Skip to main content

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.

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).
One origin, both dialects

3 · Make the first call

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).
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:

Claude Code

Four environment variables and Claude Code runs on the Layer X1 catalog.

Codex CLI

One provider block in config.toml, wire_api = responses.

Cursor

OpenAI-compatible base URL + key in the model settings.

Other tools

Aider, Continue, and Cline — exact config for each.