> ## Documentation Index > Fetch the complete documentation index at: https://docs.orq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Invoke an agent > Creates a model response for the given input. Returns a response object or a stream of server-sent events. **Related guide**: Build agents guide. See the [Build agents guide](/ai-studio/ai-engineering/build-agents) for a walkthrough with examples. Invoke an **Agent** with the [Responses API](/reference/responses/create-response) by setting `model` to `agent/`. 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](https://www.openresponses.org/) 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](/ai-studio/ai-engineering/run-agents) and the [Responses API documentation](/ai-gateway/features/responses-api). ```bash Simple text theme={"theme":{"light":"github-light","dark":"github-dark"}} curl -X POST https://my.orq.ai/v3/router/responses \ -H "Authorization: Bearer $ORQ_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "agent/my-agent", "input": "Help me plan a microservices architecture for our e-commerce platform." }' ``` ```bash Image input theme={"theme":{"light":"github-light","dark":"github-dark"}} curl -X POST https://my.orq.ai/v3/router/responses \ -H "Authorization: Bearer $ORQ_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "agent/image-classifier", "input": [ { "type": "message", "role": "user", "content": [ { "type": "input_text", "text": "What can you see in this image?" }, { "type": "input_image", "image_url": "https://example.com/image.jpg", "detail": "auto" } ] } ] }' ``` ```bash Variables theme={"theme":{"light":"github-light","dark":"github-dark"}} curl -X POST https://my.orq.ai/v3/router/responses \ -H "Authorization: Bearer $ORQ_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "agent/my-agent", "input": "I need help with my account.", "variables": { "user_name": "John Smith", "user_role": "admin", "api_token": { "secret": true, "value": "sk-secret-123" } } }' ``` ```bash Memory theme={"theme":{"light":"github-light","dark":"github-dark"}} curl -X POST https://my.orq.ai/v3/router/responses \ -H "Authorization: Bearer $ORQ_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "agent/agent-memories", "input": "Do you remember what my name is?", "memory": { "entity_id": "customer_456" } }' ``` ```bash Streaming theme={"theme":{"light":"github-light","dark":"github-dark"}} curl -X POST https://my.orq.ai/v3/router/responses \ -H "Authorization: Bearer $ORQ_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "agent/my-agent", "input": "Help me plan a microservices architecture for our e-commerce platform.", "stream": true }' ``` ```bash Multi-turn theme={"theme":{"light":"github-light","dark":"github-dark"}} curl -X POST https://my.orq.ai/v3/router/responses \ -H "Authorization: Bearer $ORQ_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "agent/my-agent", "previous_response_id": "resp_01KP6DFC5FB7K7K10TVP60PF81", "input": "Can you expand on the challenges section?" }' ``` ```json Simple text theme={"theme":{"light":"github-light","dark":"github-dark"}} { "id": "resp_01KP6DFC5FB7K7K10TVP60PF81", "object": "response", "created_at": 1776184439, "completed_at": 1776184439, "status": "completed", "model": "agent/my-agent", "output": [ { "type": "message", "id": "msg_01KP6DFCG3RF80BEBXP06XX258", "role": "assistant", "status": "completed", "content": [ { "type": "output_text", "text": "Here's a microservices architecture for your e-commerce platform: start with a catalog service, a cart service, an order service, and a payment service, each owning its own database.", "annotations": [] } ] } ], "usage": { "input_tokens": 120, "output_tokens": 340, "total_tokens": 460, "input_tokens_details": { "cached_tokens": 0, "cache_creation_tokens": 0 }, "output_tokens_details": { "reasoning_tokens": 0 }, "input_cost": 0.0003, "output_cost": 0.00204, "total_cost": 0.00234 } } ``` ```json Image input theme={"theme":{"light":"github-light","dark":"github-dark"}} { "id": "resp_01KP6EJD020945A3WCBMD581RH", "object": "response", "created_at": 1776185587, "completed_at": 1776185591, "status": "completed", "model": "agent/image-classifier", "input": [ { "type": "message", "role": "user", "content": [ { "type": "input_text", "text": "What can you see in this image?" }, { "type": "input_image", "image_url": "https://example.com/image.jpg", "detail": "auto" } ] } ], "output": [ { "type": "message", "id": "msg_01KP6EJJ7FKC0SDWVBEC626TCM", "role": "assistant", "status": "completed", "content": [ { "type": "output_text", "text": "The image shows a city skyline at dusk, with several high-rise buildings and a river in the foreground.", "annotations": [] } ] } ], "usage": { "input_tokens": 8514, "output_tokens": 24, "total_tokens": 8538 } } ``` ```json Variables theme={"theme":{"light":"github-light","dark":"github-dark"}} { "id": "resp_01KP6GDRS1FY0VW4V77GTK9P7G", "object": "response", "created_at": 1776185700, "completed_at": 1776185701, "status": "completed", "model": "agent/my-agent", "output": [ { "type": "message", "id": "msg_01KP6GDS6TK09C7RM7GKAFPQ1Z", "role": "assistant", "status": "completed", "content": [ { "type": "output_text", "text": "Hi John, I can see you have an admin account. What would you like help with?", "annotations": [] } ] } ], "variables": { "user_name": "John Smith", "user_role": "admin" }, "usage": { "input_tokens": 95, "output_tokens": 24, "total_tokens": 119 } } ``` ```json Memory theme={"theme":{"light":"github-light","dark":"github-dark"}} { "id": "resp_01KP6H2N8QF4Z0RB7M9KCV3PXA", "object": "response", "created_at": 1776186000, "completed_at": 1776186001, "status": "completed", "model": "agent/agent-memories", "output": [ { "type": "message", "id": "msg_01KP6H2NJ7KC0SDWVBEC992RTM", "role": "assistant", "status": "completed", "content": [ { "type": "output_text", "text": "Yes, your name is John. How can I help you today?", "annotations": [] } ] } ], "usage": { "input_tokens": 142, "output_tokens": 18, "total_tokens": 160 } } ``` ```text Streaming (SSE) theme={"theme":{"light":"github-light","dark":"github-dark"}} event: response.created data: {"type":"response.created","sequence_number":1, "response":{"id":"resp_01KP6E957P5VF...","status":"in_progress",...}} event: response.in_progress data: {"type":"response.in_progress","sequence_number":2,...} event: response.output_item.added data: {"type":"response.output_item.added","sequence_number":3, "output_index":0, "item":{"id":"msg_01kp6e95fs...","type":"message","role":"assistant","content":[]}} event: response.content_part.added data: {"type":"response.content_part.added","sequence_number":4, "item_id":"msg_01kp6e95fs...","output_index":0,"content_index":0, "part":{"type":"output_text","text":""}} event: response.output_text.delta data: {"type":"response.output_text.delta","sequence_number":5, "item_id":"msg_01kp6e95fs...","output_index":0,"content_index":0, "delta":"Here's a microservices architecture"} event: response.output_text.delta data: {"type":"response.output_text.delta","sequence_number":6, "item_id":"msg_01kp6e95fs...","output_index":0,"content_index":0, "delta":" for your e-commerce platform."} event: response.output_text.done data: {"type":"response.output_text.done","sequence_number":7, "item_id":"msg_01kp6e95fs...","output_index":0,"content_index":0, "text":"Here's a microservices architecture for your e-commerce platform."} event: response.output_item.done data: {"type":"response.output_item.done","sequence_number":8, "output_index":0, "item":{"type":"message","role":"assistant","status":"completed", "content":[{"type":"output_text","text":"Here's a microservices architecture for your e-commerce platform.","annotations":[]}]}} event: response.completed data: {"type":"response.completed","sequence_number":9, "response":{"id":"resp_01KP6E957P5VF...","status":"completed", "usage":{"input_tokens":120,"output_tokens":340,"total_tokens":460}}} event: done data: [DONE] ``` ```json Multi-turn theme={"theme":{"light":"github-light","dark":"github-dark"}} { "id": "resp_01KP6ENF391202692JCGD6YBM5", "object": "response", "created_at": 1776185687, "completed_at": 1776185687, "status": "completed", "model": "agent/my-agent", "previous_response_id": "resp_01KP6DFC5FB7K7K10TVP60PF81", "input": [ { "type": "message", "id": "msg_01KP6DFXWPKZ12AS254YKHRA8R", "role": "user", "content": [{ "type": "input_text", "text": "Can you expand on the challenges section?" }] } ], "output": [ { "type": "message", "id": "msg_01KP6ENFR9G5G69TTE5AD9W65W", "role": "assistant", "status": "completed", "content": [ { "type": "output_text", "text": "The main challenges are distributed transactions across services, eventual consistency between the order and payment services, and the operational overhead of running and monitoring each service independently.", "annotations": [] } ] } ], "usage": { "input_tokens": 460, "output_tokens": 88, "total_tokens": 548 } } ``` ## OpenAPI ````yaml post /v3/router/responses openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://my.orq.ai security: - ApiKey: [] tags: - name: Chunking description: Split text into smaller chunks for retrieval and generation workflows. - name: File Systems description: >- Create and manage persistent file systems that agents and MCP clients read from and write to. - name: Knowledge Bases description: Create and manage knowledge bases used by agents and retrieval workflows. - name: Memory Stores description: Create and manage memory stores, memories, and memory documents. - name: Evals description: Run an evaluator against a conversation and its result - name: Logs description: >- OpenTelemetry log query API. Search, filter, aggregate, and facet log records ingested via OTLP. - name: Reporting description: >- GenAI reporting API over canonical analytics rollups. Accepts a metric name, time range, grain, group-by, and filters; returns a typed time series and optional totals. - name: Traces description: >- Query and inspect ingested trace data: search trace summaries, aggregate metrics, and read individual traces and their spans. - description: List models available through the AI Router. name: Models - name: Policies - name: Alerts description: >- Alerts evaluate a Reporting API metric on a fixed interval and fire notifications through notifiers when the value breaches a threshold. Each breach opens a trigger that tracks the incident until the value recovers. - name: Annotation Queues description: Annotation queues collect spans for human review. - name: API keys description: >- API keys authenticate programmatic access to the workspace. They expose opaque tokens, per-domain access grants, and budget and rate-limit constraints. - name: Audit Logs description: Audit logs record workspace entity changes and access-relevant events. - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, API key, provider, and model. Every applicable budget is enforced, and the most restrictive limit applies per dimension. - name: Files description: File upload and retrieval operations. - name: Guardrail Rules description: >- Guardrail Rules conditionally enforce evaluators and plugins for AI Gateway traffic. Rules may be scoped to a project or the whole workspace. - name: Hub description: Hub items are reusable templates available to a workspace. - name: Identities description: >- Identities represent end users from your system for usage and engagement tracking. - name: Management keys description: >- Management keys are workspace-scoped credentials that authenticate programmatic access to workspace administration surfaces (API keys, budgets). Unlike project-scoped API keys, a management key always operates at the workspace level. - name: MCP Gateway description: >- Register upstream MCP servers, discover and sync their tools, and assemble gateways that expose a curated tool surface to MCP clients. - name: Model Catalog description: >- Browse the orq.ai model catalog: every model orq offers, across every provider, with pricing, capabilities and benchmark data. List endpoints only return models that are not deprecated. This API is public, requires no authentication, and is rate limited to 120 requests per minute per IP. Responses carry a 5-minute cache-control max-age. - name: Notifiers description: Notifier destinations used to send delivery and workflow notifications. - name: Projects description: Projects organize resources within a workspace - name: Routing Rules description: >- Routing Rules conditionally select models and enforce request plugins for AI Gateway traffic. Rules are evaluated by ascending priority and may be scoped to a project or the whole workspace. - name: Threads description: Threads group related trace invocations and their aggregate usage - name: Skills description: >- Skills are modular instructions you can use to codify processes and conventions - name: Smart Routers description: >- Create and manage workspace Smart Routers. A Smart Router selects a model from an eligible pool for each request according to a quality, balanced, or cost profile. - name: Webhooks description: >- Create and manage webhooks that deliver workspace events to external HTTPS endpoints. - name: Workspaces description: >- A workspace is the tenant. Create is called from a user session during onboarding; Get, List, and Update are the public management surface. - name: Workspace Security description: >- Workspace-level domain verification and IP allowlist controls. These operations are restricted to workspace administrators. - name: Workspace Settings description: >- Workspace-level settings managed with a workspace credential. A workspace is the tenant, so these settings are a singleton — there is nothing to create or delete, only read and update. - name: Responses - description: Run agents on a cron cadence. Minimum firing interval is 1 hour. name: Agent Schedules - name: Embeddings - name: Telemetry description: >- Unified query envelope for traces, metrics, and logs. One request shape, one filter dialect, and one response shape per source, validated by a per-source registry. - description: Beta. Run typed classification questions against a classify model. name: Classify - description: Search Gateway with managed credits or BYOK. name: Web Search externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v3/router/responses: post: tags: - Responses summary: Create response description: >- Creates a model response for the given input. Returns a response object or a stream of server-sent events. operationId: create-router-response requestBody: content: application/json: schema: additionalProperties: false properties: background: description: If true, the response runs asynchronously in the background. type: boolean cache: $ref: '#/components/schemas/CacheConfig' description: Exact-match response cache configuration for this request. cache_control: description: >- Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. properties: ttl: default: 5m description: >- The time-to-live for the cache control breakpoint. This may be one of the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. Only supported by Anthropic Claude models. enum: - 5m - 1h type: string type: description: >- Create a cache control breakpoint. Accepts only the value "ephemeral". enum: - ephemeral type: string required: - type title: Cache control type: object conversation: $ref: '#/components/schemas/ConversationParam' description: Conversation context for multi-turn interactions. fallbacks: description: >- Fallback models to try if the primary model fails. Each entry specifies a model in provider/model format. items: $ref: '#/components/schemas/FallbackConfig' type: - array - 'null' frequency_penalty: description: >- Penalize new tokens based on their frequency in the text so far. Between -2.0 and 2.0. format: double type: number guardrails: description: Guardrails to evaluate the request against. items: $ref: '#/components/schemas/EvaluatorRef' type: array identity: $ref: '#/components/schemas/ResponseIdentity' description: Identity/contact information for the end-user. input: anyOf: - description: A simple text string as input. title: Text type: string - description: An array of input items. items: description: >- An input item. The "type" field determines the item kind: "message", "function_call", "function_call_output", "item_reference", etc. properties: arguments: description: >- The function arguments as a JSON string (for function_call items). type: string async: description: >- Whether a function or custom tool call runs asynchronously. type: boolean call_id: description: >- The function call identifier (for function_call and function_call_output items). type: string content: anyOf: - title: Text type: string - items: anyOf: - description: A text content part. properties: cache_control: properties: ttl: default: 5m description: >- The time-to-live for the cache control breakpoint. This may be one of the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. Only supported by Anthropic Claude models. enum: - 5m - 1h type: string type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". required: - type title: Cache control type: object text: type: string description: The text content. type: enum: - input_text type: string required: - type - text title: Text type: object - description: An image content part. properties: cache_control: properties: ttl: default: 5m description: >- The time-to-live for the cache control breakpoint. This may be one of the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. Only supported by Anthropic Claude models. enum: - 5m - 1h type: string type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". required: - type title: Cache control type: object detail: description: >- The detail level for image understanding. enum: - auto - low - high type: string file_id: description: The ID of a previously uploaded file. type: string image_url: description: The URL of the image. type: string type: enum: - input_image type: string required: - type title: Image type: object - description: >- A file content part. Provide file_id, file_data (base64), or file_url. properties: cache_control: properties: ttl: default: 5m description: >- The time-to-live for the cache control breakpoint. This may be one of the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. Only supported by Anthropic Claude models. enum: - 5m - 1h type: string type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". required: - type title: Cache control type: object file_data: description: Base64-encoded file content. type: string file_id: description: The ID of a previously uploaded file. type: string file_url: description: A URL to fetch the file from. type: string filename: description: The name of the file. type: string mime_type: description: >- The MIME type of the file (e.g., application/pdf). type: string type: enum: - input_file type: string required: - type title: File type: object description: A content part within a message. title: Content parts type: array description: >- The content of the item: a string or an array of content parts. id: description: >- The ID of the item. For item_reference items, this identifies the referenced item. type: string name: description: >- The name of the function that was called (for function_call items). type: string output: description: >- The output of the function call (for function_call_output type). type: string reasoning: description: >- Reasoning settings applied by a configuration_update item. properties: effort: enum: - none - minimal - low - medium - high - xhigh - max type: string type: object role: description: >- The role of the message sender (for message items). enum: - user - assistant - system - developer type: string status: description: The status of a model-generated input item. enum: - in_progress - completed - incomplete type: string type: description: The type of item. enum: - message - function_call - function_call_output - item_reference - reasoning - custom_tool_call - custom_tool_call_output - computer_call - computer_call_output - local_shell_call - local_shell_call_output - shell_call - shell_call_output - apply_patch_call - apply_patch_call_output - tool_search_call - tool_search_output - additional_tools - compaction - program - program_output - mcp_call - mcp_list_tools - mcp_approval_request - mcp_approval_response - configuration_update type: string type: object title: Items type: array description: >- Input to the model: a string or an array of input items (messages, files, etc.). instructions: description: System prompt / instructions for the model. type: string integration_id: description: >- Integration ID used to resolve provider credentials for this request. type: string limits: $ref: '#/components/schemas/ResponseExecutionLimits' description: >- Bound agent-loop execution. Fields: max_iterations (LLM turns), max_execution_time (seconds), max_cost (USD; send 0 to disable a manifest-configured cap), max_depth (sub-agent nesting), tool_timeout (seconds). Body values override agent-manifest defaults. load_balancer: $ref: '#/components/schemas/LoadBalancerConfig' description: >- Load balancing configuration for selecting among multiple models. max_output_tokens: description: Maximum number of tokens in the response output. format: int64 type: integer max_tool_calls: description: Maximum number of tool call rounds in the agentic loop. format: int64 type: integer memory: $ref: '#/components/schemas/MemoryParam' description: >- Attach a memory store entity to enable persistent memory across requests. See Memory Stores documentation for setup. metadata: additionalProperties: type: string description: >- Developer-defined key-value pairs attached to the response (OpenAI spec: Map). Non-string values are rejected with a 400. type: object model: description: >- The model to use in provider/model format (e.g. openai/gpt-4o). Use agent/ to invoke a pre-configured agent from the orq.ai platform. type: string parallel_tool_calls: description: Whether to allow parallel tool calls. type: boolean plugins: description: >- 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. items: $ref: '#/components/schemas/PublicPlugin' type: - array - 'null' presence_penalty: description: >- Penalize new tokens based on their presence in the text so far. Between -2.0 and 2.0. format: double type: number previous_response_id: description: >- The ID of a previous response to continue from. Requires store to be true (default) on the original response. type: string prompt_cache_key: description: Key for prompt caching across requests. type: string prompt_cache_options: $ref: '#/components/schemas/OpenAIPromptCacheOptions' description: >- OpenAI prompt cache options. GPT-5.6 and later support ttl=30m. reasoning: $ref: '#/components/schemas/ReasoningParam' description: >- Configure reasoning behavior. Set effort (none, minimal, low, medium, high, xhigh, max) to control how much the model thinks before answering. Higher effort means more reasoning tokens and better answers for complex tasks, at higher cost. retry: $ref: '#/components/schemas/ResponseRetryConfig' description: >- Retry configuration. Specify the number of retries and which HTTP status codes should trigger a retry. safety_identifier: description: Safety identifier for content filtering. type: string security: $ref: '#/components/schemas/SecurityConfig' description: Trace masking configuration for request and response data. service_tier: description: >- Processing mode for the request. Fast uses premium low-latency processing; priority remains a backward-compatible alias. enum: - auto - default - flex - fast - scale - priority type: string stop_sequences: description: >- Custom text sequences that cause the model to stop generating. Forwarded to providers that support it (e.g. Anthropic); ignored otherwise. items: type: string type: array store: description: >- Whether to persist the response (default: true). When false, the response cannot be retrieved later and previous_response_id will not work for follow-up requests. type: boolean stream: description: If true, returns a stream of server-sent events. type: boolean stream_options: $ref: '#/components/schemas/StreamOptions' temperature: description: Sampling temperature between 0 and 2. format: double type: number template_engine: description: >- Template engine for variable substitution in instructions. Defaults to the agent manifest's engine when invoking an agent, otherwise text. enum: - text - jinja - mustache type: string text: description: Configuration for text output. properties: format: anyOf: - properties: type: type: string enum: - text required: - type title: Plain text type: object - properties: description: description: >- A description of what the response format is for, used by the model to determine how to respond in the format. type: string name: description: >- The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. maxLength: 64 pattern: ^[a-zA-Z0-9_-]+$ type: string schema: additionalProperties: true description: >- The schema for the response format, described as a JSON Schema object. type: object strict: description: >- Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. type: boolean type: description: >- The type of response format being defined. Always `json_schema`. enum: - json_schema type: string required: - type - name - schema title: JSON Schema type: object description: 'The output format: plain text or structured JSON schema.' verbosity: description: Controls the verbosity of the model output. enum: - low - medium - high type: string type: object thread: $ref: '#/components/schemas/ResponseThread' description: Thread for grouping related requests. timeout: $ref: '#/components/schemas/TimeoutConfig' description: Provider call timeout configuration in milliseconds. tool_choice: anyOf: - description: >- Shorthand: "auto" lets the model decide, "none" disables tools, "required" forces tool use. enum: - auto - none - required title: Shorthand type: string - description: Select a specific function tool by name. properties: name: type: string description: The name of the function to call. type: type: string enum: - function required: - type - name title: Specific function type: object description: >- How the model should use the provided tools. Can be a string shorthand or a specific function selector. tools: description: Tools available to the model. items: anyOf: - description: A function tool the model can call. properties: async: description: >- Whether the tool response can be returned asynchronously. type: boolean cache_control: properties: ttl: default: 5m description: >- The time-to-live for the cache control breakpoint. This may be one of the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. Only supported by Anthropic Claude models. enum: - 5m - 1h type: string type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". required: - type title: Cache control type: object description: description: A description of what the function does. type: string name: description: The name of the function. type: string parameters: additionalProperties: true description: >- The parameters the function accepts, as a JSON Schema object. type: object strict: description: Whether to enforce strict parameter validation. type: boolean type: type: string enum: - function required: - type - name title: Function type: object - description: A custom tool that accepts free-form input. properties: async: description: >- Whether the tool response can be returned asynchronously. type: boolean description: description: A description of what the custom tool does. type: string name: description: The name of the custom tool. type: string type: enum: - custom type: string required: - type - name title: Custom type: object - $ref: '#/components/schemas/OrqAdvisorTool' - $ref: '#/components/schemas/OrqSidekickTool' - description: >- An orq.ai platform tool reference. For MCP tools, prefer type 'mcp' with 'key' instead of 'orq:mcp' with 'tool_id'. properties: files: description: >- Files to stage in /workspace for orq:code_interpreter. Maximum 10 files. items: properties: file_id: description: The workspace file ID. type: string name: description: The file name exposed under /workspace. type: string required: - file_id - name type: object maxItems: 10 type: array network: description: >- Network access intent for orq:code_interpreter. Stored and validated today; runtime enforcement by the sandbox egress layer is rolling out and until then sandbox executions retain default public internet egress. properties: allowlist: default: [] description: >- Allowed network hostnames or IPv4 addresses when mode is allowlist. Maximum 50 entries. items: type: string maxItems: 50 type: array mode: default: disabled description: Network mode. Defaults to disabled. enum: - disabled - allowlist type: string type: object timezone: description: >- Default IANA timezone for orq:datetime (e.g., "Europe/Amsterdam"). type: string tool_id: description: The tool ID (for orq:mcp, orq:http, orq:function). type: string type: description: >- The orq.ai tool type. orq:web_search, orq:web_fetch, and orq:datetime are the canonical names for orq:google_search, orq:web_scraper, and orq:current_date. enum: - orq:web_search - orq:web_fetch - orq:datetime - orq:search_models - orq:image_generation - orq:apply_patch - orq:fusion - orq:shell - orq:query_knowledge_base - orq:retrieve_knowledge_bases - orq:current_date - orq:google_search - orq:web_scraper - orq:code_interpreter - orq:mcp - orq:http - orq:function type: string required: - type title: orq.ai Tool type: object - description: >- An MCP (Model Context Protocol) server tool. Provide server_url for inline mode, or key to reference a pre-configured MCP server. properties: allowed_tools: description: >- Filter which tools from the MCP server are exposed. properties: read_only: description: >- Only expose tools with readOnlyHint annotation. type: boolean tool_names: description: List of allowed tool names. items: type: string type: array type: object headers: additionalProperties: type: string description: >- Custom headers to send with MCP requests. Values support {{variable}} templates. type: object key: description: >- Unique identifier. Required for pre-configured MCP servers (lookup key). For inline servers, used as a trace/display label. type: string server_description: description: Human-readable description of the server. type: string server_url: description: The MCP server endpoint URL (inline mode). type: string type: enum: - mcp type: string required: - type title: MCP Tool type: object description: >- A tool definition. The "type" field determines the tool kind. type: array top_k: description: >- Only sample from the top K options for each subsequent token. Forwarded to providers that support it (e.g. Anthropic); ignored otherwise. format: int64 type: integer top_logprobs: description: Number of most likely tokens to return at each position. format: int64 type: integer top_p: description: Nucleus sampling parameter. format: double type: number variables: additionalProperties: {} description: >- Template variables for prompt substitution. Plain values fill {{variable}} placeholders in instructions. For secrets, use {"secret": true, "value": "sensitive-data"} — secrets are automatically passed to platform tools (Python, HTTP, MCP) and redacted from traces. type: object type: object required: true responses: '200': content: application/json: schema: additionalProperties: false properties: background: type: boolean completed_at: format: int64 type: - integer - 'null' conversation: $ref: '#/components/schemas/ConversationParam' created_at: format: int64 type: integer error: anyOf: - $ref: '#/components/schemas/ResponseError' - type: 'null' frequency_penalty: type: number format: double id: type: string incomplete_details: anyOf: - $ref: '#/components/schemas/IncompleteDetails' - type: 'null' input: description: >- Array of input items (messages, function call outputs, etc.) items: {} type: - array - 'null' instructions: type: - string - 'null' max_output_tokens: format: int64 type: - integer - 'null' max_tool_calls: format: int64 type: - integer - 'null' memory: $ref: '#/components/schemas/MemoryParam' metadata: additionalProperties: type: string description: >- Developer-defined key-value pairs attached to the response (OpenAI spec: Map). type: object model: type: string object: description: Always "response" type: string output: description: >- Array of output items (messages, function calls, reasoning, etc.) items: {} type: - array - 'null' parallel_tool_calls: type: boolean presence_penalty: type: number format: double previous_response_id: type: - string - 'null' prompt_cache_key: type: - string - 'null' prompt_cache_options: anyOf: - $ref: '#/components/schemas/OpenAIPromptCacheOptions' - type: 'null' prompt_cache_retention: type: - string - 'null' reasoning: anyOf: - $ref: '#/components/schemas/Reasoning' - type: 'null' safety_identifier: type: - string - 'null' service_tier: enum: - auto - default - flex - fast - scale - priority type: string status: enum: - queued - in_progress - completed - failed - incomplete type: string store: type: boolean telemetry: $ref: '#/components/schemas/ResponseTelemetry' description: >- OpenTelemetry trace and span identifiers for this response. temperature: type: number format: double text: description: Text output configuration including format and verbosity tool_choice: description: >- Tool choice setting: "auto", "none", "required", or a specific function tools: description: Array of tool configurations used in this response items: {} type: - array - 'null' top_k: description: >- Only sample from the top K options for each subsequent token. Present only when set on the request. format: int64 type: integer top_logprobs: format: int64 type: integer top_p: type: number format: double truncation: enum: - disabled - auto type: string usage: anyOf: - $ref: '#/components/schemas/PublicUsage' - type: 'null' user: type: - string - 'null' variables: type: object additionalProperties: {} required: - id - object - created_at - completed_at - status - incomplete_details - model - previous_response_id - instructions - input - output - error - tools - tool_choice - temperature - top_p - presence_penalty - frequency_penalty - top_logprobs - max_output_tokens - max_tool_calls - reasoning - text - user - usage - truncation - parallel_tool_calls - store - background - metadata - service_tier - safety_identifier - prompt_cache_key - prompt_cache_retention - prompt_cache_options type: object text/event-stream: schema: $ref: '#/components/schemas/ResponseStreamEvent' description: Returns a response object or a stream of events. components: schemas: CacheConfig: additionalProperties: false properties: ttl: format: int64 type: integer type: type: string required: - type type: object ConversationParam: additionalProperties: false properties: id: type: string required: - id type: object FallbackConfig: additionalProperties: false properties: model: type: string required: - model type: object EvaluatorRef: additionalProperties: false properties: execute_on: enum: - input - output - both type: string id: type: string minLength: 1 is_guardrail: type: boolean options: type: object additionalProperties: {} sample_rate: format: double maximum: 1 minimum: 0 type: number timeout: format: int64 maximum: 600000 minimum: 1000 type: integer required: - id - execute_on type: object ResponseIdentity: additionalProperties: false properties: display_name: type: string email: type: string id: type: string metadata: items: type: object additionalProperties: {} type: - array - 'null' tags: items: type: string type: - array - 'null' required: - id type: object ResponseExecutionLimits: additionalProperties: false properties: max_cost: type: number format: double max_depth: format: int64 type: integer max_execution_time: format: int64 type: integer max_iterations: format: int64 type: integer tool_timeout: format: int64 type: integer type: object LoadBalancerConfig: additionalProperties: false properties: models: items: $ref: '#/components/schemas/LoadBalancerModelConfig' type: - array - 'null' type: type: string required: - type - models type: object MemoryParam: additionalProperties: false properties: entity_id: type: string required: - entity_id type: object PublicPlugin: additionalProperties: false properties: entities: description: >- pii_redaction only. Entity types to redact (e.g. EMAIL_ADDRESS, BSN). On its own this is a strict allowlist; alongside regions it adds to the region coverage. Omit to redact every type detected for the language and regions. See GET /v2/pii/capabilities for valid types. items: type: string type: - array - 'null' entity_thresholds: additionalProperties: type: number format: double description: >- pii_redaction only. Per-entity confidence cutoff overrides in [0,1], keyed by entity type. An override replaces threshold for that type and may sit above or below it. Every key must also appear in entities. type: object id: description: >- Plugin discriminator. pii_redaction redacts PII, response_healing repairs malformed JSON, and trace_scrubbing removes selected sensitive fields from exported traces. enum: - pii_redaction - response_healing - trace_scrubbing type: string language: description: >- pii_redaction only. Detector language, or "auto" to detect it per request. Defaults to auto. The accepted values are whatever GET /v2/pii/capabilities lists, so they are not enumerated here: a fixed enum would reject a language the detector has since added. type: string mask: description: >- trace_scrubbing only. Trace surfaces to scrub. At least one value required. items: type: string enum: - all - system - input - output - metadata - variables minItems: 1 type: - array - 'null' on_failure: description: >- pii_redaction only. Behavior when redaction is unavailable. block (default) fails the request; passthrough sends the original text. enum: - block - passthrough type: string regions: description: >- pii_redaction only. Region codes selecting whole regions of coverage (e.g. nl, gb). Every entity type those regions cover is redacted, alongside the base catalog. ["all"] cannot be combined with other region codes, and leaving both this and entities empty also runs every region, so selecting nothing is the widest request rather than the narrowest. Combines with entities: the two selections are unioned. items: type: string type: - array - 'null' threshold: description: pii_redaction only. Detector confidence cutoff in [0,1]. format: double maximum: 1 minimum: 0 type: number required: - id type: object OpenAIPromptCacheOptions: additionalProperties: false properties: mode: enum: - implicit - explicit type: string ttl: enum: - 30m type: string type: object ReasoningParam: additionalProperties: false properties: effort: description: >- Constrains effort on reasoning for reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. enum: - none - minimal - low - medium - high - xhigh - max type: string summary: description: The format of the reasoning summary returned by the model. enum: - concise - detailed - auto type: string type: object ResponseRetryConfig: additionalProperties: false properties: count: description: Number of retries (1-5). format: int64 type: integer on_codes: description: HTTP status codes that trigger a retry (e.g. [429, 500, 502, 503]). items: format: int64 type: integer type: - array - 'null' required: - count - on_codes type: object SecurityConfig: additionalProperties: false properties: mask: items: type: string type: - array - 'null' type: object StreamOptions: additionalProperties: false properties: include_obfuscation: type: boolean required: - include_obfuscation type: object ResponseThread: additionalProperties: false properties: id: type: string tags: items: type: string type: - array - 'null' required: - id type: object TimeoutConfig: additionalProperties: false properties: call_timeout: format: int64 type: integer required: - call_timeout type: object OrqAdvisorTool: additionalProperties: false description: Lets the primary model consult a configured secondary model for advice. properties: max_tokens: description: >- Maximum secondary-model output tokens. 0 uses the provider default; the selected model may impose a lower maximum. format: int64 maximum: 128000 minimum: 0 type: integer max_transcript_tokens: description: >- Maximum estimated conversation-transcript tokens sent to the secondary model. 0 includes the full transcript. format: int64 minimum: 0 type: integer max_uses: description: Maximum invocations per request. 0 means unlimited. format: int64 minimum: 0 type: integer model: description: Secondary model in provider/model format. minLength: 1 type: string reasoning_effort: description: >- Reasoning effort for supported models. Omit to use the provider default. enum: - none - minimal - low - medium - high - xhigh - max type: string temperature: description: Sampling temperature. The selected model may impose a lower maximum. format: double maximum: 2 minimum: 0 type: number type: description: Advisor tool discriminator. enum: - orq:advisor type: string required: - type - model title: Advisor type: object OrqSidekickTool: additionalProperties: false description: >- Lets the primary model delegate a concrete task to a configured worker model. Use type "orq:subagent" ("orq:sidekick" is the legacy alias). properties: max_tokens: description: >- Maximum secondary-model output tokens. 0 uses the provider default; the selected model may impose a lower maximum. format: int64 maximum: 128000 minimum: 0 type: integer max_uses: description: Maximum invocations per request. 0 means unlimited. format: int64 minimum: 0 type: integer model: description: Secondary model in provider/model format. minLength: 1 type: string output_format: description: Optional output-format guidance for the secondary model. type: string reasoning_effort: description: >- Reasoning effort for supported models. Omit to use the provider default. enum: - none - minimal - low - medium - high - xhigh - max type: string system_prompt: description: Optional system prompt for the secondary model. type: string temperature: description: Sampling temperature. The selected model may impose a lower maximum. format: double maximum: 2 minimum: 0 type: number type: description: Subagent tool discriminator; orq:sidekick is the legacy alias. enum: - orq:subagent - orq:sidekick type: string required: - type - model title: Subagent type: object ResponseError: additionalProperties: false properties: code: type: string message: type: string required: - code - message type: object IncompleteDetails: additionalProperties: false properties: reason: type: string required: - reason type: object Reasoning: additionalProperties: false properties: effort: description: >- Constrains effort on reasoning for reasoning models. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. enum: - none - minimal - low - medium - high - xhigh - max type: string summary: description: The format of the reasoning summary returned by the model. enum: - concise - detailed - auto - null type: - string - 'null' type: object ResponseTelemetry: additionalProperties: false properties: span_id: type: string trace_id: type: string required: - trace_id - span_id type: object PublicUsage: additionalProperties: false properties: input_cost: description: >- Cost (USD) of input tokens. Present when billing was computed for this response. format: double type: number input_tokens: format: int64 type: integer input_tokens_details: $ref: '#/components/schemas/InputTokensDetails' output_cost: description: >- Cost (USD) of output tokens. Present when billing was computed for this response. format: double type: number output_tokens: format: int64 type: integer output_tokens_details: $ref: '#/components/schemas/OutputTokensDetails' server_tool_use: $ref: '#/components/schemas/ServerToolUseDetails' description: >- Per-tool breakdown of server tool calls (provider-native and orq-executed) made during this response. total_cost: description: >- Total cost (USD) of the response. Present when billing was computed for this response. format: double type: number total_tokens: format: int64 type: integer web_search_requests: format: int64 type: integer required: - input_tokens - output_tokens - total_tokens - input_tokens_details - output_tokens_details type: object ResponseStreamEvent: description: >- A single server-sent event emitted on the response stream. The `type` field discriminates the payload. discriminator: mapping: error: '#/components/schemas/ResponseErrorStreamEvent' response.code_interpreter_call.completed: '#/components/schemas/ResponseCodeInterpreterCallCompletedStreamEvent' response.code_interpreter_call.in_progress: >- #/components/schemas/ResponseCodeInterpreterCallInProgressStreamEvent response.code_interpreter_call.interpreting: >- #/components/schemas/ResponseCodeInterpreterCallInterpretingStreamEvent response.code_interpreter_call_code.delta: '#/components/schemas/ResponseCodeInterpreterCallCodeDeltaStreamEvent' response.code_interpreter_call_code.done: '#/components/schemas/ResponseCodeInterpreterCallCodeDoneStreamEvent' response.completed: '#/components/schemas/ResponseCompletedStreamEvent' response.content_part.added: '#/components/schemas/ResponseContentPartAddedStreamEvent' response.content_part.done: '#/components/schemas/ResponseContentPartDoneStreamEvent' response.created: '#/components/schemas/ResponseCreatedStreamEvent' response.custom_tool_call_input.delta: '#/components/schemas/ResponseCustomToolCallInputDeltaStreamEvent' response.custom_tool_call_input.done: '#/components/schemas/ResponseCustomToolCallInputDoneStreamEvent' response.failed: '#/components/schemas/ResponseFailedStreamEvent' response.file_search_call.completed: '#/components/schemas/ResponseFileSearchCallCompletedStreamEvent' response.file_search_call.in_progress: '#/components/schemas/ResponseFileSearchCallInProgressStreamEvent' response.file_search_call.searching: '#/components/schemas/ResponseFileSearchCallSearchingStreamEvent' response.function_call_arguments.delta: '#/components/schemas/ResponseFunctionCallArgumentsDeltaStreamEvent' response.function_call_arguments.done: '#/components/schemas/ResponseFunctionCallArgumentsDoneStreamEvent' response.image_generation_call.completed: '#/components/schemas/ResponseImageGenerationCallCompletedStreamEvent' response.image_generation_call.generating: >- #/components/schemas/ResponseImageGenerationCallGeneratingStreamEvent response.image_generation_call.in_progress: >- #/components/schemas/ResponseImageGenerationCallInProgressStreamEvent response.image_generation_call.partial_image: >- #/components/schemas/ResponseImageGenerationCallPartialImageStreamEvent response.in_progress: '#/components/schemas/ResponseInProgressStreamEvent' response.incomplete: '#/components/schemas/ResponseIncompleteStreamEvent' response.mcp_call.completed: '#/components/schemas/ResponseMCPCallCompletedStreamEvent' response.mcp_call.failed: '#/components/schemas/ResponseMCPCallFailedStreamEvent' response.mcp_call.in_progress: '#/components/schemas/ResponseMCPCallInProgressStreamEvent' response.mcp_call_arguments.delta: '#/components/schemas/ResponseMCPCallArgumentsDeltaStreamEvent' response.mcp_call_arguments.done: '#/components/schemas/ResponseMCPCallArgumentsDoneStreamEvent' response.mcp_list_tools.completed: '#/components/schemas/ResponseMCPListToolsCompletedStreamEvent' response.mcp_list_tools.failed: '#/components/schemas/ResponseMCPListToolsFailedStreamEvent' response.mcp_list_tools.in_progress: '#/components/schemas/ResponseMCPListToolsInProgressStreamEvent' response.output_item.added: '#/components/schemas/ResponseOutputItemAddedStreamEvent' response.output_item.done: '#/components/schemas/ResponseOutputItemDoneStreamEvent' response.output_text.annotation.added: '#/components/schemas/ResponseOutputTextAnnotationAddedStreamEvent' response.output_text.delta: '#/components/schemas/ResponseOutputTextDeltaStreamEvent' response.output_text.done: '#/components/schemas/ResponseOutputTextDoneStreamEvent' response.queued: '#/components/schemas/ResponseQueuedStreamEvent' response.reasoning.delta: '#/components/schemas/ResponseReasoningDeltaStreamEvent' response.reasoning.done: '#/components/schemas/ResponseReasoningDoneStreamEvent' response.reasoning_summary_part.added: '#/components/schemas/ResponseReasoningSummaryPartAddedStreamEvent' response.reasoning_summary_part.done: '#/components/schemas/ResponseReasoningSummaryPartDoneStreamEvent' response.reasoning_summary_text.delta: '#/components/schemas/ResponseReasoningSummaryTextDeltaStreamEvent' response.reasoning_summary_text.done: '#/components/schemas/ResponseReasoningSummaryTextDoneStreamEvent' response.reasoning_text.delta: '#/components/schemas/ResponseReasoningTextDeltaStreamEvent' response.reasoning_text.done: '#/components/schemas/ResponseReasoningTextDoneStreamEvent' response.refusal.delta: '#/components/schemas/ResponseRefusalDeltaStreamEvent' response.refusal.done: '#/components/schemas/ResponseRefusalDoneStreamEvent' response.web_search_call.completed: '#/components/schemas/ResponseWebSearchCallCompletedStreamEvent' response.web_search_call.in_progress: '#/components/schemas/ResponseWebSearchCallInProgressStreamEvent' response.web_search_call.searching: '#/components/schemas/ResponseWebSearchCallSearchingStreamEvent' propertyName: type oneOf: - $ref: '#/components/schemas/ResponseCreatedStreamEvent' - $ref: '#/components/schemas/ResponseQueuedStreamEvent' - $ref: '#/components/schemas/ResponseInProgressStreamEvent' - $ref: '#/components/schemas/ResponseCompletedStreamEvent' - $ref: '#/components/schemas/ResponseFailedStreamEvent' - $ref: '#/components/schemas/ResponseIncompleteStreamEvent' - $ref: '#/components/schemas/ResponseOutputItemAddedStreamEvent' - $ref: '#/components/schemas/ResponseOutputItemDoneStreamEvent' - $ref: '#/components/schemas/ResponseContentPartAddedStreamEvent' - $ref: '#/components/schemas/ResponseContentPartDoneStreamEvent' - $ref: '#/components/schemas/ResponseOutputTextDeltaStreamEvent' - $ref: '#/components/schemas/ResponseOutputTextDoneStreamEvent' - $ref: '#/components/schemas/ResponseOutputTextAnnotationAddedStreamEvent' - $ref: '#/components/schemas/ResponseRefusalDeltaStreamEvent' - $ref: '#/components/schemas/ResponseRefusalDoneStreamEvent' - $ref: '#/components/schemas/ResponseFunctionCallArgumentsDeltaStreamEvent' - $ref: '#/components/schemas/ResponseFunctionCallArgumentsDoneStreamEvent' - $ref: '#/components/schemas/ResponseReasoningDeltaStreamEvent' - $ref: '#/components/schemas/ResponseReasoningTextDeltaStreamEvent' - $ref: '#/components/schemas/ResponseReasoningDoneStreamEvent' - $ref: '#/components/schemas/ResponseReasoningTextDoneStreamEvent' - $ref: '#/components/schemas/ResponseReasoningSummaryTextDeltaStreamEvent' - $ref: '#/components/schemas/ResponseReasoningSummaryTextDoneStreamEvent' - $ref: '#/components/schemas/ResponseReasoningSummaryPartAddedStreamEvent' - $ref: '#/components/schemas/ResponseReasoningSummaryPartDoneStreamEvent' - $ref: '#/components/schemas/ResponseWebSearchCallInProgressStreamEvent' - $ref: '#/components/schemas/ResponseWebSearchCallSearchingStreamEvent' - $ref: '#/components/schemas/ResponseWebSearchCallCompletedStreamEvent' - $ref: '#/components/schemas/ResponseFileSearchCallInProgressStreamEvent' - $ref: '#/components/schemas/ResponseFileSearchCallSearchingStreamEvent' - $ref: '#/components/schemas/ResponseFileSearchCallCompletedStreamEvent' - $ref: >- #/components/schemas/ResponseCodeInterpreterCallInProgressStreamEvent - $ref: >- #/components/schemas/ResponseCodeInterpreterCallInterpretingStreamEvent - $ref: '#/components/schemas/ResponseCodeInterpreterCallCompletedStreamEvent' - $ref: >- #/components/schemas/ResponseImageGenerationCallInProgressStreamEvent - $ref: >- #/components/schemas/ResponseImageGenerationCallGeneratingStreamEvent - $ref: '#/components/schemas/ResponseImageGenerationCallCompletedStreamEvent' - $ref: '#/components/schemas/ResponseMCPCallInProgressStreamEvent' - $ref: '#/components/schemas/ResponseMCPCallCompletedStreamEvent' - $ref: '#/components/schemas/ResponseMCPCallFailedStreamEvent' - $ref: '#/components/schemas/ResponseMCPListToolsInProgressStreamEvent' - $ref: '#/components/schemas/ResponseMCPListToolsCompletedStreamEvent' - $ref: '#/components/schemas/ResponseMCPListToolsFailedStreamEvent' - $ref: '#/components/schemas/ResponseCodeInterpreterCallCodeDeltaStreamEvent' - $ref: '#/components/schemas/ResponseCodeInterpreterCallCodeDoneStreamEvent' - $ref: '#/components/schemas/ResponseMCPCallArgumentsDeltaStreamEvent' - $ref: '#/components/schemas/ResponseMCPCallArgumentsDoneStreamEvent' - $ref: '#/components/schemas/ResponseCustomToolCallInputDeltaStreamEvent' - $ref: '#/components/schemas/ResponseCustomToolCallInputDoneStreamEvent' - $ref: >- #/components/schemas/ResponseImageGenerationCallPartialImageStreamEvent - $ref: '#/components/schemas/ResponseErrorStreamEvent' title: Response Stream Event LoadBalancerModelConfig: additionalProperties: false properties: model: type: string weight: type: number format: double required: - model - weight type: object InputTokensDetails: additionalProperties: false properties: cache_creation_1h_tokens: format: int64 type: integer cache_creation_5m_tokens: format: int64 type: integer cache_creation_tokens: format: int64 type: integer cache_write_tokens: format: int64 type: integer cached_tokens: format: int64 type: integer required: - cached_tokens - cache_write_tokens - cache_creation_tokens type: object OutputTokensDetails: additionalProperties: false properties: reasoning_tokens: format: int64 type: integer required: - reasoning_tokens type: object ServerToolUseDetails: additionalProperties: false properties: advisor_requests: format: int64 type: integer code_interpreter_sessions: format: int64 type: integer datetime_requests: format: int64 type: integer fusion_requests: format: int64 type: integer image_generation_calls: format: int64 type: integer search_models_requests: format: int64 type: integer shell_commands: format: int64 type: integer subagent_requests: format: int64 type: integer web_fetch_requests: format: int64 type: integer web_search_requests: format: int64 type: integer type: object ResponseErrorStreamEvent: additionalProperties: true description: A `error` server-sent event. properties: error: $ref: '#/components/schemas/ResponseError' sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - error type: string required: - type - sequence_number - error title: Error type: object ResponseCodeInterpreterCallCompletedStreamEvent: additionalProperties: true description: A `response.code_interpreter_call.completed` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.code_interpreter_call.completed type: string required: - type - sequence_number - item_id - output_index title: Code Interpreter Call Completed type: object ResponseCodeInterpreterCallInProgressStreamEvent: additionalProperties: true description: A `response.code_interpreter_call.in_progress` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.code_interpreter_call.in_progress type: string required: - type - sequence_number - item_id - output_index title: Code Interpreter Call In Progress type: object ResponseCodeInterpreterCallInterpretingStreamEvent: additionalProperties: true description: A `response.code_interpreter_call.interpreting` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.code_interpreter_call.interpreting type: string required: - type - sequence_number - item_id - output_index title: Code Interpreter Call Interpreting type: object ResponseCodeInterpreterCallCodeDeltaStreamEvent: additionalProperties: true description: A `response.code_interpreter_call_code.delta` server-sent event. properties: delta: description: Incremental text or argument chunk. type: string item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.code_interpreter_call_code.delta type: string required: - type - sequence_number - item_id - output_index - delta title: Code Interpreter Call Code Delta type: object ResponseCodeInterpreterCallCodeDoneStreamEvent: additionalProperties: true description: A `response.code_interpreter_call_code.done` server-sent event. properties: code: description: The completed code interpreter code. type: string item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.code_interpreter_call_code.done type: string required: - type - sequence_number - item_id - output_index - code title: Code Interpreter Call Code Done type: object ResponseCompletedStreamEvent: additionalProperties: true description: A `response.completed` server-sent event. properties: response: $ref: '#/components/schemas/PublicResponseResource' sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.completed type: string required: - type - sequence_number - response title: Completed type: object ResponseContentPartAddedStreamEvent: additionalProperties: true description: A `response.content_part.added` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer part: additionalProperties: true description: The content part. type: object sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.content_part.added type: string required: - type - sequence_number - item_id - output_index - content_index - part title: Content Part Added type: object ResponseContentPartDoneStreamEvent: additionalProperties: true description: A `response.content_part.done` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer part: additionalProperties: true description: The content part. type: object sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.content_part.done type: string required: - type - sequence_number - item_id - output_index - content_index - part title: Content Part Done type: object ResponseCreatedStreamEvent: additionalProperties: true description: A `response.created` server-sent event. properties: response: $ref: '#/components/schemas/PublicResponseResource' sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.created type: string required: - type - sequence_number - response title: Created type: object ResponseCustomToolCallInputDeltaStreamEvent: additionalProperties: true description: A `response.custom_tool_call_input.delta` server-sent event. properties: delta: description: Incremental text or argument chunk. type: string item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.custom_tool_call_input.delta type: string required: - type - sequence_number - item_id - output_index - delta title: Custom Tool Call Input Delta type: object ResponseCustomToolCallInputDoneStreamEvent: additionalProperties: true description: A `response.custom_tool_call_input.done` server-sent event. properties: input: description: The completed custom tool call input. type: string item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.custom_tool_call_input.done type: string required: - type - sequence_number - item_id - output_index - input title: Custom Tool Call Input Done type: object ResponseFailedStreamEvent: additionalProperties: true description: A `response.failed` server-sent event. properties: response: $ref: '#/components/schemas/PublicResponseResource' sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.failed type: string required: - type - sequence_number - response title: Failed type: object ResponseFileSearchCallCompletedStreamEvent: additionalProperties: true description: A `response.file_search_call.completed` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.file_search_call.completed type: string required: - type - sequence_number - item_id - output_index title: File Search Call Completed type: object ResponseFileSearchCallInProgressStreamEvent: additionalProperties: true description: A `response.file_search_call.in_progress` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.file_search_call.in_progress type: string required: - type - sequence_number - item_id - output_index title: File Search Call In Progress type: object ResponseFileSearchCallSearchingStreamEvent: additionalProperties: true description: A `response.file_search_call.searching` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.file_search_call.searching type: string required: - type - sequence_number - item_id - output_index title: File Search Call Searching type: object ResponseFunctionCallArgumentsDeltaStreamEvent: additionalProperties: true description: A `response.function_call_arguments.delta` server-sent event. properties: delta: description: Incremental text or argument chunk. type: string item_id: description: ID of the output item this event refers to. type: string obfuscation: description: Obfuscation padding accompanying the delta, when present. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.function_call_arguments.delta type: string required: - type - sequence_number - item_id - output_index - delta title: Function Call Arguments Delta type: object ResponseFunctionCallArgumentsDoneStreamEvent: additionalProperties: true description: A `response.function_call_arguments.done` server-sent event. properties: arguments: description: The completed function-call arguments JSON. type: string item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.function_call_arguments.done type: string required: - type - sequence_number - item_id - output_index - arguments title: Function Call Arguments Done type: object ResponseImageGenerationCallCompletedStreamEvent: additionalProperties: true description: A `response.image_generation_call.completed` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.image_generation_call.completed type: string required: - type - sequence_number - item_id - output_index title: Image Generation Call Completed type: object ResponseImageGenerationCallGeneratingStreamEvent: additionalProperties: true description: A `response.image_generation_call.generating` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.image_generation_call.generating type: string required: - type - sequence_number - item_id - output_index title: Image Generation Call Generating type: object ResponseImageGenerationCallInProgressStreamEvent: additionalProperties: true description: A `response.image_generation_call.in_progress` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.image_generation_call.in_progress type: string required: - type - sequence_number - item_id - output_index title: Image Generation Call In Progress type: object ResponseImageGenerationCallPartialImageStreamEvent: additionalProperties: true description: A `response.image_generation_call.partial_image` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer partial_image_b64: description: Base64-encoded partial image. type: string partial_image_index: description: Index of the partial image. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.image_generation_call.partial_image type: string required: - type - sequence_number - item_id - output_index - partial_image_b64 - partial_image_index title: Image Generation Call Partial Image type: object ResponseInProgressStreamEvent: additionalProperties: true description: A `response.in_progress` server-sent event. properties: response: $ref: '#/components/schemas/PublicResponseResource' sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.in_progress type: string required: - type - sequence_number - response title: In Progress type: object ResponseIncompleteStreamEvent: additionalProperties: true description: A `response.incomplete` server-sent event. properties: response: $ref: '#/components/schemas/PublicResponseResource' sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.incomplete type: string required: - type - sequence_number - response title: Incomplete type: object ResponseMCPCallCompletedStreamEvent: additionalProperties: true description: A `response.mcp_call.completed` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.mcp_call.completed type: string required: - type - sequence_number - item_id - output_index title: MCP Call Completed type: object ResponseMCPCallFailedStreamEvent: additionalProperties: true description: A `response.mcp_call.failed` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.mcp_call.failed type: string required: - type - sequence_number - item_id - output_index title: MCP Call Failed type: object ResponseMCPCallInProgressStreamEvent: additionalProperties: true description: A `response.mcp_call.in_progress` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.mcp_call.in_progress type: string required: - type - sequence_number - item_id - output_index title: MCP Call In Progress type: object ResponseMCPCallArgumentsDeltaStreamEvent: additionalProperties: true description: A `response.mcp_call_arguments.delta` server-sent event. properties: delta: description: Incremental text or argument chunk. type: string item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.mcp_call_arguments.delta type: string required: - type - sequence_number - item_id - output_index - delta title: MCP Call Arguments Delta type: object ResponseMCPCallArgumentsDoneStreamEvent: additionalProperties: true description: A `response.mcp_call_arguments.done` server-sent event. properties: arguments: description: The completed MCP-call arguments JSON. type: string item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.mcp_call_arguments.done type: string required: - type - sequence_number - item_id - output_index - arguments title: MCP Call Arguments Done type: object ResponseMCPListToolsCompletedStreamEvent: additionalProperties: true description: A `response.mcp_list_tools.completed` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.mcp_list_tools.completed type: string required: - type - sequence_number - item_id - output_index title: MCP List Tools Completed type: object ResponseMCPListToolsFailedStreamEvent: additionalProperties: true description: A `response.mcp_list_tools.failed` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.mcp_list_tools.failed type: string required: - type - sequence_number - item_id - output_index title: MCP List Tools Failed type: object ResponseMCPListToolsInProgressStreamEvent: additionalProperties: true description: A `response.mcp_list_tools.in_progress` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.mcp_list_tools.in_progress type: string required: - type - sequence_number - item_id - output_index title: MCP List Tools In Progress type: object ResponseOutputItemAddedStreamEvent: additionalProperties: true description: A `response.output_item.added` server-sent event. properties: item: additionalProperties: true description: The output item (message, function call, reasoning, etc.). type: object output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.output_item.added type: string required: - type - sequence_number - output_index - item title: Output Item Added type: object ResponseOutputItemDoneStreamEvent: additionalProperties: true description: A `response.output_item.done` server-sent event. properties: item: additionalProperties: true description: The output item (message, function call, reasoning, etc.). type: object output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.output_item.done type: string required: - type - sequence_number - output_index - item title: Output Item Done type: object ResponseOutputTextAnnotationAddedStreamEvent: additionalProperties: true description: A `response.output_text.annotation.added` server-sent event. properties: annotation: additionalProperties: true description: The annotation added to the output text. type: object annotation_index: description: Index of the annotation within the content part. type: integer content_index: description: Index of the content part within the output item. type: integer item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.output_text.annotation.added type: string required: - type - sequence_number - item_id - output_index - content_index - annotation_index - annotation title: Output Text Annotation Added type: object ResponseOutputTextDeltaStreamEvent: additionalProperties: true description: A `response.output_text.delta` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer delta: description: Incremental text or argument chunk. type: string item_id: description: ID of the output item this event refers to. type: string logprobs: description: Log probability information for the emitted tokens. items: type: object additionalProperties: true type: array obfuscation: description: Obfuscation padding accompanying the delta, when present. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.output_text.delta type: string required: - type - sequence_number - item_id - output_index - content_index - delta - logprobs title: Output Text Delta type: object ResponseOutputTextDoneStreamEvent: additionalProperties: true description: A `response.output_text.done` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer item_id: description: ID of the output item this event refers to. type: string logprobs: description: Log probability information for the emitted tokens. items: type: object additionalProperties: true type: array output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer text: description: The completed output text. type: string type: description: The event type. Discriminates the payload. enum: - response.output_text.done type: string required: - type - sequence_number - item_id - output_index - content_index - text - logprobs title: Output Text Done type: object ResponseQueuedStreamEvent: additionalProperties: true description: A `response.queued` server-sent event. properties: response: $ref: '#/components/schemas/PublicResponseResource' sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.queued type: string required: - type - sequence_number - response title: Queued type: object ResponseReasoningDeltaStreamEvent: additionalProperties: true description: A `response.reasoning.delta` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer delta: description: Incremental text or argument chunk. type: string item_id: description: ID of the output item this event refers to. type: string obfuscation: description: Obfuscation padding accompanying the delta, when present. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.reasoning.delta type: string required: - type - sequence_number - item_id - output_index - content_index - delta title: Reasoning Delta type: object ResponseReasoningDoneStreamEvent: additionalProperties: true description: A `response.reasoning.done` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer text: description: The completed reasoning text. type: string type: description: The event type. Discriminates the payload. enum: - response.reasoning.done type: string required: - type - sequence_number - item_id - output_index - content_index - text title: Reasoning Done type: object ResponseReasoningSummaryPartAddedStreamEvent: additionalProperties: true description: A `response.reasoning_summary_part.added` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer part: additionalProperties: true description: The reasoning summary part. type: object sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer summary_index: description: Index of the reasoning summary part. type: integer type: description: The event type. Discriminates the payload. enum: - response.reasoning_summary_part.added type: string required: - type - sequence_number - item_id - output_index - summary_index - part title: Reasoning Summary Part Added type: object ResponseReasoningSummaryPartDoneStreamEvent: additionalProperties: true description: A `response.reasoning_summary_part.done` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer part: additionalProperties: true description: The reasoning summary part. type: object sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer summary_index: description: Index of the reasoning summary part. type: integer type: description: The event type. Discriminates the payload. enum: - response.reasoning_summary_part.done type: string required: - type - sequence_number - item_id - output_index - summary_index - part title: Reasoning Summary Part Done type: object ResponseReasoningSummaryTextDeltaStreamEvent: additionalProperties: true description: A `response.reasoning_summary_text.delta` server-sent event. properties: delta: description: Incremental text or argument chunk. type: string item_id: description: ID of the output item this event refers to. type: string obfuscation: description: Obfuscation padding accompanying the delta, when present. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer summary_index: description: Index of the reasoning summary part. type: integer type: description: The event type. Discriminates the payload. enum: - response.reasoning_summary_text.delta type: string required: - type - sequence_number - item_id - output_index - summary_index - delta title: Reasoning Summary Text Delta type: object ResponseReasoningSummaryTextDoneStreamEvent: additionalProperties: true description: A `response.reasoning_summary_text.done` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer summary_index: description: Index of the reasoning summary part. type: integer text: description: The completed reasoning summary text. type: string type: description: The event type. Discriminates the payload. enum: - response.reasoning_summary_text.done type: string required: - type - sequence_number - item_id - output_index - summary_index - text title: Reasoning Summary Text Done type: object ResponseReasoningTextDeltaStreamEvent: additionalProperties: true description: A `response.reasoning_text.delta` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer delta: description: Incremental text or argument chunk. type: string item_id: description: ID of the output item this event refers to. type: string obfuscation: description: Obfuscation padding accompanying the delta, when present. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.reasoning_text.delta type: string required: - type - sequence_number - item_id - output_index - content_index - delta title: Reasoning Text Delta type: object ResponseReasoningTextDoneStreamEvent: additionalProperties: true description: A `response.reasoning_text.done` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer text: description: The completed reasoning text. type: string type: description: The event type. Discriminates the payload. enum: - response.reasoning_text.done type: string required: - type - sequence_number - item_id - output_index - content_index - text title: Reasoning Text Done type: object ResponseRefusalDeltaStreamEvent: additionalProperties: true description: A `response.refusal.delta` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer delta: description: Incremental text or argument chunk. type: string item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.refusal.delta type: string required: - type - sequence_number - item_id - output_index - content_index - delta title: Refusal Delta type: object ResponseRefusalDoneStreamEvent: additionalProperties: true description: A `response.refusal.done` server-sent event. properties: content_index: description: Index of the content part within the output item. type: integer item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer refusal: description: The completed refusal text. type: string sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.refusal.done type: string required: - type - sequence_number - item_id - output_index - content_index - refusal title: Refusal Done type: object ResponseWebSearchCallCompletedStreamEvent: additionalProperties: true description: A `response.web_search_call.completed` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.web_search_call.completed type: string required: - type - sequence_number - item_id - output_index title: Web Search Call Completed type: object ResponseWebSearchCallInProgressStreamEvent: additionalProperties: true description: A `response.web_search_call.in_progress` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.web_search_call.in_progress type: string required: - type - sequence_number - item_id - output_index title: Web Search Call In Progress type: object ResponseWebSearchCallSearchingStreamEvent: additionalProperties: true description: A `response.web_search_call.searching` server-sent event. properties: item_id: description: ID of the output item this event refers to. type: string output_index: description: Index of the output item in the response output array. type: integer sequence_number: description: Monotonically increasing sequence number for ordering events. type: integer type: description: The event type. Discriminates the payload. enum: - response.web_search_call.searching type: string required: - type - sequence_number - item_id - output_index title: Web Search Call Searching type: object PublicResponseResource: additionalProperties: false properties: background: type: boolean completed_at: format: int64 type: - integer - 'null' conversation: $ref: '#/components/schemas/ConversationParam' created_at: format: int64 type: integer error: anyOf: - $ref: '#/components/schemas/ResponseError' - type: 'null' frequency_penalty: type: number format: double id: type: string incomplete_details: anyOf: - $ref: '#/components/schemas/IncompleteDetails' - type: 'null' input: description: Array of input items (messages, function call outputs, etc.) items: {} type: - array - 'null' instructions: type: - string - 'null' max_output_tokens: format: int64 type: - integer - 'null' max_tool_calls: format: int64 type: - integer - 'null' memory: $ref: '#/components/schemas/MemoryParam' metadata: additionalProperties: type: string description: >- Developer-defined key-value pairs attached to the response (OpenAI spec: Map). type: object model: type: string object: description: Always "response" type: string output: description: Array of output items (messages, function calls, reasoning, etc.) items: {} type: - array - 'null' parallel_tool_calls: type: boolean presence_penalty: type: number format: double previous_response_id: type: - string - 'null' prompt_cache_key: type: - string - 'null' prompt_cache_options: anyOf: - $ref: '#/components/schemas/OpenAIPromptCacheOptions' - type: 'null' prompt_cache_retention: type: - string - 'null' reasoning: anyOf: - $ref: '#/components/schemas/Reasoning' - type: 'null' safety_identifier: type: - string - 'null' service_tier: enum: - auto - default - flex - fast - scale - priority type: string status: enum: - queued - in_progress - completed - failed - incomplete type: string store: type: boolean telemetry: $ref: '#/components/schemas/ResponseTelemetry' description: OpenTelemetry trace and span identifiers for this response. temperature: type: number format: double text: description: Text output configuration including format and verbosity tool_choice: description: >- Tool choice setting: "auto", "none", "required", or a specific function tools: description: Array of tool configurations used in this response items: {} type: - array - 'null' top_k: description: >- Only sample from the top K options for each subsequent token. Present only when set on the request. format: int64 type: integer top_logprobs: format: int64 type: integer top_p: type: number format: double truncation: enum: - disabled - auto type: string usage: anyOf: - $ref: '#/components/schemas/PublicUsage' - type: 'null' user: type: - string - 'null' variables: type: object additionalProperties: {} required: - id - object - created_at - completed_at - status - incomplete_details - model - previous_response_id - instructions - input - output - error - tools - tool_choice - temperature - top_p - presence_penalty - frequency_penalty - top_logprobs - max_output_tokens - max_tool_calls - reasoning - text - user - usage - truncation - parallel_tool_calls - store - background - metadata - service_tier - safety_identifier - prompt_cache_key - prompt_cache_retention - prompt_cache_options type: object securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.