pull a model: orca-mini

POST {{baseUrl}}/api/pull

Pull a model from the Ollama library. Cancelled pulls are resumed from where they left off, and multiple calls will share the same download progress.

Pulling a model refers to downloading the model from a remote source (such as Ollama’s model library) to your local machine.

Once a model is pulled, it is available for use locally without needing to download it again.

Parameters

You can add "stream": false to the body to get a chunked response instead of streamed

Request Body

{"name"=>"orca-mini", "stream"=>false}

RESPONSES

status: OK

{"status":"success"}