Overview
Qwen3 Omni Flash is a multimodal model supporting text, audio, image, and video inputs with text and audio output capabilities. It supports 119 text languages and 20 speech languages for cross-modal tasks at an affordable price point.
Key Features
- Omni-modal input — Accepts text, audio, image, and video inputs
- Text + audio output — Generate speech responses alongside text
- 119 text languages — Broad multilingual text understanding
- 20 speech languages — Wide speech input and output language support
- Affordable — Text input from $0.43 per 1M tokens
- OpenAI-compatible API — Drop-in replacement using chat completions format
Pricing
Per Million Tokens
Text Input: $0.43
Audio Input: $3.81
Image/Video Input: $0.78
Text Only Output: $1.66
Text Multimodal Output: $3.06
Audio Output: $15.11
Parameters
No input schema available.