Qwen4-Max
- Family
- Qwen4
- Released
- 2026-11-15
- Context
- 1M
- Max output
- 256K
- Parameters
- 2.4T (71B active)
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
Cheapest of 6 routes · DeepInfra · cache read $0.071
Cheapest of 6 routes · DeepInfra · cache read $0.071
About
Qwen4-Max is the first production model in Alibaba's Qwen4 series and the general-availability successor to Qwen4-Max-Preview, with pay-as-you-go API access on Alibaba Cloud Model Studio. The Qwen team describes a new sparse MoE architecture with a 2.4-trillion-parameter backbone, 71B parameters activated per token and an additional 328B N-gram embedding parameters, with native vision. It takes text, image and video input and returns text, with a 1,000,000-token context window, deep thinking at low, high and xhigh effort, parallel tool calling, web search, structured output, and explicit and implicit caching, over OpenAI- and Anthropic-compatible APIs.
Providers(6)
Compare all 6Compare API pricing across 6 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| DeepInfra | $1.41 | $4.24 | read $0.071 | Serverless |
| Novita AI | $1.41 | $4.24 | - | Serverless |
| Alibaba Cloud PAI-EAS | $1.50 | $4.50 | read $0.075 / 5m $1.88 / 1h $3.00 | Serverless |
| OpenRouter | $1.50 | $4.50 | read $0.075 / 5m $1.88 | Serverless |
| Vercel AI Gateway | $1.50 | $4.50 | read $0.075 / 5m $1.88 | Serverless |
| Venice AI | $1.88 | $5.63 | read $0.0938 / 5m $2.34 | Serverless |
Capabilities
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
qwen4-maxqwen/qwen4-maxalibaba/qwen4-max