Routing and reliability

Models and the catalog

What the catalog lists, how model ids are spelled, and which context figure to budget against.

The catalog is every model you can call by slug. One rule holds it together: what GET /v1/models lists, the public catalog shows, and the gateway serves are the same set. A model is never listed if no request can reach it, and the gateway never serves a model the catalog hides.

Three ways to read the catalog

EndpointShapeKey
GET /v1/modelsOpenAI list of slugs, with data_policy per modelYes
GET /api/modelsFull catalog: prices, context, capabilities, providers, filtersOptional
GET /api/v1/modelsOpenRouter shape, <vendor>/<slug> idsOptional

With your key, the listings add your organization's private models and the :free spellings you are eligible for.

GET/v1/modelsGET/api/modelsGET/api/models/{slug}
curl "https://api.experientiallabs.ai/api/models?sort=preferred&limit=20"

Spellings of one model

A model has one slug. Several spellings resolve to it at request time, so tools written for other gateways work unchanged. Usage and billing always record the slug.

You sendResolves toNote
claude-sonnet-5.5claude-sonnet-5.5The slug (dot form)
anthropic/claude-sonnet-5.5claude-sonnet-5.5OpenRouter-style vendor prefix
claude-sonnet-5-5claude-sonnet-5.5Anthropic's dashed id
<slug>:freethe free lane of <slug>Free only, never charged, see Free models
<slug>:fastthe priority tier of <slug>Only on models that list a fast path; priced higher
claude-sonnet-5-5-20261001refusedDated ids are not spellings: 403 model_not_granted
client.chat.completions.create(
    model="anthropic/claude-sonnet-5.5",
    messages=[{"role": "user", "content": "Hi"}],
)
# response.model == "claude-sonnet-5.5"

Context window vs max input tokens

context_window is the total: prompt plus the model's maximum output. Providers count the whole maximum output inside the window, whatever max_tokens you ask for. Size your prompt budget, and any agent compaction setting, to max_input_tokens.

Fieldgpt-6-luna
context_window1,050,000
max_output_tokens128,000
max_input_tokens922,000 (window minus max output)
{
  "model": {
    "slug": "gpt-6-luna",
    "context_window": 1050000,
    "max_output_tokens": 128000,
    "max_input_tokens": 922000
  }
}

Pinning a coding agent's context limit to context_window lets a session grow past what the provider accepts, and the session can no longer compact.

What a catalog entry tells you

FieldMeaning
providers[]Each rung: provider, prices in nano-USD per million tokens, capabilities
billing_sourcehost_managed (credits) or customer_managed (your key)
pricing_sourceWhere the price comes from. An estimate is never billed
retentionzdr_all_rungs, zdr_enforceable or not_zdr, see Data controls
uptime and latencyMeasured from real traffic once a route has enough volume

Filter GET /api/models with modality, provider, min_context, supports, retention, free=true and sort. Some makers (OpenAI, Anthropic, Gemini) serve only requests from their supported countries; listing a model does not establish regional eligibility.

{
  "provider": "anthropic",
  "billing_source": "host_managed",
  "input_nano_usd_per_million": 4000000000,
  "cached_input_nano_usd_per_million": 200000000,
  "output_nano_usd_per_million": 20000000000,
  "pricing_source": "provider-docs"
}

1,000,000,000 nano-USD is $1, so this rung is $4 input and $20 output per million tokens.