Qwen3 VL Thinking
Qwen vision-language model for visual reasoning, documents, and agent tasks
Context
131,072
Max output
32,768
Input / 1M
$0.40
Output / 1M
$4.00
Providers
1
01Profile
Profile
Released
2025-09-23
Last updated
2025-09-24
Knowledge cutoff
2025-09
Weights
Open
02Capabilities
Capabilities
Input
text · image · pdf
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
No
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
10+ recent events since 2025-09-23
2026-06-06Price cutvercelinput / 1M$0.70→ $0.40
2026-06-06Price cutverceloutput / 1M$8.40→ $4.00
2026-06-06ContextvercelMax output129,024→ 32,768
2026-05-18Price cutvercelinput / 1M$0.70→ $0.40
2026-05-18Price upvercelinput / 1M$0.40→ $0.70
2026-05-18Price cutverceloutput / 1M$8.40→ $4.00
2026-05-18Price upverceloutput / 1M$4.00→ $8.40
2026-05-18ContextvercelMax output129,024→ 32,768
2026-05-18ContextvercelMax output32,768→ 129,024
2025-10-14Addedverceloffering→ new