Invoke Workflow (Sync)
Invoke a workflow and wait for completion. Returns the final result.
Path Parameters
Query Parameters
Request Body
id from a previous task’s response to continue the same conversation.default or harderResponse
completed, failed, error, or stoppedExample Request
Authorizations
API Key for authentication
Path Parameters
Query Parameters
The workflow version to invoke. default = latest
Body
Pass the id from a previous response to continue a multi-turn conversation with the same agent. Omit for a new conversation.
"02843b37-4d77-48a0-8da7-2c76afe54401"
Per-execution override of the agent's LLM provider (e.g. openai, anthropic). Must match one of GET /llm_providers. Omit to use the agent's configured provider.
Per-execution override of the model name within the chosen provider. Must match a model from GET /llm_providers/{provider}/models. Examples: claude-sonnet-4-6, gpt-5, gemini-2.0-flash. Omit to use the agent's configured model.
Per-execution override of reasoning effort for reasoning-capable models (e.g. GPT-5). low for simple tasks, medium for balanced performance, high for complex reasoning, xhigh for maximum reasoning depth (slower, more expensive). Omit to use the agent's configured reasoning effort.
low, medium, high, xhigh Response
Successful Response
Unique task identifier. Use this to poll for results when invoking async.
"02843b37-4d77-48a0-8da7-2c76afe54401"
"47c3b020-9a6b-4699-8d94-d92d71929b53"
"91fbe9bc-35b3-41e8-b59d-922fb5a0f031"
pending | executing | completed | error
pending, executing, completed, error, failed, stopped "completed"
The agent's response. Populated when status is 'completed'. Null for async until polling shows completed.
"Hello! 👋"
"2026-04-10T19:01:22.898813Z"
Null until the task completes.
"2026-04-10T19:01:33.120590Z"
"api"

