Skip to main content
The /v1/models endpoint returns all models that your token has permission to use. OpenOpen8 inspects your request headers and returns the model list in the format that matches your client: OpenAI format by default, Anthropic format when Claude headers are present, or Gemini format when Google headers are present.

​
GET /v1/models

​
Authentication

Pass your token using the header that matches the format you want in the response:
Auth methodHeaders requiredResponse format
OpenAI (default)Authorization: Bearer YOUR_TOKENOpenAI model list
Anthropic (Claude)x-api-key: YOUR_TOKEN and anthropic-version: 2023-06-01Anthropic model list
Gemini (Google)x-goog-api-key: YOUR_TOKENGemini model list
You can also pass the Gemini API key as a ?key=YOUR_TOKEN query parameter instead of the x-goog-api-key header.

​
Response (OpenAI format)

When you authenticate with a Bearer token and no Claude or Gemini headers are present, the response follows the OpenAI models list format:
​
object
string
Always "list".
​
data
object[]
Array of model objects.

​
GET /v1/models/:model

Retrieve information about a specific model by its ID. 
GET /v1/models/gpt-4o
Returns a single model object in the same format as an entry in the data array above. When Claude headers are present, this endpoint returns the Anthropic model format instead.

​
Gemini format endpoint

To list models in Gemini format, you can use either of the following paths:
  • GET /v1/models with x-goog-api-key header
  • GET /v1beta/models with any valid token

​
Example

curl https://openopen8.ai/v1/models \
  -H "Authorization: Bearer YOUR_TOKEN"

​
Example response (OpenAI format)

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 1715367049,
      "owned_by": "openai"
    },
    {
      "id": "claude-3-5-sonnet-20241022",
      "object": "model",
      "created": 1715367049,
      "owned_by": "anthropic"
    },
    {
      "id": "gemini-2.0-flash",
      "object": "model",
      "created": 1715367049,
      "owned_by": "google"
    }
  ]
}
The models returned reflect what your specific token is authorized to use. If you expect a model to appear but it does not, ask your OpenOpen8 administrator to grant access via the token settings in the dashboard.