
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results. For agentic use, it handles multi-image multi-turn instructions, video timeline alignments, GUI automation, and visual coding from sketches to debugged UI. Text performance matches flagship Qwen3 models, suiting document AI, OCR, UI assistance, spatial tasks, and agent research.
Modalities
In / Out Price
$0.13 / $0.52per 1M
Context
262K
Released
Oct 6, 2025
Knowledge Cutoff
Mar 2025
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results.
Qwen3 VL 30B A3B Instruct costs $0.13/M input tokens and $0.52/M output tokens.
Qwen3 VL 30B A3B Instruct has a 262,144 token context window. It supports up to 32,768 completion tokens.
Yes. Qwen3 VL 30B A3B Instruct accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Qwen3 VL 30B A3B Instruct accepts text and images as input and returns text.
Qwen3 VL 30B A3B Instruct is served by 4 providers on OpenRouter: Alibaba Cloud Int., DeepInfra, NovitaAI and SiliconFlow. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
Qwen3 VL 30B A3B Instruct was released on October 6, 2025. Its knowledge cutoff is March 31, 2025.