Qwen3 VL 30B A3B Thinking

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex 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.

ChatQwen262k tokens$0.218 / $2.6161 · 1M

qwen/qwen3-vl-30b-a3b-thinking

Contexto
262k tokens
Máx. completion
32,768
Tools
Sí
JSON
Sí
Lanzamiento
2025-10-06

Llámalo desde Geek Hub

El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-vl-30b-a3b-thinking",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es Qwen3 VL 30B A3B Thinking?
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex 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. Qwen3 VL 30B A3B Thinking corre en el API de Geek Hub (compatible con OpenAI). Id: qwen/qwen3-vl-30b-a3b-thinking.
¿Qwen3 VL 30B A3B Thinking es gratis?
No. El input cuesta $0.218 / 1M tokens y el output $2.6161 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de Qwen3 VL 30B A3B Thinking?
Qwen3 VL 30B A3B Thinking tiene una ventana de 262k tokens. Soporta hasta 32,768 tokens de completion.
¿Qwen3 VL 30B A3B Thinking soporta tool calling y structured outputs?
Qwen3 VL 30B A3B Thinking acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó Qwen3 VL 30B A3B Thinking?
Qwen3 VL 30B A3B Thinking se lanzó el 6 de octubre de 2025.

Más modelos de Qwen