Providers endpoint

Get available AI providers and their chat and embedding models

The providers endpoint returns a list of all active providers with their available chat and embedding models. Use this endpoint before making search requests to get the valid provider IDs and model keys.

Endpoint

GET /api/providers

http://localhost:3000/api/providers

Replace localhost:3000 with your Perplexica instance URL if running on a different host or port.

Response

providers · array

A list of all active providers with their available models.

Show provider object

id · string

The UUID of the provider. Use this as the providerId when making search requests.

name · string

The display name of the provider (e.g., “OpenAI”, “Ollama”).

chatModels · array

Available chat models for this provider.

Show model object

name · string

The display name of the model (e.g., “GPT 4 Omni Mini”).

key · string

The model key/identifier (e.g., gpt-4o-mini). Use this value in the chatModel.key field when making search requests.

embeddingModels · array

Available embedding models for this provider.

Show model object

name · string

The display name of the model (e.g., “Text Embedding 3 Large”).

key · string

The model key/identifier (e.g., text-embedding-3-large). Use this value in the embeddingModel.key field when making search requests.

Request example

cURL

curl http://localhost:3000/api/providers

Response example

{
  "providers": [
    {
      "id": "550e8400-e29b-41d4-a716-446655440000",
      "name": "OpenAI",
      "chatModels": [
        {
          "name": "GPT 4 Omni Mini",
          "key": "gpt-4o-mini"
        },
        {
          "name": "GPT 4 Omni",
          "key": "gpt-4o"
        }
      ],
      "embeddingModels": [
        {
          "name": "Text Embedding 3 Large",
          "key": "text-embedding-3-large"
        }
      ]
    }
  ]
}

Use the id field as the providerId and the key field from the models arrays when making search requests.

Error responses

500 · Internal Server Error

Returned if an error occurs while fetching providers.