Overview
Qwen3.5 Omni Plus is the premium omni-modal model in the Qwen series, supporting text, audio, image, and video inputs with text and audio output. It delivers the highest accuracy among Qwen Omni models for demanding multimodal tasks.
Key Features
- Premium omni-modal — Highest accuracy in the Qwen Omni lineup
- Omni-modal input — Accepts text, audio, image, and video inputs
- Text + audio output — Generate high-quality speech responses alongside text
- Best for — Complex multimodal reasoning, voice assistants, and content analysis
- OpenAI-compatible API — Drop-in replacement using chat completions format
Pricing
Per Million Tokens
Text Input: $1.40
Audio Input: $11.00
Image/Video Input: $1.40
Text Only Output: $8.30
Text Multimodal Output: $8.30
Audio Output: $44.00
Parameters
No input schema available.