curl --request GET \
  --url https://api.venice.ai/api/v1/models \
  --header 'Authorization: Bearer <token>'

{
  "data": [
    {
      "created": 1727966436,
      "id": "llama-3.2-3b",
      "model_spec": {
        "availableContextTokens": 131072,
        "capabilities": {
          "optimizedForCode": false,
          "quantization": "fp16",
          "supportsAudioInput": false,
          "supportsFunctionCalling": true,
          "supportsLogProbs": true,
          "supportsMultipleImages": false,
          "supportsReasoning": false,
          "supportsReasoningEffort": false,
          "supportsResponseSchema": true,
          "supportsTeeAttestation": false,
          "supportsE2EE": false,
          "supportsVision": false,
          "supportsVideoInput": false,
          "supportsWebSearch": true,
          "supportsXSearch": false
        },
        "constraints": {
          "temperature": {
            "default": 0.8
          },
          "top_p": {
            "default": 0.9
          }
        },
        "description": "Compact and efficient model for quick responses and lighter workloads.",
        "name": "Llama 3.2 3B",
        "modelSource": "https://huggingface.co/meta-llama/Llama-3.2-3B",
        "offline": false,
        "privacy": "private",
        "pricing": {
          "input": {
            "usd": 0.15,
            "diem": 0.15
          },
          "output": {
            "usd": 0.6,
            "diem": 0.6
          }
        },
        "traits": [
          "fastest"
        ]
      },
      "object": "model",
      "owned_by": "venice.ai",
      "type": "text"
    }
  ],
  "object": "list",
  "type": "text"
}