Overview
Atlas Cloud is an AI API aggregation platform that provides unified access to 300+ AI models through a single API. One API key, one billing account, and consistent API patterns across all model types and providers.
Key Features
- 300+ Models: Access models from DeepSeek, Qwen, ByteDance, Black Forest Labs, Luma, MiniMax, MoonshotAI, and many more
- Unified API: Consistent API interface across all model types — LLM, image, video, and more
- OpenAI-Compatible: LLM endpoints are fully compatible with the OpenAI SDK — just change the base URL
- High Performance: Optimized inference infrastructure with fast generation speeds
- Competitive Pricing: Cost-effective access to premium AI models with transparent pay-as-you-go billing
- Developer-Friendly: Comprehensive documentation, SDK support, MCP Server, and Claude Code Skills
Supported Model Types
Our comprehensive model library covers a wide range of AI capabilities:
| Type | Description | Example Models |
|---|---|---|
| LLM | Large language models for chat, reasoning, and code | DeepSeek V3, Qwen, Kimi, GLM |
| Text-to-Image | Generate images from text descriptions | Seedream, FLUX, Qwen-Image, Ideogram |
| Image-to-Image | Transform and enhance existing images | Style transfer, upscaling, inpainting |
| Image Tools | Advanced image processing and manipulation | Background removal, face swap, upscaler |
| Text-to-Video | Create videos from text prompts | Kling, Vidu, Seedance, Wan, Hailuo, Veo |
| Image-to-Video | Animate static images into videos | Kling, Seedance, Luma |
| Video-to-Video | Transform and enhance video content | Style transfer, video effects |
| Audio-to-Video | Generate videos with synchronized audio | Lip-sync, music video generation |
Supported Providers
We integrate cutting-edge AI models from industry-leading organizations:
| Provider | Specialties |
|---|---|
| DeepSeek | High-performance reasoning and coding models |
| Qwen (Alibaba) | Multilingual LLM, Qwen-Image |
| ByteDance | Seedream image generation, Seedance video, Kling |
| Black Forest Labs | FLUX image generation series |
| MiniMax | Hailuo video, multimedia content |
| MoonshotAI | Kimi series LLM models |
| Luma AI | Professional video generation |
| KwaiVGI | Kling video generation series |
| Vidu | Next-generation video AI |
| HiDream | Creative AI for artistic content |
| PixVerse | Video generation and editing |
| Zhipu AI | GLM bilingual models |
| More | Additional providers and emerging technologies |
For a complete list of all available models, visit the Model Library.
API Endpoints
| Endpoint | Method | Description |
|---|---|---|
/v1/chat/completions | POST | LLM chat completions (OpenAI-compatible) |
/api/v1/model/generateImage | POST | Image generation |
/api/v1/model/generateVideo | POST | Video generation |
/api/v1/model/uploadMedia | POST | Upload files for generation tasks |
/api/v1/model/prediction/{id} | GET | Get async generation results |
For full API details, see the API Reference.
Getting Started
- Create an account and get your API key
- Choose a model from the Model Library
- Make your first API call — see the Quick Start guide
- Explore model-specific guides: LLM · Image · Video