---
id: "qwen/qwen3-vl-30b-a3b-instruct"
also: ["qwen/qwen3-vl-30b-a3b-instruct", "Qwen/Qwen3-VL-30B-A3B-Instruct", "hf/Qwen/Qwen3-VL-30B-A3B-Instruct"]
cheapest_list_usd_per_m: "0.13 in, 0.52 out, at alibaba on openrouter"
cheapest_effective_usd_per_m: "0.1291 in, 0.5135 out, at alibaba on openrouter"
context: 262144
max_output: 16384
input: ["text", "image"]
output: ["text"]
released: "2025-10-06"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 7
gateways: "openrouter (4), hf (3)"
no_training: 4
trains: 0
retains_prompts: 1
---
# Qwen: Qwen3 VL 30B A3B Instruct

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...