> ## Documentation Index > Fetch the complete documentation index at: https://docs.zelto.ai/llms.txt > Use this file to discover all available pages before exploring further. # Estimate a run > Prices a run before it starts and returns the `estimateToken` that starts it. Nothing is written. Required before every run. ## OpenAPI ````yaml /docs-openapi.json post /v1/benchmarks/{id}/estimate openapi: 3.1.0 info: title: Zelto REST API version: v1 description: >- Programmatic access to your Zelto organization. Every endpoint is scoped to the organization the API key belongs to. Mint a key at Settings → Integrations → API integration. servers: - url: https://api.zelto.ai description: Production security: - bearerAuth: [] tags: - name: Monitors description: Filtered, asynchronous exports of stored monitor results. - name: Agents description: Voice and text agents normalised through Zelto's ingestion pipeline. - name: Conversations description: >- Phone calls, chats, and voicemails — plus their transcripts and recordings. - name: Customer Metrics description: >- Customer-provided evaluations attached to a conversation (requires metrics enabled). - name: Reviews description: Human review state for conversations. - name: Buckets description: Reviewer routing — group conversations for batched review. - name: Companies description: Clients or brands your agents work for, and their logos. - name: Findings description: >- Structured issues discovered during analysis, with optional conversation attachments and comments. - name: Experiments description: >- Prospective measurement of two externally routed prompt versions across independent monitor outcomes. - name: Organizations description: >- Headless org provisioning. Requires an admin/service API key (not a read-only org-scoped customer key). - name: AI providers description: >- Your organization's own (bring-your-own) AI provider keys. Monitors can run on them instead of Zelto's built-in models. Owner or admin keys only; the secret is write-only. - name: Benchmarks description: >- Repeatable evaluations of agent prompts, models and speech-to-text engines over a fixed set of cases, scored by Judges. paths: /v1/benchmarks/{id}/estimate: post: tags: - Benchmarks summary: Estimate a run description: >- Prices a run before it starts and returns the `estimateToken` that starts it. Nothing is written. Required before every run. operationId: estimateBenchmarkRun parameters: - name: id in: path required: true description: Benchmark id. schema: type: string format: uuid requestBody: required: true content: application/json: schema: type: object properties: candidates: minItems: 1 maxItems: 10 type: array items: type: object properties: model: type: string minLength: 1 maxLength: 200 description: >- A `model` from the candidate options: "openai/gpt-5-mini", "bedrock/…", or for STT "deepgram/nova-3". agentVersionId: description: >- LLM only: the agent prompt version to test. Null = the prompt as recorded on each case. anyOf: - type: string format: uuid - type: 'null' aiKeyId: description: >- Run on this organization AI key (bring your own key). Omit for the platform model. anyOf: - type: string format: uuid - type: 'null' label: description: 'Display label. Default: model + version.' type: string maxLength: 200 required: - model description: What the run compares, in display order. repeats: description: Repeats per case (LLM, 1-3). STT always 1. type: integer minimum: 1 maximum: 3 versionNumber: description: >- Published version to run. Default: the current published version (or the draft when nothing is published). type: integer minimum: 1 draft: description: Run the unpublished draft instead of a published version. type: boolean required: - candidates responses: '200': description: Successful response. content: application/json: schema: $ref: '#/components/schemas/BenchmarkRunEstimate' '400': $ref: '#/components/responses/ValidationFailed' '401': $ref: '#/components/responses/Unauthorized' '403': description: >- `phi_mode_blocked`: The organization is in PHI mode, which allows only Bedrock-routed models and AWS Transcribe. content: application/json: schema: $ref: '#/components/schemas/BenchmarkError' '404': $ref: '#/components/responses/NotFound' '409': description: '`conflict`: The resource is not in a state that allows this.' content: application/json: schema: $ref: '#/components/schemas/BenchmarkError' components: schemas: BenchmarkRunEstimate: type: object properties: estimateToken: type: string description: Pass unchanged to start the run. Single use; expires in 15 minutes. benchmarkId: type: string versionNumber: type: - number - 'null' isDraftRun: type: boolean repeats: type: number caseCount: type: number cellCount: type: number perCandidate: type: array items: type: object properties: model: type: string agentVersionId: type: - string - 'null' cells: type: number unitCostUsd: type: number description: USD. costUsd: type: number description: USD. required: - model - agentVersionId - cells - unitCostUsd - costUsd additionalProperties: {} totalCostUsd: type: number description: >- What Zelto bills (platform cost plus margin, plus bring-your-own-key fees). warnings: type: array items: type: string unverifiedReferences: description: >- STT: cases scored against a reference transcript nobody has checked yet (warning `unverified_references`). type: integer missingVariables: description: >- LLM: cases whose prompt references a `{{variable}}` they don't fill (warning `missing_variables`). anyOf: - type: object properties: pairs: type: integer description: >- Case × candidate pairs that will error `missing_variable:` at $0, before the model call. cells: type: integer description: Their cells (pairs × repeats). names: type: array items: type: string description: The missing variable names, most frequent first. required: - pairs - cells - names additionalProperties: {} - type: 'null' planLimits: type: array items: type: object properties: code: type: string const: plan_limit cap: type: string description: >- `cells_per_run` (includes the hard maximum of 5,000), `runs_per_month` or `concurrent_runs`. limit: type: number current: type: number requested: type: number required: - code - cap - limit - current - requested additionalProperties: {} description: >- Plan limits starting this run would exceed. Non-empty adds the warning `plan_limit`; starting returns 403 `plan_limit`. canStart: type: boolean description: >- False when starting now would be refused (a plan limit, or spend `blocked`). candidates: type: array items: type: object properties: label: type: string model: type: string agentVersionId: type: - string - 'null' agentVersionLabel: type: - string - 'null' aiKeyId: type: - string - 'null' billedBy: type: string enum: - zelto - byok required: - label - model - agentVersionId - agentVersionLabel - aiKeyId - billedBy additionalProperties: {} billing: type: object properties: typicalCostUsd: type: number description: USD. billedByYourKeysUsd: type: number description: Billed to your own provider keys, not by Zelto. costCapUsd: type: number description: The run's hard cap (1.5 × the estimate). expiresAt: type: string required: - typicalCostUsd - billedByYourKeysUsd - costCapUsd - expiresAt additionalProperties: {} spend: type: object properties: decision: type: string enum: - allowed - approval_required - blocked description: What starting now would do. reason: anyOf: - type: string enum: - monthly_cap - threshold - free_credit_exhausted - type: 'null' monthToDateUsd: type: number description: USD. monthlyCapUsd: anyOf: - type: number description: USD. - type: 'null' creditRemainingUsd: type: number description: USD. required: - decision - reason - monthToDateUsd - monthlyCapUsd - creditRemainingUsd additionalProperties: {} required: - estimateToken - benchmarkId - versionNumber - isDraftRun - repeats - caseCount - cellCount - perCandidate - totalCostUsd - warnings - planLimits - canStart - candidates - billing - spend additionalProperties: {} description: A priced run plan plus the token that starts it. BenchmarkError: type: object required: - error - code - message properties: error: type: string enum: - validation_failed - invalid_parameter - approval_required - plan_limit - phi_mode_blocked - owner_required - not_entitled - forbidden - not_found - payload_too_large - estimate_stale - pointer_moved - no_draft_changes - conflict - idempotency_key_reused - rate_limited - model_unavailable description: Stable error code (same value as `code`). code: type: string enum: - validation_failed - invalid_parameter - approval_required - plan_limit - phi_mode_blocked - owner_required - not_entitled - forbidden - not_found - payload_too_large - estimate_stale - pointer_moved - no_draft_changes - conflict - idempotency_key_reused - rate_limited - model_unavailable description: Stable, machine-readable cause; match on this. message: type: string description: A plain-English sentence saying what is wrong. hint: type: string description: The next step to try. details: type: object additionalProperties: true description: >- Code-specific context, for example `approvalRequestId` with `approval_required` or `cap` with `plan_limit`. Error: type: object required: - error properties: error: type: string description: >- Short error name: `Unauthorized`, `Validation failed`, `Not found`, or a stable snake_case code you can match on, such as `unknown_query_parameter`, `invalid_parameter`, `payload_too_large` or `not_found`. message: type: string description: A plain-English sentence saying what is wrong and how to fix it. code: type: string description: >- Stable, machine-readable cause; match on this rather than on `error` or `message`. On a 401: `missing_credentials`, `malformed_credentials`, `ingest_key_not_allowed` (a write-only observability ingest key was used on an endpoint that needs an API key), `key_expired` or `invalid_credentials`. Elsewhere, for example: `not_found`, `invalid_parameter`, `unknown_query_parameter`, `missing_parameter`, `validation_failed`, `invalid_json`, `payload_too_large`, `conversation_not_found`, `plan_required`. hint: type: string description: >- The next step to try: where to find the right id, which parameters the endpoint takes, how to upgrade the plan, how to authenticate. parameter: type: string description: 'With `invalid_parameter`: the query parameter that was rejected.' unknown: type: array items: type: string description: >- With `unknown_query_parameter`: the parameters that were sent but are not accepted here. valid: type: array items: type: string description: >- With `unknown_query_parameter`: the parameters this endpoint accepts. details: type: object additionalProperties: true responses: ValidationFailed: description: >- The request body or query string failed validation. `code` says which kind (`validation_failed`, `invalid_json`, `invalid_parameter`, `unknown_query_parameter`, `missing_parameter`), and an enum filter names the allowed values in `valid` (every repeated value is checked, e.g. `?status=open&status=zz` is a 400). A `validation_failed` body also carries `message` (the first failing fields), `hint` (how to fix it, for example that a finding `description` is a TipTap JSON document and not a string) and `details` (field name to messages). content: application/json: schema: $ref: '#/components/schemas/Error' Unauthorized: description: >- Missing or invalid API key. The body names the cause in `code` (for example `ingest_key_not_allowed` when a write-only ingest key is used here) with a `message` and `hint`. content: application/json: schema: $ref: '#/components/schemas/Error' NotFound: description: >- Resource not found in your organization. Also returned when a path id is not a UUID, and `{ "error": "not_found" }` for a path this API does not have. The body keeps `error: "Not found"` and adds `code: "not_found"` and a `hint`. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearerAuth: type: http scheme: bearer description: >- Send `Authorization: Bearer YOUR_API_KEY`. The key resolves to a single organization. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.