Aiter AI World
EnglishSign inGet started
Loading…

Quickstart

Make your first request in under five minutes with any OpenAI-compatible client.

Base URL for this deployment: https://www.aiteraiworld.com/api/v1

Three steps

  1. Create an account and add credits under Billing. The free tier covers models whose id ends in :free once your email is verified.
  2. Create an API key under API keys. Keys are shown once; give each application its own key with a monthly limit and, optionally, a model allowlist.
  3. Point your client at the base URL below and call /chat/completions with a catalog model id.
text
Base URL: https://www.aiteraiworld.com/api/v1

Your first request

The chat endpoint accepts the OpenAI request format. Only the base URL and the key change.

bash
curl https://www.aiteraiworld.com/api/v1/chat/completions \
  -H "Authorization: Bearer $AITER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "author/model", "messages": [{"role": "user", "content": "Hello!"}]}'
python
from openai import OpenAI

client = OpenAI(base_url="https://www.aiteraiworld.com/api/v1", api_key="<AITER_API_KEY>")
completion = client.chat.completions.create(
    model="author/model",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)
typescript
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://www.aiteraiworld.com/api/v1", apiKey: process.env.AITER_API_KEY });
const completion = await client.chat.completions.create({
  model: "author/model",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);

What comes back

Responses follow the chat.completion object. Every proxied call also carries headers that identify the generation, the provider that served it and what it cost.

json
{
  "id": "gen-6f1c…",
  "object": "chat.completion",
  "model": "author/model",
  "choices": [{ "index": 0, "message": { "role": "assistant", "content": "Hello! How can I help?" }, "finish_reason": "stop" }],
  "usage": { "prompt_tokens": 9, "completion_tokens": 7, "total_tokens": 16 }
}
HeaderMeaning
X-AiterAI-Generation-IdIdentifier for the generation record; pass it to GET /generation?id=.
X-AiterAI-ProviderProvider that served the request after routing and fallback.
X-AiterAI-ModelModel id after alias resolution.
X-AiterAI-CostCost in USD with six decimals. Zero on streams until the record settles.
X-AiterAI-Cachedtrue when an exact cache hit answered the request at no charge.

Next: Streaming, Provider routing and Errors and rate limits.