Models

API reference for the /v1/models endpoint to list available models.

The Models endpoint returns a list of all models available through InferXgate.

List Models

GET /v1/models

Response

{
  "object": "list",
  "data": [
    {
      "id": "claude-opus-4-5-20251101",
      "object": "model",
      "created": 1699000000,
      "owned_by": "anthropic",
      "permission": [],
      "root": "claude-opus-4-5-20251101",
      "parent": null
    },
    {
      "id": "claude-sonnet-4-5-20250929",
      "object": "model",
      "created": 1699000000,
      "owned_by": "anthropic"
    },
    {
      "id": "gpt-4-turbo",
      "object": "model",
      "created": 1699000000,
      "owned_by": "openai"
    },
    {
      "id": "gemini-3-pro-preview",
      "object": "model",
      "created": 1699000000,
      "owned_by": "google"
    }
  ]
}

Example

curl https://api.yourdomain.com/v1/models \
  -H "Authorization: Bearer $API_KEY"

Available Models by Provider

Anthropic

Model IDDescription
claude-opus-4-5-20251101Most capable, extended thinking
claude-sonnet-4-5-20250929Advanced performance and speed
claude-haiku-4-5-20250929Fast and efficient
claude-opus-4-1-20250414Previous flagship
claude-sonnet-4-20250514Balanced Claude 4
claude-opus-4-20250514Claude 4 base
claude-3-5-haiku-20241022Legacy fast model
claude-3-haiku-20240307Legacy efficient

OpenAI

Model IDDescription
gpt-4-turboLatest GPT-4 Turbo
gpt-4GPT-4 base model
gpt-3.5-turboFast and cost-effective

Google Gemini

Model IDDescription
gemini-3-pro-previewBest multimodal understanding
gemini-3-pro-image-previewImage-optimized
gemini-2.5-proAdvanced reasoning
gemini-2.5-flashFast and efficient
gemini-2.5-flash-liteLightweight
gemini-2.0-flashFast responses
gemini-2.0-flash-liteLightweight fast