Skip to main content
GET
/
v1
/
public
/
model-registry
/
models
Returns a comprehensive list of all AI models with their configurations, pricing, and capabilities
curl --request GET \
  --url https://api.helicone.ai/v1/public/model-registry/models
{
  "data": {
    "models": [
      {
        "id": "<string>",
        "name": "<string>",
        "author": "<string>",
        "contextLength": 123,
        "endpoints": [
          {
            "provider": "<string>",
            "providerSlug": "<string>",
            "pricing": {
              "prompt": 123,
              "completion": 123,
              "audio": 123,
              "thinking": 123,
              "web_search": 123,
              "image": 123,
              "video": 123,
              "cacheRead": 123,
              "cacheWrite": 123,
              "threshold": 123
            },
            "endpoint": {
              "pricing": [
                {
                  "threshold": 123,
                  "input": 123,
                  "output": 123,
                  "image": 123,
                  "cacheMultipliers": {
                    "cachedInput": 123,
                    "write1h": 123,
                    "write5m": 123
                  },
                  "cacheStoragePerHour": 123,
                  "thinking": 123,
                  "request": 123,
                  "audio": 123,
                  "video": 123,
                  "web_search": 123
                }
              ],
              "contextLength": 123,
              "maxCompletionTokens": 123,
              "ptbEnabled": true,
              "modelConfig": {
                "pricing": [
                  {
                    "threshold": 123,
                    "input": 123,
                    "output": 123,
                    "image": 123,
                    "cacheMultipliers": {
                      "cachedInput": 123,
                      "write1h": 123,
                      "write5m": 123
                    },
                    "cacheStoragePerHour": 123,
                    "thinking": 123,
                    "request": 123,
                    "audio": 123,
                    "video": 123,
                    "web_search": 123
                  }
                ],
                "contextLength": 123,
                "maxCompletionTokens": 123,
                "ptbEnabled": true,
                "providerModelId": "<string>",
                "provider": "baseten",
                "author": "anthropic",
                "supportedParameters": [
                  "max_tokens"
                ],
                "endpointConfigs": {},
                "version": "<string>",
                "unsupportedParameters": [
                  "max_tokens"
                ],
                "supportedPlugins": [
                  "web"
                ],
                "rateLimits": {
                  "rpm": 123,
                  "tpm": 123,
                  "tpd": 123
                },
                "crossRegion": true,
                "priority": 123,
                "quantization": "fp4",
                "responseFormat": "ANTHROPIC",
                "requireExplicitRouting": true,
                "providerModelIdAliases": [
                  "<string>"
                ]
              },
              "userConfig": {
                "region": "<string>",
                "location": "<string>",
                "projectId": "<string>",
                "baseUri": "<string>",
                "deploymentName": "<string>",
                "resourceName": "<string>",
                "apiVersion": "<string>",
                "crossRegion": true,
                "gatewayMapping": "OPENAI",
                "modelName": "<string>",
                "heliconeModelId": "<string>"
              },
              "provider": "baseten",
              "author": "anthropic",
              "providerModelId": "<string>",
              "supportedParameters": [
                "max_tokens"
              ],
              "version": "<string>",
              "unsupportedParameters": [
                "max_tokens"
              ],
              "priority": 123
            },
            "supportsPtb": true,
            "pricingTiers": [
              {
                "prompt": 123,
                "completion": 123,
                "audio": 123,
                "thinking": 123,
                "web_search": 123,
                "image": 123,
                "video": 123,
                "cacheRead": 123,
                "cacheWrite": 123,
                "threshold": 123
              }
            ]
          }
        ],
        "inputModalities": [
          "text"
        ],
        "outputModalities": [
          "text"
        ],
        "supportedParameters": [
          "max_tokens"
        ],
        "maxOutput": 123,
        "trainingDate": "<string>",
        "description": "<string>",
        "pinnedVersionOfModel": "<string>"
      }
    ],
    "total": 123,
    "filters": {
      "capabilities": [
        "audio"
      ],
      "authors": [
        "<string>"
      ],
      "providers": [
        {
          "displayName": "<string>",
          "name": "<string>"
        }
      ]
    }
  },
  "error": null
}
This endpoint returns the complete catalog of AI models and provider endpoints that the Helicone AI Gateway can route to. The gateway uses this registry to determine which providers support a requested model and how to intelligently route requests for maximum reliability and cost optimization. When you request a model through the AI Gateway (like gpt-4o-mini), the gateway consults this registry to find all providers offering that model, then applies routing logic to select the best provider based on your configuration, availability, and pricing.

Response

200 - application/json

Complete model registry with models and filter options

​
data
object
required
​
error
enum<number> | null
required
Available options: