Parse LLM Text Output
Parses the output text of computer use model and returns the parsed actions.
Path Parameters
typestring
The type of the prompt to parse the input for
Value in
"ui-tars" | "seed" | "glm-4.1v" | "glm-4.5v" | "qwen-2.5-vl"textContentstring
The text content to parse
Response Body
{
"actions": [
{
"callId": "string",
"type": "mouse:click",
"x": {
"type": "px",
"value": 0
},
"y": {
"type": "px",
"value": 0
},
"button": 0,
"holdKey": "string"
}
],
"unknown": "string",
"memory": "string",
"thoughts": "string"
}