All Models

Qwen3 VL 30B A3B Thinking

ReasoningTool CallingAttachmentsOpen WeightsStructured Output

Multimodal model for analyzing text, images, documents, and rich media

Providers6
ReleasedOct 6, 2025
Input Modalitiestext, image, video
Output Modalitiestext
Tarsk Usecoding

Available Providers (6)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
NovitaAIqwen/qwen3-vl-30b-a3b-thinking$0.20/MTok$1/MTok131.1K32.8K
Kilo Gatewayqwen/qwen3-vl-30b-a3b-thinking$0.20/MTok$2.40/MTok131.1K32.8K
OpenRouterqwen/qwen3-vl-30b-a3b-thinking$0.20/MTok$2.40/MTok262.1K32.8K
SiliconFlow (China)Qwen/Qwen3-VL-30B-A3B-Thinking$0.29/MTok$1/MTok262K262K
SiliconFlowQwen/Qwen3-VL-30B-A3B-Thinking$0.29/MTok$1/MTok262K262K
Qiniuqwen3-vl-30b-a3b-thinking—/MTok—/MTok128K32K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output