> ## Documentation Index > Fetch the complete documentation index at: https://penseapp.vercel.app/docs/llms.txt > Use this file to discover all available pages before exploring further. # Get evaluator > Get one evaluator with its full version history ## OpenAPI ````yaml /api-reference/openapi.json get /evaluators/{evaluator_uuid} openapi: 3.1.0 info: title: Calibrate Public API version: 0.1.0 description: Programmatic API for CI/automation. Pass your key in the `X-API-Key` header. servers: - url: https://api.calibrate.artpark.ai description: Production security: [] paths: /evaluators/{evaluator_uuid}: get: tags: - evaluators summary: Get evaluator description: Get one evaluator with its full version history operationId: get_evaluator_endpoint_evaluators__evaluator_uuid__get parameters: - name: evaluator_uuid in: path required: true schema: type: string description: Evaluator to retrieve examples: - f47ac10b-58cc-4372-a567-0e02b2c3d479 title: Evaluator Uuid description: Evaluator to retrieve - name: compact in: query required: false schema: type: boolean description: >- Return a compact response that omits heavy detail fields (`versions.system_prompt`, `versions.output_config`, `versions.variables`), keeping only the lightweight decision fields. Omit for full detail default: false title: Compact description: >- Return a compact response that omits heavy detail fields (`versions.system_prompt`, `versions.output_config`, `versions.variables`), keeping only the lightweight decision fields. Omit for full detail responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/EvaluatorDetailResponseCompact' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - ApiKeyAuth: [] components: schemas: EvaluatorDetailResponseCompact: properties: uuid: type: string maxLength: 36 minLength: 36 title: Uuid description: Evaluator ID examples: - f47ac10b-58cc-4372-a567-0e02b2c3d479 name: type: string title: Name description: Evaluator name description: anyOf: - type: string - type: 'null' title: Description description: What the evaluator checks evaluator_type: type: string enum: - tts - stt - llm - llm-general - conversation title: Evaluator Type description: | What the evaluator judges: - `tts`: TTS audio - `stt`: one transcript - `llm`: a reply with its conversation history - `llm-general`: a standalone input and output pair - `conversation`: a full conversation data_type: type: string enum: - text - audio title: Data Type description: | The modality the judge reads: - `text` - `audio` output_type: type: string enum: - binary - rating title: Output Type description: | How the evaluator scores: - `binary`: pass or fail - `rating`: a numeric score, using the scale in `output_config` is_default: type: boolean title: Is Default description: >- True when the evaluator is a built-in default or your workspace's editable copy of one. False for an evaluator you created yourself slug: anyOf: - type: string - type: 'null' title: Slug description: Stable slug for a built-in default evaluator source_default_slug: anyOf: - type: string - type: 'null' title: Source Default Slug description: >- Stable slug of the built-in default this evaluator is your editable copy of. Set on your default forks so you can identify a specific default by it live_version_id: anyOf: - type: string maxLength: 36 minLength: 36 - type: 'null' title: Live Version Id description: ID of the version that is currently live examples: - 6ba7b810-9dad-11d1-80b4-00c04fd430c8 created_at: type: string title: Created At description: When the evaluator was created (ISO 8601 UTC) updated_at: type: string title: Updated At description: When the evaluator was last updated (ISO 8601 UTC) versions: items: $ref: '#/components/schemas/EvaluatorVersionCompact' type: array title: Versions description: Full version history, oldest first type: object required: - uuid - name - evaluator_type - data_type - output_type - is_default - created_at - updated_at - versions title: EvaluatorDetailResponseCompact HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError EvaluatorVersionCompact: properties: uuid: type: string maxLength: 36 minLength: 36 title: Uuid description: Version ID examples: - 6ba7b810-9dad-11d1-80b4-00c04fd430c8 version_number: type: integer title: Version Number description: >- The version's number. The first version is 1, and it goes up by one for each new version of the evaluator judge_model: type: string title: Judge Model description: >- The model that runs the judge, named the way its provider does, for example `openai/gpt-4.1` or `anthropic/claude-sonnet-4` system_prompt: anyOf: - type: string - type: 'null' title: System Prompt description: Judge system prompt, with `{{variable}}` placeholders unrendered output_config: anyOf: - $ref: '#/components/schemas/OutputConfig' - type: 'null' description: >- The scale points and their labels. Required for a `rating` evaluator. A `binary` evaluator uses the default Correct/Wrong labels unless you set your own variables: anyOf: - items: $ref: '#/components/schemas/VariableSpec' type: array - type: 'null' title: Variables description: Declared prompt variables created_at: type: string title: Created At description: When the version was created (ISO 8601 UTC) type: object required: - uuid - version_number - judge_model - created_at title: EvaluatorVersionCompact ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError OutputConfig: properties: scale: anyOf: - items: $ref: '#/components/schemas/OutputScaleEntry' type: array - type: 'null' title: Scale description: >- The ordered scale points that make up the rubric, each with its label type: object title: OutputConfig VariableSpec: properties: name: type: string title: Name description: Name of a `{{placeholder}}` used in the system prompt description: anyOf: - type: string - type: 'null' title: Description description: What the variable is for. Omit if self-evident default: anyOf: - type: string - type: 'null' title: Default description: Default value used when you omit this variable. Omit for no default type: object required: - name title: VariableSpec OutputScaleEntry: properties: value: title: Value description: >- The value for this scale point. Use a boolean for a `binary` evaluator, a number for a `rating` one name: type: string title: Name description: Short label for this scale point description: anyOf: - type: string - type: 'null' title: Description description: >- Rubric text for this level, added to the judge prompt. Omit to leave this level undescribed color: anyOf: - type: string - type: 'null' title: Color description: Color to show for this level. Omit for the default type: object required: - value - name title: OutputScaleEntry description: >- One entry in an evaluator's output_config.scale. `value` is bool|number|string depending on output_type. securitySchemes: ApiKeyAuth: type: apiKey in: header name: X-API-Key description: API key for authentication ````