Skip to main content
MiniMaxFeb 12, 2026

MiniMax M2.5

minimax-m25PrivateOpen weights

MiniMax-M2.5 is a large language model optimized for coding, agentic workflows, and modern application development with enhanced reasoning capabilities.

$0.27/$0.95
per 1M in / out
198K
context window
32K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 74%90.4%
Blended pricecheaper than 78%$0.44
Context windowlarger than 14%198K
Max outputlarger than 21%32K

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.

InText
OutText
Streamingstream: true
Function callingtoolsReasoningreasoning_effort low · medium · high
Web searchenable_web_search
Prompt cachingReads at $0.03
Optimized for codeTuned for software work

Not supportedstructured outputs, image input, video input, audio input, X search and log probabilities

Benchmarks

GPQA Diamond
90.4%36th of 139 · none scores higher for less

Specs

Model ID
minimax-m25
Endpoint
POST /api/v1/chat/completions
Context window
198,000 tokens
Max output
32,768 tokens
Reasoning
low · medium · high · default low
Precision
Not disclosed
Privacy
Private
Added
Feb 12, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
MiniMax M2.5$0.27$0.9590.4%198K32K——
Qwen3 VL 30B A3B E2EE$0.25$0.9041.4%128K4K——
Qwen 3.6 35B A3B E2EE$0.182$1.1855.2% (off)32K4K——
Qwen 3.5 35B A3B$0.15$1.0083.8%256K16K——
GPT-5.6 Luna$0.20$1.2088.4%1M128K——

Other versions

  1. MiniMax M2.5Feb 2026
  2. MiniMax M2.7Mar 2026

Pricing

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

Input$0.27per 1M tokens
Cached input$0.0389% off input
Output$0.95per 1M tokens

Estimate a workload

$0.001per request
$10.15for 10,000 requests

Blended price against similar models

MiniMax M2.5$0.44

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": "minimax-m25",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "low"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelminimax-m25Required
messagestextContent parts the model reads
max_completion_tokensUp to 32,768Counts reasoning tokens
reasoning_effortlow | medium | highDefault low
toolsFunction definitionsWith tool_choice
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations