Qwen/Qwen2.5-72B-Instruct

by DeepInfra — Price updated 2026-04-04

Pricing ($/1M tokens)
Input $0.12
Output $0.39
Specifications
Context Window 32,768
Max Output 32,768
Input text
Output text
About This Model

Qwen/Qwen2.5-72B-Instruct is a budget-friendly language model from DeepInfra.

It supports a context window of 32K tokens with up to 32K output tokens.

With input pricing at $0.12/1M tokens, it sits in the mid-range of available models.