> ## Documentation Index > Fetch the complete documentation index at: https://docs.cekura.ai/llms.txt > Use this file to discover all available pages before exploring further. # Preview Metric V3 > Evaluate a metric configuration on up to 10 call logs or runs and return the verdicts, without saving the metric. Use it to check a metric before creating or updating it. Usually 30 seconds to 3 minutes; custom-code metrics can take longer. ## OpenAPI ````yaml post /test_framework/v3/metrics/preview/ openapi: 3.1.0 info: title: Cekura API version: v1 description: >- Complete API documentation for the Cekura platform. This API provides endpoints for testing, observing, and evaluating AI voice agents — including managing agents, running evaluators, defining metrics, and analyzing call quality. servers: - url: https://api.cekura.ai security: [] paths: /test_framework/v3/metrics/preview/: post: tags: - test_framework summary: Preview metric description: >- Evaluate a metric configuration on up to 10 call logs or runs and return the verdicts, without saving the metric. Use it to check a metric before creating or updating it. Usually 30 seconds to 3 minutes; custom-code metrics can take longer. operationId: metrics-v3-preview requestBody: content: application/json: schema: $ref: '#/components/schemas/MetricPreview' application/x-www-form-urlencoded: schema: $ref: '#/components/schemas/MetricPreview' multipart/form-data: schema: $ref: '#/components/schemas/MetricPreview' required: true responses: '200': content: application/json: schema: type: object properties: status: type: string enum: - completed - failed description: >- `failed` when the job could not produce its result; see `error` / `errors`. project_id: type: - integer - 'null' agent_id: type: - integer - 'null' completed: type: integer description: Items evaluated. total: type: integer results: type: array items: type: object description: >- One per previewed call log (`call_log_id`, `call_id`) or run (`run_id`). The verdict is `result`, or `score` / `enum` for custom-code metrics. properties: result: description: Verdict for LLM-judge metrics. score: type: number enum: type: string explanation: type: string is_relevant: type: boolean call_log_id: type: integer call_id: type: - string - 'null' run_id: type: integer error: type: - string - 'null' error: type: - string - 'null' description: Why the job failed, when it did. description: '' '400': content: application/json: schema: type: object properties: field_name: type: array items: type: string description: '' '403': description: No access to the agent, project or metric the job runs on. '504': description: >- The job did not finish within 15 minutes. It may still complete in the background. security: - api_key: [] - oauth2: [] - embedded_session: [] - supabase_session: [] components: schemas: MetricPreview: type: object properties: agent_id: type: integer description: Agent ID - all call logs/runs must belong to this agent project_id: type: integer description: Project ID - all call logs/runs must belong to this project call_log_ids: type: array items: type: integer description: >- List of call log IDs to evaluate (maximum 10, required if run_ids not provided) maxItems: 10 minItems: 1 run_ids: type: array items: type: integer description: >- List of run IDs to evaluate (maximum 10, required if call_log_ids not provided) maxItems: 10 minItems: 1 metric_data: allOf: - $ref: '#/components/schemas/MetricPreviewData' description: Metric configuration to evaluate required: - metric_data MetricPreviewData: type: object properties: name: type: string description: Name of the metric maxLength: 255 type: enum: - basic - custom_prompt - custom_code - llm_judge type: string x-spec-enum-id: b44700c0a6443b40 description: >- Type of metric: basic, custom_prompt, or custom_code * `basic` - Basic (Deprecated in favor of LLM Judge) * `custom_prompt` - Custom Prompt ( Deprecated in favor of LLM Judge) * `custom_code` - Custom Code * `llm_judge` - LLM Judge eval_type: enum: - binary - continuous_qualitative - numeric - enum type: string x-spec-enum-id: b40eac6824409cc2 description: >- Evaluation type: binary, continuous_qualitative, numeric, or enum. Legacy values (binary_workflow_adherence, binary_qualitative) are accepted and mapped to binary. * `binary` - Binary * `continuous_qualitative` - Continuous Qualitative * `numeric` - Numeric * `enum` - Enum evaluation_trigger: enum: - always - automatic - custom type: string x-spec-enum-id: ecd3c02e0e393ef5 default: always description: |- When to trigger evaluation: always, automatic, or custom * `always` - Always * `automatic` - Automatic * `custom` - Custom trigger_type: enum: - llm_judge - custom_code type: string x-spec-enum-id: 2adad4b8df61914f default: llm_judge description: >- Type of trigger evaluation: llm_judge or custom_code (only used when evaluation_trigger is custom) * `llm_judge` - LLM Judge * `custom_code` - Custom Code evaluation_trigger_prompt: type: string default: '' description: >- Prompt for evaluation trigger (required for custom trigger with llm_judge) evaluation_trigger_custom_code: type: string default: '' description: >- Python code for trigger evaluation (required for custom trigger with custom_code) description: type: string default: '' description: Description of what the metric measures (required for basic type) prompt: type: string default: '' description: Custom prompt for evaluation (required for custom_prompt type) custom_code: type: string default: '' description: Python code for custom evaluation (required for custom_code type) enum_values: type: array items: type: string description: List of possible enum values (required when eval_type is enum) audio_enabled: type: boolean default: false description: Whether the LLM judge must evaluate the source recording required: - eval_type - name - type securitySchemes: api_key: type: apiKey in: header name: X-CEKURA-API-KEY description: >- API Key Authentication. It should be included in the header of each request. oauth2: type: http scheme: bearer bearerFormat: JWT description: OAuth access token issued by Cekura for connected apps. embedded_session: type: http scheme: bearer bearerFormat: JWT description: Embedded-dashboard session token. Internal. supabase_session: type: http scheme: bearer bearerFormat: JWT description: Cekura dashboard session token. Not a customer API credential. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.