Invoke an agent
model to agent/<key>. The agent’s configured model, tools, knowledge bases, and memory apply automatically, so the request only needs to provide the input.
This endpoint implements the OpenResponses specification, a multi-provider, interoperable LLM interface. Orq.ai extends the spec with platform features like variables, memory, identity, and Orq.ai tools.
For a comprehensive guide with examples, see the Run Agents documentation and the Responses API documentation.
Authorizations
Body
Context management entries. One compaction entry summarizes history older than compact_threshold into a single item. See the Context Compaction guide.
Additional fields to include in the response. Use web_search_call.action.sources to add source URLs and titles to a web search action, or web_search_call.results for detailed results. See the Web search guide for the supported values.
Request-scoped transforms applied to the text exchanged with the model. Supports pii_redaction, which replaces PII with placeholders before the provider sees it and restores the original values in the response; response_healing, which repairs malformed JSON in non-streaming model output; and trace_scrubbing, which removes selected sensitive fields from exported traces.
Configuration for text output.
Extended thinking configuration for Google Gemini and Anthropic models. Carries type, budget_tokens, and thinking_level. See the Reasoning guide.
Response
Returns a response object or a stream of events.
Array of output items (messages, function calls, reasoning, etc.)
A message from the model.
- Message
- Function call
- Function call output
- Reasoning
- Orq tool call
- Other item