompt caching dan batch processing ditagih terpisah dan mengurangi biaya efektif pada beban kerja yang panjang dan berulang.
Mimo V2.5 mendukung hingga 1049K token konteks dengan hingga 131K token output per permintaan.
Ya. WaveSpeedAI menyediakan Mimo V2.5 melalui endpoint yang kompatibel dengan OpenAI di https://llm.wavespeed.ai/v1. Arahkan OpenAI SDK resmi ke base URL ini dengan API key WaveSpeedAI Anda — tanpa perubahan kode lainnya.
Masuk ke WaveSpeedAI, buat API key di Access Keys, lalu kirim permintaan ke https://llm.wavespeed.ai/v1/chat/completions dengan model id seperti ditampilkan di atas. Akun baru menerima kredit gratis untuk menguji Mimo V2.5.