curl --request GET \
  --url http://localhost:8080/v1/models

{
  "data": [
    {
      "id": "<string>",
      "canonical_slug": "<string>",
      "name": "<string>",
      "deployment": "<string>",
      "created": 123,
      "context_length": 123,
      "max_input_tokens": 123,
      "max_output_tokens": 123,
      "architecture": {
        "modality": "<string>",
        "tokenizer": "<string>",
        "instruct_type": "<string>",
        "input_modalities": [
          "<string>"
        ],
        "output_modalities": [
          "<string>"
        ]
      },
      "pricing": {
        "prompt": "<string>",
        "completion": "<string>",
        "request": "<string>",
        "image": "<string>",
        "web_search": "<string>",
        "internal_reasoning": "<string>",
        "input_cache_read": "<string>",
        "input_cache_write": "<string>"
      },
      "top_provider": {
        "is_moderated": true,
        "context_length": 123,
        "max_completion_tokens": 123
      },
      "per_request_limits": {
        "prompt_tokens": 123,
        "completion_tokens": 123
      },
      "supported_parameters": [
        "<string>"
      ],
      "default_parameters": {
        "temperature": 123,
        "top_p": 123,
        "frequency_penalty": 123
      },
      "hugging_face_id": "<string>",
      "description": "<string>",
      "owned_by": "<string>",
      "supported_methods": [
        "<string>"
      ]
    }
  ],
  "extra_fields": {
    "request_type": "<string>",
    "provider": "openai",
    "model_requested": "<string>",
    "model_deployment": "<string>",
    "latency": 123,
    "chunk_index": 123,
    "raw_request": {},
    "raw_response": {},
    "cache_debug": {
      "cache_hit": true,
      "cache_id": "<string>",
      "hit_type": "<string>",
      "provider_used": "<string>",
      "model_used": "<string>",
      "input_tokens": 123,
      "threshold": 123,
      "similarity": 123
    }
  },
  "next_page_token": "<string>"
}