Qwen2.5 72B Instruct

Overview

Qwen2.5-72B-Instruct is an instruction-tuned 72 billion parameter language model, part of the Qwen2.5 series. It is designed to follow instructions, generate long texts (over 8K tokens), understand structured data (e.g., tables), and generate structured outputs, especially JSON. The model supports multilingual capabilities across over 29 languages.

Qwen2.5 72B Instruct was released on September 19, 2024. API access is available through 4 providers, including DeepInfra, Hyperbolic and others.

Benchmarks

Qwen2.5 72B Instruct Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Sat Dec 06 2025

Pricing

Pricing, performance, and capabilities for Qwen2.5 72B Instruct across different providers:

Provider	Input ($/M)	Output ($/M)	Max Input	Max Output	Latency (s)	Throughput	Quantization	Input	Output
DeepInfra	$0.35	$0.40	131.1K	8.2K	0.5	10.0 tok/s	—	Text Image Audio Video	Text Image Audio Video
Hyperbolic	$0.40	$0.40	131.1K	8.2K	0.5	100.0 tok/s	—	Text Image Audio Video	Text Image Audio Video
Fireworks	$0.89	$0.89	131.1K	8.2K	0.37	59.0 tok/s	—	Text Image Audio Video	Text Image Audio Video
Together	$1.20	$1.20	131.1K	8.2K	0.5	47.0 tok/s	—	Text Image Audio Video	Text Image Audio Video

Price Comparison for Qwen2.5 72B Instruct

Price per 1M input tokens (USD), lower is better

llm-stats.com - Sat Dec 06 2025

Throughput Comparison for Qwen2.5 72B Instruct

Tokens per second, higher is better

llm-stats.com - Sat Dec 06 2025

Latency Comparison for Qwen2.5 72B Instruct

Time to first token (s), lower is better

llm-stats.com - Sat Dec 06 2025

Example Outputs

API Access