One key, both protocols.

Getting a key

Keys are created and revoked in the dashboard under /dashboard/keys. A key is shown once at creation — store it somewhere safe. Keys are always prefixed lx1_.

Treat keys as secrets. Set them through environment variables rather than committing them, and rotate from the dashboard if one leaks.

How to present the key

Protocol	Endpoint	Header
Anthropic Messages	`/v1/messages`	`x-api-key: lx1_...`
OpenAI Chat Completions	`/v1/chat/completions`	`Authorization: Bearer lx1_...`
OpenAI Responses	`/v1/responses`	`Authorization: Bearer lx1_...`
Embeddings / Completions / Batches	`/v1/...`	`Authorization: Bearer lx1_...`

The Anthropic endpoint also accepts Authorization: Bearer lx1_... as an alternative to x-api-key, which is convenient when a client only lets you set one auth header.

Examples

Anthropic — x-api-key

curl https://api.layerx1.com/v1/messages \
  -H "x-api-key: lx1_your_key" \
  -H "content-type: application/json" \
  -d '{"model":"lx1-gpt-oss-120b","max_tokens":256,"messages":[{"role":"user","content":"Hi"}]}'

OpenAI — Authorization: Bearer

curl https://api.layerx1.com/v1/chat/completions \
  -H "authorization: Bearer lx1_your_key" \
  -H "content-type: application/json" \
  -d '{"model":"lx1-gpt-oss-120b","messages":[{"role":"user","content":"Hi"}]}'

Failure modes

A missing or malformed key returns 401 with an error body shaped for the protocol you called.
A valid key naming a model that does not exist in the catalog returns 404 — check the id against GET /v1/models.

See Errors for the full status-code reference and body shapes.

Get started

API reference

Agent-native API

Guides

Reference

One key, both protocols.

Getting a key

How to present the key

Examples

Failure modes

​Getting a key

​How to present the key

​Examples

​Failure modes

Getting a key

How to present the key

Examples

Failure modes