invoke_model
Run inference against a served model by sending 1–20 text inputs, optionally to a named workspace, to get model predictions.
Instructions
Run inference against a served model.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"model": "<model>",
"inputs": "<inputs>"
},
"name": "invoke_model"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | ||
| inputs | Yes | 1-20 text inputs. | |
| workspace | No | Named workspace. Omit to use the default workspace. |