Match your specific use case
Text generation
Explore our flagship text generation models for various use cases. More
qwen3.6-max-preview
Complex reasoning and coding
qwen3.6-plus
Balanced performance, speed, and cost
qwen3.6-flash
Fast and cost-effective
Images & videos
Understanding
Understand images and video with multimodal models. More
Generation
Create images and videos from text or images. More
qwen-image-2.0-pro
Text-to-image and image editing
wan2.7-image-pro
Text-to-image
wan2.7-t2v
Text-to-video
wan2.7-i2v
Image-to-video
Audio & speech
Text to speech
Convert text to natural speech. More
cosyvoice-v3-plus
High quality, rich voice library
qwen3-tts-instruct-flash
Instruction control for speed, emotion, style
Speech to text
Transcribe audio to text. More
fun-asr-realtime
Real-time transcription with hotwords
qwen3-asr-flash-realtime
Multilingual real-time transcription
fun-asr
Batch transcription with speaker diarization
Speech to speech
Real-time voice conversation. More
Embedding & reranking
Convert text and images to vectors, and improve search accuracy with reranking. More
text-embedding-v4
Latest text embedding model
tongyi-embedding-vision-plus
Multimodal embedding for text and image
qwen3-rerank
Re-score search results for better accuracy
Browse our full catalog
Model Catalog
Explore our complete collection of text, image, video, audio, and embedding models with detailed specifications and pricing.