AETHER · API

Context optimizationAdd it with a single API call.

Add the Aether REST API to your backend flow. Optimize context with Compress, or combine optimization and a model response with Generate.

Check out the API reference Quick Start

API Methods

Integration option that suits your flow.

Both production endpoints use the same authentication, idempotency, and error contract.

Compress

Send context and query; Get the optimized input to use in your model call.

Generate

Reduce the integration surface by running optimization and model generation in a single request.

Usage metrics

Track the original token, optimized token and savings rate from the response metadata.

request id

Track each call in log, support and audit processes via request ID.

Quick Start

Start with a single call.

Generate your API key, submit your input, and use the optimized context with your existing model provider.

Open installation steps →

const response = await fetch("https://api.aether.tr/v1/compress", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <API_KEY>",
    "Idempotency-Key": crypto.randomUUID(),
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    context: "Your long context...",
    query: "What should be answered?",
    level: "auto"
  })
});

const payload = await response.json();
if (!response.ok) throw new Error(payload.error?.code ?? "AETHER_API_ERROR");
console.log(payload.data.compressed);

Smaller context. More controlled AI cost.

Contact our team to add Aether Compress to your current LLM workflow.