Skip to main content

​
Browsing the catalog

For an interactive browser with search, category tabs, and per-model details, visit orcarouter.ai/models (coming soon). For programmatic access, use the /v1/models endpoint.

​
List all models

curl https://api.orcarouter.ai/v1/models \
  -H "Authorization: Bearer sk-orca-..."

​
Response shape

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 1626777600,
      "owned_by": "openai",
      "supported_endpoint_types": ["chat.completion"]
    },
    {
      "id": "claude-3-5-sonnet-latest",
      "object": "model",
      "owned_by": "anthropic",
      "supported_endpoint_types": ["chat.completion"]
    }
  ]
}
The list only includes models your account has access to and that have a pricing ratio configured. See the Models API Reference for the full endpoint spec.

​
Get one model

curl https://api.orcarouter.ai/v1/models/gpt-4o \
  -H "Authorization: Bearer sk-orca-..."

​
Naming conventions

Model IDs in OrcaRouter are not prescriptive. Your admin can register models under any name — gpt-4o, openai/gpt-4o, or their own custom alias. You use whatever name appears in your /v1/models response. If your admin uses OpenRouter-style prefixed names (openai/gpt-4o, anthropic/claude-3-5-sonnet), you can use OrcaRouter as a drop-in replacement for OpenRouter SDK usage. If they use bare names (gpt-4o), you’re compatible with the OpenAI SDK convention.

​
Richer metadata coming

Richer per-model metadata — context_length, input_modalities, output_modalities, supported_parameters, full pricing object — is being rolled out in an upcoming release. The current response includes the fields necessary for programmatic routing; the fuller catalog ships with the /models browser page.