prices synced 2026-07-28

Qwen3 VL 30B A3B Instruct

Alibaba · Multimodal · Released Oct 2025

Compare

A 30B multimodal vision-language model from Alibaba that processes text, images, and video with a 262k-token context window.

Strengths
Handles longer documents and complex multimodal tasks with its extended context window, larger than the 8B and 32B VL models in the same generation.
Best for
Long-form document analysis with visual content, where extended context and parameter count matter more than reasoning overhead.
Limitations
Lacks the extended reasoning capabilities of the Qwen3 VL 30B A3B Thinking variant, which offers structured problem-solving for more complex tasks.

Input / 1M

$0.15

Output / 1M

$0.6

Cached input / 1M

Context window

262K

Price history

Input (solid)Output (dashed)
Price per 1M tokens over timeOutput went from $0.52 to $0.6; Input went from $0.13 to $0.15 between Jun 2026 and Jul 2026.$0$0.2$0.4$0.6Output on 11 Jun 2026: $0.52Output on 23 Jul 2026: $0.6Out $0.6Input on 11 Jun 2026: $0.13Input on 23 Jul 2026: $0.15In $0.15Jun 2026Jul 2026

Price change

30d
in increased 15.4% out increased 15.4%
90d
in increased 15.4% out increased 15.4%
1y
in increased 15.4% out increased 15.4%
Since launch
in increased 15.4% out increased 15.4%

Snapshots

Effective Input Output Cached in Note Source
23 Jul 2026 $0.15 $0.6 Imported from OpenRouter openrouter.ai
11 Jun 2026 $0.13 $0.52 Imported from OpenRouter openrouter.ai

More from Alibaba

Report a problem