Gemini Native
List Models
List available models using Google Gemini API format
Returns the models that accept Gemini requests, in Google Gemini API format. The supportedGenerationMethods of each model lists the actions you can call on it.
Query Parameters
Maximum number of models to return. Default: 50, maximum: 1000.
Continuation token returned by a previous page. Pass it back unchanged to fetch the next slice.
Authentication
Authentication is not required for the public model catalog read endpoints.
Gemini-style auth hints such as ?key= or x-goog-api-key do not change the response contract here.
Response
Array of model objects. See Get Model for the fields.
Returned when more models are available. Pass this value as pageToken to continue pagination.
Errors
- Invalid
pageTokenreturns400 INVALID_ARGUMENT. - Unexpected list failures return
500 INTERNAL.
Request
curl "https://api.tokenlab.sh/v1beta/models?pageSize=2" \
-H "x-goog-api-key: sk-your-api-key"Response
{
"models": [
{
"name": "models/gemini-2.5-flash",
"baseModelId": "gemini-2.5-flash",
"version": "gemini-2.5-flash",
"displayName": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"streamGenerateContent",
"countTokens"
]
},
{
"name": "models/gemini-2.5-flash-lite",
"baseModelId": "gemini-2.5-flash-lite",
"version": "gemini-2.5-flash-lite",
"displayName": "Gemini 2.5 Flash-Lite",
"description": "Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": [
"generateContent",
"streamGenerateContent",
"countTokens"
]
}
],
"nextPageToken": "b2Zmc2V0OjI"
}Query Parameters
Maximum number of models to return. Default: 50.
1 <= value <= 100050Continuation token from a previous page. An invalid token returns 400.
Response
application/json
application/json
application/json