Cheapest Qwen Max Models
As of October 21, 2026, among LiteLLM's active models with a 32K-token context window or more, offered by at least two providers or by their own lab, the cheapest of the Qwen Max models is Qwen3 Max, at $2.40 per 1M tokens (blended), from DeepInfra.
Top 3
Sorted by blended price: 3 input tokens for every output token, at each model's headline price (its own lab's API where it sells it, otherwise its cheapest provider). Only Qwen Max models. Only active models with a 32K-token context window or more, offered by at least two providers or by their own lab. Free models are left out.
| # | Model | Lab | Blended price per 1M tokens | Price per 1M (in / out) | Context | Providers | Price from |
|---|---|---|---|---|---|---|---|
| 1 | Qwen3 Max | Alibaba | $2.40 | $1.20 / $6.00 | 256K | 5 | DeepInfra |
| 2 | Qwen3.8 Max | Alibaba | $3.00 | $2.00 / $6.00 | 992K | 8 | Alibaba Cloud Model Studio |
| 3 | Qwen3.7 Max | Alibaba | $3.75 | $2.50 / $7.50 | 992K | 6 | Alibaba Cloud Model Studio |