VISION & MULTIMODAL · Qwen
Qwen2.5 VL 72B Instruct
Qwen2.5 VL 72B Instruct is a language model from Qwen in the Qwen family, living in Maple Highlands (vision & multimodal). It reads text and images and writes text, with a 128K-token context window and up to 115K tokens of output. On OpenRouter it costs $0.800 per million input tokens and $1.00 per million output tokens.
See Qwen2.5 VL 72B Instruct in 3DOpen in the WorktableView on OpenRouter
Specifications
- Provider
- Qwen
- Family
- Qwen
- Province
- Maple Highlands
- Context window
- 128K tokens
- Maximum output
- 115K tokens
- Input / 1M tokens
- $0.800
- Output / 1M tokens
- $1.00
- Accepts
- text, images
- Produces
- text
- Reasoning
- No
- Tool use
- No
- Added to OpenRouter
- 2025-02-01
- Model ID
qwen/qwen2.5-vl-72b-instruct- Price history
- —All recorded prices
From the 2026-10-24 catalog snapshot. Prices are US dollars per million tokens.