Load model to memory

Loads the selected model into RAM

Parameters

Function LoadModelToMemory(Val URL, Val Model, Val Period = 300, Val AdditionalHeaders = "") Export

Parameter	CLI option	Type	Required	Description
URL	--url	String	✔	Ollama server URL
Model	--model	String	✔	Models name
Period	--keep	Number	✖	Model hold time in seconds
AdditionalHeaders	--headers	Map Of KeyAndValue	✖	Additional request headers, if necessary

Returns

Map Of KeyAndValue - Processing result

Advanced call ?

Parameter	Description
proxy	InternetProxy or a structure with fields Protocol, Host, Port, User, Password, UseOSAuthentication
timeout	Request execution timeout
adv_response	Formats the response as a complete structure with fields code, body, and headers

tip

Method at API documentation: Load a model

1C:Enterprise/OneScript code example

    URL   = "https://hut.openintegrations.dev/ollama";
    Token = "12We34..."; // Authorization - not part API Ollama

    Model  = "tinyllama";
    Period = 500;

    AdditionalHeaders = New Map;
    AdditionalHeaders.Insert("Authorization", StrTemplate("Bearer %1", Token));

    Result = OPI_Ollama.LoadModelToMemory(URL, Model, Period, AdditionalHeaders);

Bash

    # JSON data can also be passed as a path to a .json file
    
    oint ollama LoadModelToMemory \
      --url "https://hut.openintegrations.dev/ollama" \
      --model "tinyllama" \
      --keep 500 \
      --headers "{'Authorization':'***'}"

CMD/Bat

    :: JSON data can also be passed as a path to a .json file
    
    oint ollama LoadModelToMemory ^
      --url "https://hut.openintegrations.dev/ollama" ^
      --model "tinyllama" ^
      --keep 500 ^
      --headers "{'Authorization':'***'}"

Result

{
 "model": "tinyllama",
 "created_at": "2026-05-02T12:30:25.9314608Z",
 "response": "",
 "done": true,
 "done_reason": "load"
}