Models

Choose a model on the Pricing page

Open the Omrouter Pricing page, choose a model, and copy the model name shown on the page.

Enter that name in the application’s Model field. Keep its capitalization and punctuation unchanged.

Load models through the API

If an application needs to load models automatically, call this endpoint with the API key:

curl --silent --show-error \
  'https://omrouter.com/v1/models' \
  --header "Authorization: Bearer $OMROUTER_API_KEY"

If the API key has a model restriction, the endpoint returns only the models allowed for that key.

Example response:

{
  "object": "list",
  "data": [
    {
      "id": "model-name",
      "owned_by": "provider",
      "supported_endpoint_types": ["openai", "openai-response"]
    }
  ]
}

Field	Meaning
id	The model name to send in the request’s model field.
owned_by	The model provider.
supported_endpoint_types	Request formats supported by this model.

Request format mapping

For a normal OpenAI client, choose a model that supports openai. The other values matter only when the application specifically requires those formats.

Returned value	Request endpoint
openai	/v1/chat/completions
openai-response	/v1/responses
anthropic	/v1/messages
gemini	/v1beta/models/{model}:generateContent
image-generation	/v1/images/generations
embeddings	/v1/embeddings
jina-rerank	/v1/rerank
openai-video	/v1/videos

For most users, copying the model name from the Pricing page is enough; there is no need to handle these values manually.