Skip to main content
XiaomiJun 11, 2026

MiMo-V2.5

xiaomi-mimo-v2-5PrivateOpen weights

MiMo-V2.5 is Xiaomi’s native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding in a unified architecture. Built on a sparse Mixture-of-Experts backbone with 310B total and 15B active parameters, it delivers long-context reasoning up to 1M tokens, function calling, and multimodal perception.

$0.40/$2.00
per 1M in / out
1M
context window
64K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 27%74.7%
Blended pricecheaper than 68%$0.80
Context windowlarger than 42%1M
Max outputlarger than 37%64K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InTextImageVideoAudio
OutText
Streamingstream: true
Function callingtoolsStructured outputsresponse_formatReasoningreasoning_effort none · low · medium · highVisionUp to 10 images
Video inputVideo in messages
Audio inputAudio in messages
Web searchenable_web_search
Prompt cachingReads at $0.08
Optimized for codeTuned for software work

Not supportedX search and log probabilities

Benchmarks

GPQA Diamond
74.7%102nd of 139 · 23 score higher for less, including DeepSeek v4.1 Flash (1017), MiniMax M2.5 and DeepSeek V4.1 Flash 1017 Uncensored

Specs

Model ID
xiaomi-mimo-v2-5
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
65,536 tokens
Reasoning
none · low · medium · high · default high
Precision
FP8
Privacy
Private
Added
Jun 11, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
MiMo-V2.5$0.40$2.0074.7%1M64K——
Qwen 3.7 Plus$0.50$2.0081.8%1M64K——
Venice Role Play Uncensored$0.50$2.0040.2%128K4K——
MiniMax M2.7$0.375$1.5088.4%198K32K——
Gemini 3.5 Flash-Lite$0.375$3.1379.8%1M64K——

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$0.40per 1M tokens
Cached input$0.0880% off input
Output$2.00per 1M tokens

Estimate a workload

$0.0018per request
$18.00for 10,000 requests

Blended price against similar models

MiMo-V2.5$0.80

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xiaomi-mimo-v2-5",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "high"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelxiaomi-mimo-v2-5Required
messagestext · image_url · video_url · input_audioContent parts the model reads
max_completion_tokensUp to 65,536Counts reasoning tokens
reasoning_effortnone | low | medium | highDefault high
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations