Qwen2-VL-72B
Qwen2 vision-language flagship. Strong on document understanding, chart QA, and agentic UI tasks.
Qwen2-VL-72B is a multimodal AI model from Qwen. It costs $2.00 per million input tokens and $2.00 per million output tokens (blended $2.00/M), with a 32,000-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.
- Strong vision
- Document understanding
- Open weights
- Long-video support
- Self-hosted vision QA
- Document parsing
- UI agents
Benchmarks
More from Qwen
See all 22 →Frequently asked questions
How much does Qwen2-VL-72B cost?
Qwen2-VL-72B costs $2.00 per million input tokens and $2.00 per million output tokens, for a blended reference rate of $2.00 per million tokens.
What is Qwen2-VL-72B's context window?
Qwen2-VL-72B supports up to 32,000 tokens of context in a single request.
What is Qwen2-VL-72B best for?
Qwen2-VL-72B is well suited to Strong vision, Document understanding and Open weights.
Who makes Qwen2-VL-72B?
Qwen2-VL-72B is developed and served by Qwen. It was released in Aug 2024.
