明确标注真实可用性的 Qwen 模型目录

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

模态

图像

成本

10 credits / image

输入

Text, up to 3 images

输出

PNG or JPEG

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

模态

图像

成本

10 credits / image

输入

Text or image

输出

PNG or JPEG

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

模态

图像

成本

5 credits / image

输入

Text or images

输出

PNG, JPEG, WebP

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

模态

图像

成本

5 credits / image

输入

1-3 images

输出

PNG or JPEG

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

模态

图像

成本

10 credits / layer

输入

Image and instruction

输出

Layer images

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

模态

对话

成本

Route pending

输入

Text

输出

Text

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

模态

对话

成本

Route pending

输入

Text and code

输出

Text and code

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

模态

视觉

成本

Route pending

输入

Text and images

输出

Text

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

模态

向量嵌入

成本

Route pending

输入

Text

输出

Vectors

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

模态

音频

成本

Route pending

输入

Text

输出

Audio

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

模态

音频

成本

Route pending

输入

Text

输出

Audio