Quickstart

Inert speaks three API shapes on one base URL: the Anthropic Messages API (/v1/messages), the OpenAI Chat Completions API (/v1/chat/completions) and the OpenAI Responses API (/v1/responses). Same headers either way. Get a key, fund it, point a request at it.

Base URL and auth

The base URL is the bare host. Send the key in either header:

text

https://api.inert.lol

x-api-key: <key>
Authorization: Bearer <key>

Create a key

Keys are generated in the Inert dashboard. If you do not have an account yet, sign up first, then create a key from the dashboard. A key is shown once and never again, so store it like a secret.

Fund your balance

A new account starts at zero, so add funds before the first request. Until the balance covers it, every request comes back with Your credit balance is too low to access the Inert API.

List models

The model IDs are the route names, kebab-cased: fable-5 and opus-5. GET /v1/models is always the live list:

bash

curl https://api.inert.lol/v1/models \
  -H "x-api-key: <key>"

First request

OpenAI-SDK tools point their base URL at https://api.inert.lol/v1 and send a chat completion:

bash

curl https://api.inert.lol/v1/chat/completions \
  -H "Authorization: Bearer <key>" \
  -H "Content-Type: application/json" \
  -d '{"model": "fable-5", "messages": [{"role": "user", "content": "hello"}]}'

For the OpenAI SDK, set the environment instead:

bash

OPENAI_BASE_URL=https://api.inert.lol/v1
OPENAI_API_KEY=<key>

Anthropic-native tools use /v1/messages instead; see the Claude Code guide. Codex CLI uses /v1/responses; see the Codex CLI guide.

Next steps

Claude CodeThe flagship harness, and a native Anthropic client.