Match your specific use case
Text generation
From most capable to most cost-effective — pick what fits your use case. More
Qwen models
qwen3.8-max
Complex reasoning and coding
qwen3.7-plus
Balanced performance, speed, and cost
qwen3.8-flash
Fast and cost-effective
Third-party models
Same API format as Qwen models.
deepseek-v4-pro-0813
Text generation
deepseek-v4.1-flash
Text generation, vision understanding
kimi-k2.7-code
Text generation
kimi-k3
Text generation
glm-5.2
Text generation
glm-5.3
Text generation
Image & video
Understanding
Extract text descriptions or structured data from images and videos. More
qwen3.8-max
Visual understanding
qwen3.7-plus
Visual understanding
qwen3.8-omni-flash
Visual understanding
kimi-k2.7-code
Visual understanding
Generation
Generate images and videos from text or images, with support for editing, reference, and high-resolution output. More
qwen-image-3.0-pro
Image generation
wan2.7-image-pro
Image generation
wan3.0-video
Video generation
wan3.0-video-prime
Video generation
happyhorse-1.1-t2v
Video generation
happyhorse-1.1-i2v
Video generation
happyhorse-1.1-r2v
Video generation
happyhorse-1.0-video-edit
Video generation
World models
Build interactive digital worlds with Adventure, Directing, and Acting modes. More
happyoyster-1.0-adventure
World exploration
happyoyster-1.0-directing
Real-time directing
happyoyster-1.0-acting
Character acting
Audio & speech
Text-to-speech
For audiobook reading, voice broadcasting, virtual avatars, and more. More
Speech recognition
Dedicated ASR and LLM-based approaches — choose based on accuracy and flexibility. More
qwen-audio-3.1-asr-flash-streaming
Speech recognition
qwen-audio-3.1-asr-flash-filetrans
Speech recognition
qwen3.5-omni-plus-realtime
Speech recognition
qwen3.5-omni-plus
Speech recognition
Speech-to-speech
End-to-end voice conversation without separate ASR and TTS calls. More
qwen3.8-omni-flash-realtime
Speech-to-speech
qwen-audio-3.1-realtime-plus
Speech-to-speech
qwen3.5-omni-plus
Speech-to-speech
Omni
Integrates understanding and generation capabilities across text, image, audio, and video modalities. More
Embeddings & reranking
Convert text or multimodal content into vectors, combined with reranking to improve retrieval accuracy. More
qwen3.7-text-embedding
Embeddings
text-embedding-v4
Embeddings
tongyi-embedding-vision-plus
Embeddings
qwen3-rerank
Reranking
Decision models
Structured decision models for high-frequency business decisions. A single forward pass performs classification, yes-or-no decisions, and scoring, returning probability distributions and confidence.
View all models
Model Marketplace
Explore our complete collection of text, image, video, audio, and embedding models with detailed specifications and pricing.