Qwen 4 Max Thinking
qwen/qwen4-max:thinkingQwen 4 Max with reasoning enabled for deeper coding, knowledge work, data analysis, and long-running agent workflows. It accepts text, image, and video input and supports tool calling, structured output, and a 1M-token context window.
- Vision
- Reasoning
- Video input
- Tool calling
- Structured output
Pricing
Includes our margin. Charged per request from your balance.
- Input
- $1.55 per 1M tokens
- Output
- $4.66 per 1M tokens
- Cache read
- $0.0781 per 1M tokens
- Cache write
- $1.94 per 1M tokens
- Typical message
- $0.0031
Details
- Provider
- Qwen
- Context
- 1M tokens
- Max output
- 262K tokens
- Added
- Nov 16, 2026
- Reasoning effort
- low, high, xhigh
Use it from the API
Replace $HIDE_API_KEY with a key from the Developers page. Base URL https://hide.st/api/v1.
curl https://hide.st/api/v1/chat/completions \
-H "Authorization: Bearer $HIDE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen4-max:thinking",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'