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 name | Qwen 4 Max |
| API ID | qwen-4-max |
| Model vendor | Qwen |
| Type | Text model (chat / completions) |
| Context window | 1M tokens |
| Max output | 131.1K tokens |
| Image input | yes |
| Tokenator usage multiplier | 0.8× |
| Output token multiplier | 4× |
| Badge | NEW |
| Input modalities | text, image, video |
| Aliases | cursor-qwen-4-max |
| Supported API formats | /v1/chat/completions /v1/responses /v1/messages |
| Upstream providers | 1 |
| Current status | available |
| Data updated | 2026-11-22 |
Benchmarks
| Intelligence index | 42.9 |
| 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
| Provider | Multiplier | Output token multiplier |
|---|---|---|
| Qwen Cloud | 0.8× | 4× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
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.
See also
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.