Qwen-Max pricing
Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion... This page tracks 4 listings in total. Highlighted lows are $1.04 per million input and $4.16 per million output (see table for which seller matches each).
Pricing across providers
Use this table to read Qwen-Max list prices. We show 4 sources right now. Lowest input in the grid: Openrouter. The chart below the table helps when output prices are much higher than input prices.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
AC Alibaba Cloud | $1.60 | $6.40 | — | — |
O Openrouter | $1.04 | $4.16 | — | — |
QA Qwen Ai Platform | $1.60 | $6.40 | — | — |
Q Qwencloud | $1.60 | $6.40 | — | — |
Input vs output · per provider
Cost calculator
Use this block to stress test Qwen-Max cost without a spreadsheet. All estimates come from public list rates in this page.
Provider
0.160000¢ / req
0.320000¢ / req
Model specifications
These fields describe Qwen-Max as we store it (Family: Qwen. source: Alibaba). They sit next to price so buyers can check limits and tools in one place.
- Context window
- 30,720 tokens
- Max output
- 8,192 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- No
- Released
- Feb 2025
- Primary provider
- Alibaba
- Model family
- Qwen
Compare Qwen-Max
These links open full side by side pages for Qwen-Max. We picked pairs that people often shop together. 6 ready to open.
Locked
Compare with
Pick a model on both sides.
Popular Qwen-Max comparisons
- Qwen-Max vs GPT-4o
Compare pricing side by side
- Qwen-Max vs Claude Sonnet 4.6
Compare pricing side by side
- Qwen-Max vs Gemini 2.0 Flash
Compare pricing side by side
- Qwen-Max vs Llama 3.1 70B
Compare pricing side by side
- Qwen-Max vs Mistral 7B
Compare pricing side by side
- Qwen-Max vs GLM 4.7
Compare pricing side by side
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion...
Related models
Models close to Qwen-Max by family, provider, and context window — each with live pricing in our catalog.