Qwen 2.5 VL 72B Instruct
by Qiniu · listed Aug 2025TV
Qwen vision-language model for visual reasoning, documents, and agent tasks
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
qwen2.5-vl-72b-instruct- Context window
- 128K tokens
- Max output
- 8K tokens
- Input modalities
- text, image, audio, video
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-08-05
- Last updated
- 2025-08-05
- Provider docs
- developer.qiniu.com/aitokenapi
Also listed at
- NanoGPT$0.70 in · $0.70 out
- Kilo Gateway$0.80 in · $1.00 out
- NovitaAI$0.80 in · $0.80 out
- OpenRouter$0.80 in · $1.00 out
- OVHcloud AI Endpoints$1.01 in · $1.01 out
- Cortecs$1.01 in · $1.01 out