Model overview
Text generationMiMo-V2.5-Pro is Xiaomi's latest flagship model. It improves general agent capability, complex software engineering, and long-horizon task execution, ranks strongly on ClawEval, GDPVal, and SWE-bench Pro, and supports a 1M-token context window for agent frameworks.
Company: XiaomiProvider: Alibaba Cloud
Model capabilities
Input modalityT
Output modalityT
Model experience✓
Function calling✓
Structured output-
Web search✓
Prefix completion-
Context cache✓
Batch inference✓
Fine-tuning-
Model pricing
Input$1.04/1M tokens
Input (cache hit)$0.209/1M tokens
Output$3.13/1M tokens
Rate limits and context
Maximum input length1M
Maximum input length (thinking mode)1M
Context length1M
Maximum output length128K
Maximum output length (thinking mode)128K
Maximum reasoning length128K
RPM100
TPM10000000
API reference
EndpointPOST /v1/chat/completions
SDKOpenAI-compatible
API code examples
from openai import OpenAI client = OpenAI( api_key="$WLROUTER_API_KEY", base_url="https://api.wlrouter.com/v1" ) response = client.chat.completions.create( model="xiaomi/mimo-v2.5-pro", messages=[ {"role": "user", "content": "Reply with one short sentence."} ], max_tokens=32 ) print(response.choices[0].message.content)