Qwen2.5-VL 7B Instruct
Qwen vision-language model for visual reasoning, documents, and agent tasks
Context
131,072
Max output
8,192
Input / 1M
$0.29
Output / 1M
$0.72
Providers
3
01Profile
Profile
Released
2024-09
Last updated
2025-08-05
Knowledge cutoff
2024-04
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
No
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
Not listed
Cache write
Not listed
03Pricing
Pricing across 2 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
5+ recent events since 2024-09
2026-06-13Removedsiliconflowofferingremoved→ new
2026-01-15Addedqiniu-aioffering→ new
2025-11-25Addedsiliconflowoffering→ new
2025-10-14Addedalibabaoffering→ new
2025-10-14Addedalibaba-cnoffering→ new