Qwen2-72B-Instruct
Previous-generation flagship Qwen. Largely superseded by Qwen2.5, kept for legacy fine-tunes.
Qwen2-72B-Instruct is a frontier AI model from Qwen. It costs $0.9000 per million input tokens and $0.9000 per million output tokens (blended $0.9000/M), with a 128,000-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
Hand-maintained from Qwen's published pricing; no check date on record.
- Open weights
- Multilingual
- Wide ecosystem
- Existing Qwen2 fine-tunes
- Migration to Qwen2.5
Benchmarks
More from Qwen
See all 22 →Frequently asked questions
How much does Qwen2-72B-Instruct cost?
Qwen2-72B-Instruct costs $0.9000 per million input tokens and $0.9000 per million output tokens, for a blended reference rate of $0.9000 per million tokens.
What is Qwen2-72B-Instruct's context window?
Qwen2-72B-Instruct supports up to 128,000 tokens of context in a single request.
What is Qwen2-72B-Instruct best for?
Qwen2-72B-Instruct is well suited to Open weights, Multilingual and Wide ecosystem.
Who makes Qwen2-72B-Instruct?
Qwen2-72B-Instruct is developed and served by Qwen. It was released in Jun 2024.
