About Aether API
What Aether API is: one OpenAI-compatible endpoint for chat, image, audio, embedding, and video models from 16 providers, with per-token billing, per-key spend limits, and credits that never expire.
Aether API is a gateway for AI models. One base URL, one API key, and one request format give you every model in the catalogue: chat, image generation, audio, embeddings, and video.
What Aether API is
Aether API is a gateway for AI models. One base URL, one API key, and one request format give you every model in the catalogue: chat, image generation, audio, embeddings, and video.
The request format is the OpenAI format. If your code already speaks the OpenAI API, switching is a configuration change: point the SDK at a different base URL and use a different key.
Which models
The catalogue covers 16 providers, including OpenAI, Anthropic, Google, xAI, DeepSeek, Alibaba, Mistral, Moonshot, Minimax, Black Forest Labs, Z.AI, Xiaomi, Perplexity, Runware, Together, and StepFun.
Every model is priced below the provider's own list price, and the saving of each model is on its page.
- Chat, reasoning, and agent workflows
- Image generation and image editing
- Embeddings for search and retrieval
- Text to speech and transcription
- Video generation
How it works
A request goes to the provider that hosts the model, and the answer comes back in the OpenAI format. You do not write a second integration for the second provider.
Usage is metered per token and charged against prepaid credits. The dashboard shows the estimated cost of every request, broken down by API key, so a bill can be explained line by line.
What you get as a customer
Per-token billing without a minimum commitment, and credits that never expire.
A daily or monthly spend limit for every API key, so a runaway loop cannot spend the whole balance.
A public status page, request-level logs, and a support address that reaches a human.
How your data is handled
Under normal operating conditions, Aether API does not store your prompts or responses. If an automated abuse system flags a request, the relevant prompt and response can be retained temporarily for review.
The full rules are in the privacy policy, and the billing rules are in the terms of service.
Where to go next
The model catalogue with every price, context window, and request example. The pricing page with credit packages and pay-as-you-go rates. The quickstart for the first request, and the contact page for support, status, and security reports.
Aether API — OpenAI-compatible access to 13+ providers through one API key.