Qwen 4 Max Thinking
Qwen 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.
- Reasoning
- Vision
- Video Input
- Tool Calling
- Structured Output
Added Nov 16, 2026
Pricing
Auto routing · per 1M tokens- Input
- $1.50
- Output
- $4.50
- Cache read
- $0.075
Specifications
- Context window
- 983.6K
- Max output
- 262.1K
Benchmarks
No public benchmark scores for this model yet.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| Cache write /M | ||||||
|---|---|---|---|---|---|---|
| $1.50 | $4.50 | $0.075 | $1.88 | N/A | N/A | |
| $1.57 | $4.72 | $0.0787 | $1.97 | N/A | N/A |
Privacy:No training on prompts