Runs

Allows you to start a new run, i.e. resolve templates and send the fully formatted prompt to an LLM of your choice.

Select the active template set version based on version and environment as described in Flows
Take the prompt entrypoint and start recursively replacing tokens given in parameters. Parameters always precede descending into a template of the same name
Send the prompt to the LLM chosen as default for the selected entrypoint in the respective version, unless overrideModel is specified. The model must be one of Models
Waits until the request is finished and returns both the formatted request and the LLM response, along with some metadata

Last updated 10 months ago

POST /api/v1/flows/{flowId}/runs HTTP/1.1 Host: Content-Type: application/json Accept: */* Content-Length: 146 { "parameters": { "ANY_ADDITIONAL_PROPERTY": "text" }, "environment": "text", "overrideModel": "text", "tags": [ "text" ], "entrypoint": "text", "version": "text" }

{ "creditsUsed": 1, "milliseconds": 1, "id": "text", "timestamp": "2025-04-26T08:38:05.368Z", "flowId": "text", "tenantId": "text", "userId": "text", "flowRequest": { "parameters": { "ANY_ADDITIONAL_PROPERTY": "text" }, "environment": "text", "overrideModel": "text", "tags": [ "text" ], "entrypoint": "text", "version": "text" }, "requests": [ { "id": "text", "idCreated": "2025-04-26T08:38:05.368Z", "shuttleRequestId": "text", "messages": [ { "role": "client", "text": "text" } ], "model": "text", "maxTokens": 1, "seed": 1, "temperature": 1, "topP": 1, "topK": 1 } ], "responses": [ { "model": "text", "provider": "text", "usage": { "tokensIn": 1, "tokensOut": 1, "tokensTotal": 1, "costUsd": 1, "costCredits": 1 }, "textResponse": "text", "verbatimResponse": "text" } ], "creditsLeft": 1 }