All Models

Qwen3 VL 30B A3B Instruct

qwenTool CallingAttachmentsOpen WeightsStructured Output

Qwen vision-language model for visual reasoning, documents, and agent tasks

Providers9
ReleasedSep 23, 2025
Input Modalitiestext, image, video
Output Modalitiestext
Tarsk Usecoding

Benchmarks

7.9
Intelligence Index
72.3
Math Index

Available Providers (9)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Kilo Gatewayqwen/qwen3-vl-30b-a3b-instruct$0.13/MTok$0.52/MTok131.1K32.8K
OpenRouterqwen/qwen3-vl-30b-a3b-instruct$0.13/MTok$0.52/MTok262.1K32.8K
LLM Gatewaydeepinfra/qwen3-vl-30b-a3b-instruct$0.15/MTok$0.60/MTok262.1K32.8K
DevPass (LLM Gateway)qwen3-vl-30b-a3b-instruct$0.15/MTok$0.60/MTok262.1K8.2K
NEAR AI CloudQwen/Qwen3-VL-30B-A3B-Instruct$0.15/MTok$0.55/MTok16.4K8.2K
LLM Gatewaynovita/qwen3-vl-30b-a3b-instruct$0.20/MTok$0.70/MTok131.1K32.8K
NovitaAIqwen/qwen3-vl-30b-a3b-instruct$0.20/MTok$0.70/MTok131.1K32.8K
SiliconFlow (China)Qwen/Qwen3-VL-30B-A3B-Instruct$0.29/MTok$1/MTok262K262K
SiliconFlowQwen/Qwen3-VL-30B-A3B-Instruct$0.29/MTok$1/MTok262K262K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output