Qwen/Qwen3-Max-Thinking

by DeepInfra — Price updated 2026-04-04

Pricing ($/1M tokens)
Input $1.20
Output $6.00
Cache Read $0.24
Specifications
Context Window 256,000
Max Output 256,000
Input text
Output text
About This Model

Qwen/Qwen3-Max-Thinking is a mid-range language model from DeepInfra.

It supports a context window of 256K tokens with up to 256K output tokens.

With input pricing at $1.20/1M tokens, it sits in the mid-range of available models.

Available Providers (2)
Provider Input ($/1M) Output ($/1M)
Qwen $0.78 $3.90
DeepInfra $1.20 $6.00