Platform Overview

Connect an OpenAI-compatible client to ExosAI, choose a model from the live catalog and send your first request. Availability and supported features vary by model.

Base URL
https://api.exosai.tech/v1

ExosAI is one OpenAI-compatible API for many AI models. If your code or tool already talks to OpenAI, you only change two things: the base URL and the API key. Pick any model ID from the live catalog and send the request.

Start in three steps

  1. Create a key in Dashboard → API keys. It is shown once, so save it right away.
  2. Pick a model on the Models page and replace YOUR_MODEL_ID below with its current ID.
  3. Send a request to https://api.exosai.tech/v1/chat/completions. The next pages show it in curl, Python and JavaScript.
bash
curl https://api.exosai.tech/v1/chat/completions \
  -H "Authorization: Bearer $EXOSAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "YOUR_MODEL_ID", "messages": [{"role": "user", "content": "Hello!"}]}'

What you get

  • One key for every model. Switch models by changing the model string. No second SDK or account.
  • Prepaid credit. The playground and the API use the same balance. Every request appears in your usage history with its tokens and cost.
  • Limits you control. Restrict a key to certain models or IP ranges, set request limits, and revoke it any time.
  • Free models. Models ending in :free cost nothing, with stricter rate limits.

Where things are in the dashboard

  • Overview: balance, usage for the last 30 days and recent activity.
  • Playground: chat with any model in the browser, no code needed.
  • API keys: create, limit, rotate and revoke keys.
  • Usage and Limits: requests, tokens, spend and the limits of each key.
  • Billing: manage your plan and balance. Rewards: daily credit and referrals.

ExosAI

ExosAI — OpenAI-compatible AI API