Thursday, October 29, 2026 🏢 AI Companies Hub RSS About Contact Admin
POPULAR BEATS: Generative AI LLMs & NLP Autonomous Agents Robotics & Hardware Enterprise AI AI Ethics & Policy 🏢 All AI Companies

Qwen 2.5 72B Instruct

Dense Transformer Open Weights
Official Source & Paper
Alibaba Cloud logo Alibaba Cloud 📄 Open Weights (Apache 2.0) 🌍 China (China) 🗓️ Effective Date: 19.09.2024

Widely recognized as one of the world's strongest open-weights 70B-class models, achieving near-frontier scores across coding and STEM.

Model Size / Parameters 72.7B Dense Architecture: Dense Transformer Open Weights
Context Window (Input) 128k tokens Token Capacity
Max Output Tokens 8,192 tokens Single Generation Limit
Supported Modalities Text, Code Native Multimodal Ingestion
License & Access Open Weights (Apache 2.0) Open Weights vs. API
Release Date September 2024 Effective Date: 19.09.2024

Verified Benchmark Results

Standardized academic and industry evaluation benchmarks (Effective Date: 19.09.2024).

MMLU-Pro / 5-Shot General Intellect
86.1%
SWE-bench Verified Software Engineering
41.5%
MATH 500 / AIME Mathematical Reasoning
83.1%
GPQA Diamond Doctoral Science
50.2%
HumanEval / Python Algorithm Synthesis
86.4%

Pricing & Cost Efficiency

Official API token pricing and self-hosted licensing terms.

Input Pricing (Prompt)
$0.35 / 1M tokens
Per 1 million processed tokens
Output Pricing (Generation)
$0.70 / 1M tokens
Per 1 million generated tokens
Verified Datasheet: Source: Alibaba Cloud Research Documentation • Effective Date: 19.09.2024
← Back to All AI Model Datasheets

Latest Coverage & Analysis on Qwen 2.5 72B Instruct