Get started · Quickstart

Key. Base URL. First call.

Three steps from zero to a response. If you are wiring up a coding agent, one command does all three — see the fast paths at the bottom.

1 · Get a key

Create a key in the dashboard under /dashboard/api. Keys are prefixed lx1_ and shown once at creation — store yours in an environment variable, not in code.

export LAYERX1_API_KEY=lx1_your_key

2 · Set the base URL

Everything is served from one origin. OpenAI-style clients append /v1; Anthropic-style clients use the bare origin (their SDKs add /v1/messages themselves).

# OpenAI SDKs / OpenAI-compatible tools
https://api.layerx1.in/v1

# Anthropic SDKs / Claude Code
https://api.layerx1.in

One origin, both dialects

3 · Make the first call

curl https://api.layerx1.in/v1/chat/completions \
  -H "authorization: Bearer $LAYERX1_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "lx1-gpt-oss-120b",
    "messages": [{ "role": "user", "content": "Say hello." }]
  }'

Same request in three clients

Swap lx1-gpt-oss-120b for any model in the catalog — every plan includes all of them. Set stream: true for tokens as they are generated (see Streaming).

Note

The Anthropic dialect works the same way: POST to /v1/messages with your key in x-api-key. Both dialects accept every model in the catalog. See the API reference.

Fast paths for coding agents

The layerx1 CLI configures popular coding agents in one command — no install, safe to re-run:

npx layerx1

Claude CodeFour environment variables and Claude Code runs on the lx1 catalog.Codex CLIOne provider block in config.toml, wire_api = responses.CursorOpenAI-compatible base URL + key in the model settings.Other toolsAider, Continue, and Cline — exact config for each.