Qwen: Qwen2.5 VL 72B Instruct
阿里云 Qwen · Text
Qwen vision-language model for visual reasoning, documents, and agent tasks
Model ID qwen/qwen2.5-vl-72b-instructUpdated Jan 26, 2025
Pricing & billing
Billing unit: 1M tokens. Vendor reference price; conversion is approximate.
ItemUSD referenceList price (USD)
Input$0.80$0.80
Output$1.00$1.00
Cache read—No public pricing—No public pricing
Cache write—No public pricing—No public pricing
Specifications
- Form
- Text model
- Input modalities
- Text、Image
- Output modalities
- Text
- Context length
- 128K
- Max output
- 115K
- Weights
- Open weights
- Family
- qwen
- Knowledge cutoff
- 2024-04
- Released
- Jan 26, 2025
Uses and capabilities
Capabilities Text model、Structured output、Open weights
Function calling
Structured output
Reasoning
Prompt caching
Open weights
Sources
Use these links to verify specs and pricing — they may point to the vendor's site or to a third-party catalog.