List and retrieve models.

Why read the catalog

The Models page is a snapshot of the catalog at the time it was generated. The endpoint is the catalog. Models are added, retired and repriced without an API version bump (Reliability), so anything that picks a model at runtime — a router, a model-picker UI, a capability check before sending an image — should read it here rather than ship a copy. This endpoint is unauthenticated and cacheable (cache-control: public, max-age=300). Every SDK calls it at client-init; it costs you nothing and draws no usage.

List

GET /v1/models

curl https://api.layerx1.com/v1/models

Response (OpenAI shape)

{
  "object": "list",
  "data": [
    {
      "id": "lx1-gpt-oss-120b",
      "object": "model",
      "created": 1735689600,
      "owned_by": "sideren",
      "aliases": ["gpt-oss-120b"],
      "tier": "workhorse",
      "context_window": 131072,
      "max_output": 32768,
      "capabilities": {
        "tools": true,
        "reasoning": false,
        "vision": false,
        "documents": false
      },
      "pricing_usd_per_mtok": {
        "input": 0.05,
        "output": 0.35,
        "cached_input": null
      },
      "supported_parameters": [
        "messages", "system", "max_tokens", "temperature",
        "top_p", "stop", "stream", "tools", "tool_choice"
      ],
      "native_wires": ["chat_completions"]
    }
  ]
}

Fields

Field	Notes
`id`	The canonical catalog id — always what you put in `model`.
`aliases`	Other strings that resolve to this model. See Model routing.
`tier`	The catalog tier this model sits in (`frontier`, `premium`, `workhorse`, …), matching the groupings on Models.
`context_window`	Total tokens the model accepts.
`max_output`	Output ceiling, or `null` when the model publishes none.
`capabilities.tools`	Accepts `tools` / `tool_choice`.
`capabilities.reasoning`	Has a reasoning mode. See Reasoning.
`capabilities.vision`	Reads images. See Vision.
`capabilities.documents`	Accepts document/PDF input.
`pricing_usd_per_mtok`	List rates per million tokens: `input`, `output`, and `cached_input` — `null` when the model publishes no cached rate, which is also when repeated context earns no discount (Prompt caching).
`supported_parameters`	The parameter names this model honors. A capability-aware client should check here before sending `response_format` or a forced `tool_choice`.
`native_wires`	Protocols this model is served over natively. Informational — every model works on every endpoint.

Providers and upstream deployment names are never in the response. One row is one logical model; which backend serves it is an implementation detail that can change mid-flight, which is exactly what makes continuity possible.

Anthropic shape

Send an anthropic-version header — as every Anthropic SDK does — and the same endpoint answers in Anthropic’s list envelope instead, so client.models.list() type-checks:

{
  "data": [
    {
      "type": "model",
      "id": "lx1-gpt-oss-120b",
      "display_name": "lx1-gpt-oss-120b",
      "created_at": "2025-01-01T00:00:00.000Z"
    }
  ],
  "has_more": false,
  "first_id": "lx1-gpt-oss-120b",
  "last_id": "lx1-qwen3.7-max"
}

Retrieve one

GET /v1/models/{id}

Accepts a canonical id, an alias, or the bare id without its lx1- prefix — so lx1-gpt-oss-120b, gpt-oss-120b and any published alias all resolve. Returns the same entry shape as the list (or the Anthropic per-item shape with anthropic-version set).

curl https://api.layerx1.com/v1/models/lx1-gpt-oss-120b

An unknown id returns 404:

{ "error": { "type": "not_found", "message": "no such model: lx1-nope" } }

Retrieve is a validity check, so it is deliberately stricter than the chat endpoints: the foreign-name compatibility handles that let gpt-4o work in a chat request are not resolved here. If you need to know what a foreign id maps to, send it to a chat endpoint and read the model back off the response.

From the CLI

npx layerx1 models

Prints the catalog with pricing, straight from this endpoint.

Get started

API reference

Agent-native API

Guides

Reference

List and retrieve models.

Why read the catalog

List

Fields

Anthropic shape

Retrieve one

From the CLI

​Why read the catalog

​List

​Fields

​Anthropic shape

​Retrieve one

​From the CLI

Why read the catalog

List

Fields

Anthropic shape

Retrieve one

From the CLI