Skip to main content
Alibaba QwenNov 16, 2026New

Qwen 4 Max

qwen-4-maxAnonymized

Qwen 4 Max is the flagship model of the Qwen 4 series. It accepts text, image, and video input, thinks by default with adjustable reasoning effort, and supports a 1M-token context window.

$1.50/$4.50
per 1M in / out
1M
context window
384K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 88%94.4%
Blended pricecheaper than 43%$2.25
Context windowlarger than 42%1M
Max outputlarger than 100%384K

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.

InTextImageVideo
OutText
Streamingstream: true
Function callingtoolsReasoningAlways onVisionUp to 10 images
Video inputVideo in messages
Web searchenable_web_search
Prompt cachingReads at $0.075
Optimized for codeTuned for software work

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

Benchmarks

GPQA Diamond
94.4%14th of 139 · Gemini 3.8 Flash, Gemini 3.7 Flash and Pareto score higher for less

Specs

Model ID
qwen-4-max
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
393,216 tokens
Reasoning
Always on
Precision
Set by the provider
Privacy
Anonymized
Weights
Closed
Added
Nov 16, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Qwen 4 Max$1.50$4.5094.4%1M384K——
GPT-6.1 Terra$1.00$5.0092.9%1.05M128K——
Muse Spark Open$1.56$5.3171.7%1M128K——
DeepSeek V4.1 Flash 1017 Ultrafast$1.50$6.0088.9%1M128K——
DeepSeek V4 Pro 0813$1.65$4.9582.3%1M256K——

Other versions

  1. Qwen 3.7 MaxMay 2026
  2. Qwen 3.8 MaxJul 2026
  3. Qwen 4 MaxNov 2026

Pricing

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

Input$1.50per 1M tokens
Cached input$0.07595% off input
Output$4.50per 1M tokens

Estimate a workload

$0.0053per request
$52.50for 10,000 requests

Blended price against similar models

Qwen 4 Max$2.25

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": "qwen-4-max",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelqwen-4-maxRequired
messagestext · image_url · video_urlContent parts the model reads
max_completion_tokensUp to 393,216Counts reasoning tokens
toolsFunction definitionsWith tool_choice
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations