qwen logo
qwen

Qwen: Qwen4 Max

Source description (English)

Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....

Overview

Model specifications

Context
1,000,000 tokens
Maximum output
131,072 tokens
Architecture
text+image+video->text
Tokenizer
Qwen
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$1.425
per 1M tokens
Output
$4.275
per 1M tokens
Cache read
$0.0713
per 1M tokens
Cache write
$1.7813
per 1M tokens
Cache Creation (1h)
$3
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
No
Default parameters
high
Capabilities
xhigh, high, low, none
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen4-max","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimagevideo
Output
text
Reasoning

Yes · xhigh · high · low · none

API

Supported API parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

1 Provider

Checked: November 16, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Alibaba

Not provided
Context
1M
Maximum output
131K
Input
$1.425
Output
$4.275
Cache read
$0.0713
Cache write
$1.7813
qwen

4 models

All models