Qwen4-Max
A multimodal flagship for coding, professional work, scientific exploration, and long-running agent tasks with reasoning, vision, video, tools, and structured outputs.
Source: https://docs.qwencloud.com/developer-guides/getting-started/model-prices, https://docs.qwencloud.com/developer-guides/run-and-scale/explicit-cache-qwen4, https://docs.qwencloud.com/developer-guides/getting-started/latest-model, https://docs.qwencloud.com/developer-guides/getting-started/text-generation-models, https://qwen.ai/blog/qwen4-max, https://docs.qwencloud.com/developer-guides/text-generation/thinking
- Text
- Image
- Video
- Text
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate |
|---|---|
| Input | $1.43 / M |
| Output | $4.28 / M |
| Cache read | $0.07125 / M |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.
Provider
Where this model runs, and what it charges.
| Platform | Input / M | Output / M | Cache read / M | Batch | Access |
|---|---|---|---|---|---|
Alibaba | $1.43 | $4.28 | $0.07125 | - | via OpenRouter |
Price history
Has this model gotten cheaper or more expensive?
More from Qwen
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every Qwen4-Max call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.