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>",
"endpoint": {
"pricing": [
{
"threshold": 123,
"input": 123,
"output": 123,
"image": 123,
"cacheMultipliers": {
"write1h": 123,
"write5m": 123,
"cachedInput": 123
},
"cacheStoragePerHour": 123,
"thinking": 123,
"request": 123,
"audio": 123,
"video": 123,
"web_search": 123
}
],
"contextLength": 123,
"maxCompletionTokens": 123,
"ptbEnabled": true,
"version": "<string>",
"baseUrl": "<string>",
"provider": "anthropic",
"author": "anthropic",
"providerModelId": "<string>",
"supportedParameters": [
"max_tokens"
]
},
"supportsPtb": true,
"pricing": {
"prompt": 123,
"completion": 123,
"audio": 123,
"thinking": 123,
"web_search": 123,
"image": 123,
"video": 123,
"cacheRead": 123,
"cacheWrite": 123,
"threshold": 123
},
"pricingTiers": [
{
"prompt": 123,
"completion": 123,
"audio": 123,
"thinking": 123,
"web_search": 123,
"image": 123,
"video": 123,
"cacheRead": 123,
"cacheWrite": 123,
"threshold": 123
}
]
}
],
"maxOutput": 123,
"trainingDate": "<string>",
"description": "<string>",
"inputModalities": [
"text"
],
"outputModalities": [
"text"
],
"supportedParameters": [
"max_tokens"
]
}
],
"total": 123,
"filters": {
"capabilities": [
"audio"
],
"authors": [
"<string>"
],
"providers": [
{
"displayName": "<string>",
"name": "<string>"
}
]
}
}
}
Returns all models and endpoints supported by the Helicone AI Gateway
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>",
"endpoint": {
"pricing": [
{
"threshold": 123,
"input": 123,
"output": 123,
"image": 123,
"cacheMultipliers": {
"write1h": 123,
"write5m": 123,
"cachedInput": 123
},
"cacheStoragePerHour": 123,
"thinking": 123,
"request": 123,
"audio": 123,
"video": 123,
"web_search": 123
}
],
"contextLength": 123,
"maxCompletionTokens": 123,
"ptbEnabled": true,
"version": "<string>",
"baseUrl": "<string>",
"provider": "anthropic",
"author": "anthropic",
"providerModelId": "<string>",
"supportedParameters": [
"max_tokens"
]
},
"supportsPtb": true,
"pricing": {
"prompt": 123,
"completion": 123,
"audio": 123,
"thinking": 123,
"web_search": 123,
"image": 123,
"video": 123,
"cacheRead": 123,
"cacheWrite": 123,
"threshold": 123
},
"pricingTiers": [
{
"prompt": 123,
"completion": 123,
"audio": 123,
"thinking": 123,
"web_search": 123,
"image": 123,
"video": 123,
"cacheRead": 123,
"cacheWrite": 123,
"threshold": 123
}
]
}
],
"maxOutput": 123,
"trainingDate": "<string>",
"description": "<string>",
"inputModalities": [
"text"
],
"outputModalities": [
"text"
],
"supportedParameters": [
"max_tokens"
]
}
],
"total": 123,
"filters": {
"capabilities": [
"audio"
],
"authors": [
"<string>"
],
"providers": [
{
"displayName": "<string>",
"name": "<string>"
}
]
}
}
}
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.Ok
The response is of type object
.
Was this page helpful?