DeepInfra raises $107M Series B to scale the inference cloud — read the announcement

Qwen logo

Qwen/

Qwen4-Max

Partner

$1.413

in

$4.24

out

$0.071

cached

/ 1M tokens

Qwen's next-generation flagship multimodal model, combining text, image and video understanding with deep reasoning for coding, office work and complex agentic tasks.

Public
1,000,000
JSON
Function
Multimodal
Qwen/Qwen4-Max cover image
api
Qwen/Qwen4-Max cover image
Qwen4 Max

Ask me anything

0.00s

You need to log in to use this model

Log in

Settings

Model Information
  • Next-generation Qwen flagship that combines text generation, image and video understanding, and deep reasoning in one model.
  • Built for coding, office productivity, frontend design, and complex agentic work: long-horizon planning, tool calling, and feedback-driven iteration.
  • Covers the full engineering pipeline, from understanding requirements and setting up environments to implementation, packaging, and deployment.
  • Operates professional software such as CAD, Blender, Unity, and Godot for engineering, 3D modeling, and game development tasks.
  • Deep research that traces evidence to its source and cross-checks it, for financial, legal, and healthcare workflows.
  • 1M-token context window with native vision: reads long documents and large image sets in a single pass.
  • Supports function calling, structured outputs, and optional thinking mode.