Qwen/Qwen3-Omni-30B-A3B-Instruct

Qwen/Qwen3-Omni-30B-A3B-Instruct

A multimodal large language model from Alibaba
2025-09-23
LLM
Model capability: imageModel capability: thinkingModel capability: function_call
Input:
$0.1/1M tokens
Output:
$0.4/1M tokens
Bulk order? Contact your manager for exclusive deals

API Overview

Qwen3-Omni-30B-A3B-Instruct is a new member of Alibaba's Qwen3 series from the Tongyi Qianwen team. It is a Mixture-of-Experts (MoE) model featuring 30 billion total parameters and 3 billion active parameters, effectively reducing inference costs while maintaining strong performance. The model was trained on high-quality, multi-source, multilingual data and excels in fundamental capabilities such as multilingual dialogue, coding, and mathematics.

Playground

Log in to explore more features! Click to Log In

API Analytics

API Reference (1)

API DescriptionAPI EndpointRequest MethodStabilityParameter Description
Chat(SiliconFlow)
POST
Stable
View Details

API Pricing

$
ModelDescriptionContextOfficial Price302.AI Price

Qwen/Qwen3-Omni-30B-A3B-Instruct

-
64000

Input$0.1 / 1M tokens
Output$0.4 / 1M tokens

Input$0.1/ 1M tokens
Output$0.4/ 1M tokens
Original Price