Qwen 4 Max via the Tokenator API

What the model is for

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. Reasoning effort can be set to low, high, or xhigh (default high), or reasoning can be turned off. Tool calling and structured outputs are supported.

Specification

Full nameQwen 4 Max
API IDqwen-4-max
Model vendorQwen
TypeText model (chat / completions)
Context window1M tokens
Max output131.1K tokens
Image inputyes
Tokenator usage multiplier0.8×
Output token multiplier4×
BadgeNEW
Input modalitiestext, image, video
Aliasescursor-qwen-4-max
Supported API formats/v1/chat/completions /v1/responses /v1/messages
Upstream providers1
Current statusavailable
Data updated2026-11-22

Benchmarks

Intelligence index42.9
Vals Finance Index (Vals AI)62%
Vals Index (Vals AI)63.2%
Vals Legal Index (Vals AI)70.7%
Terminal-Bench 4.0 (Vals AI)48.5%
Vibe Code Bench v1.1 (Vals AI)86.7%
EMB v1.1 (Vals AI)70.8%
Finance Agent v2.1 (Vals AI)66.7%
Tax Agent Bench (Vals AI)40.4%
HLAB-Vals-1.1 (Vals AI)21.3%
Legal Research Bench (Vals AI)41.3%

Artificial Analysis and Vals AI data loaded into the catalog for this model.

Upstream providers

ProviderMultiplierOutput token multiplier
Qwen Cloud0.8×4×

A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.

Example request

curl
curl https://api.tokenator.top/v1/chat/completions \
  -H "Authorization: Bearer sk-your-tokenator-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-4-max",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Compatible tools

The model can be used in any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code, Cherry Studio, DeepSeek Harness, Hermes, Pi, OpenClaw.

FAQ about Qwen 4 Max

What is the API ID of Qwen 4 Max?

qwen-4-max — put this into the model field of your request.

What context window does Qwen 4 Max have?

1M tokens; max output is 131.1K tokens.

How many tokens will a request cost?

(input × 0.8×) + (output × 4×). See the documentation for details.

Which tools support this model?

Any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code. Setup guides are in the integrations section.