Skip to main content

​
What is Layer X1

Layer X1 serves its own catalog of lx1- models through a single gateway that is wire-compatible with the Anthropic Messages API, the OpenAI Chat Completions API, and the OpenAI Responses API. Swap your base URL and key; keep the rest of your stack exactly as it is. What you get on the other side of that swap:
  • The whole catalog, one key — from fast, near-free small models to premium reasoning and vision, all included on every plan. See Models.
  • Every protocol your tools speak — Messages, Chat Completions, Responses, legacy Completions, embeddings, and batches, with streaming on every chat surface.
  • Sessions that keep moving — if a model can’t answer, the engine keeps your session moving. See Reliability.
  • Predictable plans — a monthly pool of included usage measured in dollars at public list rates, with published rate limits. See Plans & limits.
  • A surface for jobs, not just turns — durable runs, state handles, and queryable artifacts for work that outlives a request. See Agent Runs.

​
Base URL

The gateway lives at a single origin. Every endpoint is served under /v1.
API keys are created in the dashboard and are prefixed lx1_. The Anthropic-style endpoints accept the key as x-api-key; the OpenAI-style endpoints accept it as a bearer token. See Authentication for the details.
A first request (Anthropic-compatible)

​
Next steps

Quickstart

Key → base URL → first call, in three steps. One command for coding agents.

Claude Code

Run Claude Code on the Layer X1 catalog with four environment variables.

API reference

Every endpoint on the unified surface, with request and response shapes.

Models

The full catalog: tiers, context windows, capabilities, and list pricing.

Migrating

Already calling OpenAI or Anthropic? It is usually two lines.

Troubleshooting

The failures people actually hit, and the one thing to change for each.