> ## 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. # Add metrics > Add metrics to a deployment ## OpenAPI ````yaml post /v2/deployments/{id}/metrics openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://api.orq.ai security: - ApiKey: [] tags: - name: Guardrail Rules - name: Policies - name: Routing Rules - name: Files description: File upload and retrieval operations. - name: FilesService - name: Projects description: Projects organize resources within a workspace - name: ProjectsService - name: Skills description: >- Skills are modular instructions you can use to codify processes and conventions - name: SkillsService - name: Responses - description: >- Run agents on a cadence — cron, interval, or one-off. Minimum firing interval is 1 hour. name: Agent Schedules - 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: ReportingService description: |- ReportingService exposes a single QueryReport RPC that maps allowlisted analytics payloads onto safe rollup queries. Callers never send SQL; the backend picks the rollup family and grain from the metric catalogue, the requested range, and the requested grouping. externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/deployments/{id}/metrics: post: tags: - Deployments summary: Add metrics description: Add metrics to a deployment operationId: DeploymentCreateMetric parameters: - schema: type: string description: Deployment ID required: true description: Deployment ID name: id in: path requestBody: required: true description: The deployment request payload content: application/json: schema: type: object properties: metadata: type: object additionalProperties: {} description: >- Your own custom key-value pairs can be attached to the logs. This is useful for storing additional information related to your interactions with the LLM providers or specifics within your application. usage: type: object properties: prompt_tokens: type: number description: Number of tokens in the prompt. completion_tokens: type: number description: Number of tokens in the generated completion. total_tokens: type: number description: >- Total number of tokens used in the request (prompt + completion). required: - prompt_tokens - completion_tokens description: Usage statistics to add to the deployment performance: type: object properties: latency: type: number description: >- Total time in milliseconds of the request to the LLM provider API. time_to_first_token: type: number description: >- Total time in milliseconds to generate the first token of the completion. required: - latency messages: type: array items: oneOf: - type: object properties: role: type: string enum: - system description: >- The role of the messages author, in this case `system`. content: anyOf: - type: string description: The contents of the system message. - type: array items: $ref: '#/components/schemas/TextContentPartSchema' minItems: 1 description: >- An array of content parts with a defined type. For system messages, only type `text` is supported. description: The contents of the system message. name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - role - content title: System message description: >- Developer-provided instructions that the model should follow, regardless of messages sent by the user. - type: object properties: role: type: string enum: - developer description: >- The role of the messages author, in this case `developer`. content: anyOf: - type: string description: The contents of the system message. - type: array items: $ref: '#/components/schemas/TextContentPartSchema' minItems: 1 description: >- An array of content parts with a defined type. For system messages, only type `text` is supported. description: The contents of the developer message. name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - role - content title: Developer message - type: object properties: role: type: string enum: - user description: >- The role of the messages author, in this case `user`. name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. content: anyOf: - type: string description: The text contents of the message. - type: array items: oneOf: - $ref: >- #/components/schemas/TextContentPartSchema - $ref: >- #/components/schemas/ImageContentPartSchema - $ref: >- #/components/schemas/AudioContentPartSchema - type: object properties: type: type: string enum: - file description: >- The type of the content part. Always `file`. cache_control: type: object properties: type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". ttl: type: string enum: - 5m - 1h 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. required: - type file: $ref: >- #/components/schemas/FileContentPartSchema required: - type - file description: >- An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text, image, or audio inputs. description: The contents of the user message. required: - role - content title: User message - type: object properties: content: anyOf: - type: string description: The contents of the assistant message. - type: array items: oneOf: - $ref: >- #/components/schemas/TextContentPartSchema - $ref: '#/components/schemas/RefusalPartSchema' - $ref: '#/components/schemas/ReasoningPartSchema' - $ref: >- #/components/schemas/RedactedReasoningPartSchema discriminator: propertyName: type mapping: text: $ref: >- #/components/schemas/TextContentPartSchema refusal: $ref: '#/components/schemas/RefusalPartSchema' reasoning: $ref: '#/components/schemas/ReasoningPartSchema' redacted_reasoning: $ref: >- #/components/schemas/RedactedReasoningPartSchema description: >- An array of content parts with a defined type. Can be one or more of type `text`, or exactly one of type `refusal`. - type: 'null' description: >- The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. refusal: type: - string - 'null' description: The refusal message by the assistant. role: type: string enum: - assistant description: >- The role of the messages author, in this case `assistant`. name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. audio: type: - object - 'null' properties: id: type: string description: >- Unique identifier for a previous audio response from the model. required: - id description: >- Data about a previous audio response from the model. tool_calls: type: array items: type: object properties: id: type: string description: The ID of the tool call. type: type: string enum: - function description: >- The type of the tool. Currently, only `function` is supported. function: type: object properties: name: type: string description: The name of the function to call. arguments: type: string description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. thought_signature: type: string description: >- Encrypted representation of the model internal reasoning state during function calling. Required by Gemini 3 models when continuing a conversation after a tool call. required: - id - type - function description: >- The tool calls generated by the model, such as function calls. required: - role title: Assistant message - type: object properties: role: type: string enum: - tool description: >- The role of the messages author, in this case tool. content: anyOf: - type: string - type: array items: oneOf: - $ref: >- #/components/schemas/TextContentPartSchema discriminator: propertyName: type mapping: text: $ref: >- #/components/schemas/TextContentPartSchema description: The contents of the tool message. tool_call_id: type: - string - 'null' description: Tool call that this message is responding to. cache_control: type: object properties: type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". ttl: type: string enum: - 5m - 1h 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. required: - type required: - role - content - tool_call_id title: Tool message description: A list of messages sent to the model. choices: type: array items: oneOf: - type: object properties: role: type: string enum: - system description: >- The role of the messages author, in this case `system`. content: anyOf: - type: string description: The contents of the system message. - type: array items: $ref: '#/components/schemas/TextContentPartSchema' minItems: 1 description: >- An array of content parts with a defined type. For system messages, only type `text` is supported. description: The contents of the system message. name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - role - content title: System message description: >- Developer-provided instructions that the model should follow, regardless of messages sent by the user. - type: object properties: role: type: string enum: - developer description: >- The role of the messages author, in this case `developer`. content: anyOf: - type: string description: The contents of the system message. - type: array items: $ref: '#/components/schemas/TextContentPartSchema' minItems: 1 description: >- An array of content parts with a defined type. For system messages, only type `text` is supported. description: The contents of the developer message. name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - role - content title: Developer message - type: object properties: role: type: string enum: - user description: >- The role of the messages author, in this case `user`. name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. content: anyOf: - type: string description: The text contents of the message. - type: array items: oneOf: - $ref: >- #/components/schemas/TextContentPartSchema - $ref: >- #/components/schemas/ImageContentPartSchema - $ref: >- #/components/schemas/AudioContentPartSchema - type: object properties: type: type: string enum: - file description: >- The type of the content part. Always `file`. cache_control: type: object properties: type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". ttl: type: string enum: - 5m - 1h 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. required: - type file: $ref: >- #/components/schemas/FileContentPartSchema required: - type - file description: >- An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text, image, or audio inputs. description: The contents of the user message. required: - role - content title: User message - type: object properties: content: anyOf: - type: string description: The contents of the assistant message. - type: array items: oneOf: - $ref: >- #/components/schemas/TextContentPartSchema - $ref: '#/components/schemas/RefusalPartSchema' - $ref: '#/components/schemas/ReasoningPartSchema' - $ref: >- #/components/schemas/RedactedReasoningPartSchema discriminator: propertyName: type mapping: text: $ref: >- #/components/schemas/TextContentPartSchema refusal: $ref: '#/components/schemas/RefusalPartSchema' reasoning: $ref: '#/components/schemas/ReasoningPartSchema' redacted_reasoning: $ref: >- #/components/schemas/RedactedReasoningPartSchema description: >- An array of content parts with a defined type. Can be one or more of type `text`, or exactly one of type `refusal`. - type: 'null' description: >- The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. refusal: type: - string - 'null' description: The refusal message by the assistant. role: type: string enum: - assistant description: >- The role of the messages author, in this case `assistant`. name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. audio: type: - object - 'null' properties: id: type: string description: >- Unique identifier for a previous audio response from the model. required: - id description: >- Data about a previous audio response from the model. tool_calls: type: array items: type: object properties: id: type: string description: The ID of the tool call. type: type: string enum: - function description: >- The type of the tool. Currently, only `function` is supported. function: type: object properties: name: type: string description: The name of the function to call. arguments: type: string description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. thought_signature: type: string description: >- Encrypted representation of the model internal reasoning state during function calling. Required by Gemini 3 models when continuing a conversation after a tool call. required: - id - type - function description: >- The tool calls generated by the model, such as function calls. required: - role title: Assistant message - type: object properties: role: type: string enum: - tool description: >- The role of the messages author, in this case tool. content: anyOf: - type: string - type: array items: oneOf: - $ref: >- #/components/schemas/TextContentPartSchema discriminator: propertyName: type mapping: text: $ref: >- #/components/schemas/TextContentPartSchema description: The contents of the tool message. tool_call_id: type: - string - 'null' description: Tool call that this message is responding to. cache_control: type: object properties: type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". ttl: type: string enum: - 5m - 1h 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. required: - type required: - role - content - tool_call_id title: Tool message description: >- A list of completion choices. If you are using a `completion` model then you must provide the `completion content` with the chat completion format feedback: type: object properties: score: type: integer minimum: 0 maximum: 100 description: >- The feedback score. This allow you to come with specific logic on what a `score` number means required: - score description: Feedback from the user on the completion responses: '200': description: Successful operation content: application/json: schema: type: object properties: success: type: boolean description: Whether the request was successful required: - success '400': description: Bad Request '401': description: Unauthorized. deprecated: true components: schemas: TextContentPartSchema: type: object properties: type: type: string enum: - text description: The type of the content part. text: type: string description: The text content. cache_control: type: object properties: type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". ttl: type: string enum: - 5m - 1h 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. required: - type required: - type - text title: Text content part description: The type of the content part. ImageContentPartSchema: type: object properties: type: type: string enum: - image_url image_url: type: object properties: url: type: string description: Either a URL of the image or the base64 encoded image data. detail: type: string enum: - low - high - auto description: Specifies the detail level of the image. required: - url cache_control: type: object properties: type: type: string enum: - ephemeral description: >- Create a cache control breakpoint at this content block. Accepts only the value "ephemeral". ttl: type: string enum: - 5m - 1h 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. required: - type required: - type - image_url title: Image content part description: An image content part AudioContentPartSchema: type: object properties: type: type: string enum: - input_audio input_audio: type: object properties: data: type: string description: Base64 encoded audio data. format: type: string enum: - mp3 - wav description: >- The format of the encoded audio data. Currently supports `wav` and `mp3`. required: - data - format required: - type - input_audio title: Audio content part description: An audio content part FileContentPartSchema: type: object properties: file_data: type: string description: >- The file data as a data URI string in the format 'data:;base64,'. Example: 'data:image/png;base64,iVBORw0KGgoAAAANS...' uri: type: string description: >- URL to the file. Only supported by Anthropic Claude models for PDF files. mimeType: type: string description: MIME type of the file (e.g., application/pdf, image/png) filename: type: string description: >- The name of the file, used when passing the file to the model as a string. description: >- File data for the content part. Must contain either file_data or uri, but not both. RefusalPartSchema: type: object properties: type: type: string enum: - refusal description: The type of the content part. Always `refusal`. refusal: type: string description: The refusal message generated by the model. required: - type title: Refusal part description: A message part containing a refusal message. ReasoningPartSchema: type: object properties: type: type: string enum: - reasoning description: The type of the content part. Always `reasoning`. reasoning: type: string description: >- The reasoning or thought process behind the response. Used for chain-of-thought or extended thinking. signature: type: string description: >- Optional cryptographic signature to verify the authenticity and integrity of the reasoning content required: - type - reasoning - signature title: Reasoning Part description: A message part containing reasoning or chain-of-thought content RedactedReasoningPartSchema: type: object properties: type: type: string enum: - redacted_reasoning description: The type of the content part. Always `reasoning`. data: type: string description: >- The encrypted reasoning or thought process behind the response. Used for chain-of-thought or extended thinking. required: - type - data title: Reasoning Part description: A message part containing reasoning or chain-of-thought content securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ````