Model catalog

Qwen models, with honest availability

Compare every Qwen catalog entry by capability and availability. Live means callable now; Preview means the production route is still pending.

11All models
5Live
6Preview
Qwen Image 3Live

Qwen Image 3

qwen-image-3

High-fidelity text-to-image and image-to-image generation with strong typography, layout, and multilingual prompt following.

Modality
Image
Cost
10 credits / image
Input
Text, up to 3 images
Output
PNG or JPEG
View API reference
Qwen2 ImageLive

Qwen2 Image

qwen2-image

Reliable Qwen image route for text generation and image editing workflows with broad prompt and aspect-ratio support.

Modality
Image
Cost
10 credits / image
Input
Text or image
Output
PNG or JPEG
View API reference
Qwen Image 2512Live

Qwen Image 2512

qwen-image-2512

Cost-efficient image generation route for production batches, concept exploration, and image-editing pipelines.

Modality
Image
Cost
5 credits / image
Input
Text or images
Output
PNG, JPEG, WebP
View API reference
Qwen Multi-AnglesLive

Qwen Multi-Angles

qwen-multi-angles

Create a new camera viewpoint from one to three reference images using explicit horizontal, vertical, and distance controls.

Modality
Image
Cost
5 credits / image
Input
1-3 images
Output
PNG or JPEG
View API reference
Qwen LayeredLive

Qwen Layered

qwen-layered

Decompose a source image into editable semantic layers for design, compositing, and asset-production workflows.

Modality
Image
Cost
10 credits / layer
Input
Image and instruction
Output
Layer images
View API reference
Qwen3 MaxPreview

Qwen3 Max

qwen3-max

Flagship Qwen language model catalog entry for advanced reasoning and general-purpose text workloads.

Modality
Chat
Cost
Route pending
Input
Text
Output
Text
View preview details
Qwen3 Coder PlusPreview

Qwen3 Coder Plus

qwen3-coder-plus

Code-focused Qwen catalog entry for repository analysis, generation, refactoring, and agentic development.

Modality
Chat
Cost
Route pending
Input
Text and code
Output
Text and code
View preview details
Qwen3 VL PlusPreview

Qwen3 VL Plus

qwen3-vl-plus

Vision-language catalog entry for understanding documents, screenshots, photos, and mixed visual context.

Modality
Vision
Cost
Route pending
Input
Text and images
Output
Text
View preview details
Text Embedding V4Preview

Text Embedding V4

text-embedding-v4

Embedding catalog entry for semantic search, retrieval, clustering, and ranking pipelines.

Modality
Embedding
Cost
Route pending
Input
Text
Output
Vectors
View preview details
Qwen Audio 3 TTS FlashPreview

Qwen Audio 3 TTS Flash

qwen-audio-3-tts-flash

Low-latency Qwen text-to-speech catalog entry awaiting a billing-backed production route.

Modality
Audio
Cost
Route pending
Input
Text
Output
Audio
View preview details
Qwen Audio 3 TTS PlusPreview

Qwen Audio 3 TTS Plus

qwen-audio-3-tts-plus

Quality-focused Qwen text-to-speech catalog entry awaiting a billing-backed production route.

Modality
Audio
Cost
Route pending
Input
Text
Output
Audio
View preview details