Qwen: Qwen3 VL 30B A3B Instruct
Qwen vision-language model for visual reasoning, documents, and agent tasks
Context
262,144
Max output
262,000
Input / 1M
$0.13
Output / 1M
$0.52
Providers
8
01Profile
Profile
Released
2025-10-06
Last updated
2025-11-25
Knowledge cutoff
—
Weights
Closed
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
No
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 9 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2025-10-06
2026-09-09ContextnearaiContext window256,000→ 16,384
2026-09-09ContextnearaiMax output32,768→ 8,192
2026-08-28ContextkiloContext window131,072→ 262,144
2026-08-28ContextkiloMax output32,768→ 16,384
2026-08-28Price upopenrouterinput / 1M$0.13→ $0.15
2026-08-28Price upopenrouteroutput / 1M$0.52→ $0.60
2026-08-28ContextopenrouterMax output32,768→ 16,384
2026-08-20Addedllmgateway-providersoffering→ new
2026-08-20Addedllmgateway-providersoffering→ new
2026-08-14ContextkiloContext window262,144→ 131,072
2026-08-14ContextkiloMax output16,384→ 32,768
2026-08-14Price cutopenrouterinput / 1M$0.15→ $0.13