Skip to main content

Models

List the LLM models available for use with the Vexrail API. The response follows the OpenAI models list format.

Endpoint​

GET /v1/models

Authentication​

Requires x-publishable-key and x-secret-key headers. See Authentication.

Example Request​

curl https://api.vexrail.com/v1/models \
  -H "x-publishable-key: pk_live_your_key" \
  -H "x-secret-key: sk_live_your_key"

Example Response​

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o-mini",
      "object": "model",
      "created": 1700000000,
      "owned_by": "openai"
    },
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 1700000000,
      "owned_by": "openai"
    },
    {
      "id": "claude-3-5-sonnet-20241022",
      "object": "model",
      "created": 1700000000,
      "owned_by": "anthropic"
    }
  ]
}

Model Selection​

When making a chat completion request, specify the model using its id value from this endpoint.

{
  "model": "gpt-4o-mini",
  "messages": [...]
}

Model Availability​

The list of available models may change over time as new models are added or deprecated. The models endpoint response is cached for 10 minutes, so newly added models may take up to 10 minutes to appear.

Choosing a Model​

Different models have different capabilities, performance characteristics, and costs:

  • Smaller models (e.g., gpt-4o-mini) are faster and cheaper per token. Good for simple queries, high-volume applications, or when cost is a priority.
  • Larger models (e.g., gpt-4o) provide higher quality responses for complex reasoning tasks but cost more per token.

Token costs are charged against your credit wallet.