Qwen2.5 72B Instruct

Qwen2.5 72B Instruct

Developer	Qwen
Release date	September 19, 2024
Family	Qwen
Generation	Qwen 2.5
Size class
Context window	33K tokens
Max output	16K tokens
Input	Text
Output	Text
Knowledge cutoff	2024-06-30
Weights	Open weights
Website	qwen.ai
Links	Model card Hugging Face

Part of a series on

input: $0.36
output: $0.40
Context: 33Ktokens
Released: 2y ago
Size: 72Bparameters

Specifications

Model

Developer: Qwen
Family: Qwen Qwen 2.5
Type: Language model
Released: September 19, 2024
Model ID: qwen/qwen-2.5-72b-instruct

Capabilities

Input → output: Text → Text
Native context: 32K tokens
Max output: 16K tokens
Tokenizer: Qwen
Knowledge cutoff: 2024-06-30

Weights

Openness: Open weights
Size: 72B
Hugging Face: Qwen/Qwen2.5-72B-Instruct

Sources:OpenRouter

Metadata synced Nov 11, 2026, 6:58 PM UTC

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.