Skip to content
qwen4-maxChatExamples verified 2026-09-25

Qwen4 Max

Qwen's newest flagship; reads images and video, $1.47 / $4.41, one price across the whole context.

Official price
$1.47 / $4.41/ 1M tokensInput / output
Context window
1M tokens1,000,000
Notes
  • In thinking mode a forced tool_choice is accepted, but only qwen4-max reliably calls the tool; on the others send enable_thinking: false to force a tool.
  • Up to 262,144 output tokens with thinking on. On /v1/messages, thinking disabled has no effect; to turn thinking off, use Chat Completions with enable_thinking: false.

Pricing

Official price in USD. Actual charge = official price × group multiplier.

Input
$1.47 / 1M tokens
Cached input
$0.0735 / 1M tokens
Output
$4.41 / 1M tokens

Endpoints

Same family

Prices come from the public catalog; limits come from specs exported from the gateway’s validation code. Actual charge = official price × group multiplier.