/v1/private/ollama/modelsList available Ollama modelsFetches the list of models available from the Ollama instance. URL may be provided with or without /v1 suffix (e.g., http://localhost:11434 or http://localhost:11434/v1). The /v1 suffix will be automatically removed for model discovery. For actual LLM inference, use the URL with /v1 suffix for OpenAI-compatible endpoints.
Request body
requiredapplication/json
Request with Ollama instance base URL for connection testing or model discovery.
api_keystringOptional API key for authenticated Ollama instances. If provided, will be sent as Bearer token in Authorization header.
base_urlstringrequiredBase URL of the Ollama instance. May include /v1 suffix which will be automatically removed for connection testing. For inference, use the URL with /v1 suffix for OpenAI-compatible endpoints.
{
"api_key": "",
"base_url": "http://localhost:11434/v1"
}Responses
Show array items
Ollama model information
digeststringModel digest/hash
modified_atstring · date-timeModel modification date
namestringrequiredModel name
sizeinteger · int64Model size in bytes
[
{
"digest": "string",
"modified_at": "2026-06-09T00:00:00Z",
"name": "llama2",
"size": 0
}
]codeinteger · int32detailsstringmessagestring{
"code": 0,
"details": "string",
"message": "string"
}codeinteger · int32detailsstringmessagestring{
"code": 0,
"details": "string",
"message": "string"
}