> ## 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. # Set the model a monitor runs on > Puts the monitor's AI stages on the platform model (`{ "provider": "bedrock", "modelTier"? }`) or on one of the organization's AI provider keys (`{ "aiKeyId", "model" }`). The monitor references the key, so rotating it applies at once. A different provider or model bumps the monitor version and resets its alert; another key of the same provider does not. Usage on an organization key is billed by the provider plus Zelto's bring-your-own platform fee, not the plan's evaluation allowance. Owner or admin only; an organization key is refused in PHI mode. The same operation as the `set_monitor_model` MCP tool. ## OpenAPI ````yaml /docs-openapi.json put /v1/monitors/{id}/model 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. paths: /v1/monitors/{id}/model: parameters: - name: id in: path required: true schema: type: string format: uuid put: tags: - Monitors summary: Set the model a monitor runs on description: >- Puts the monitor's AI stages on the platform model (`{ "provider": "bedrock", "modelTier"? }`) or on one of the organization's AI provider keys (`{ "aiKeyId", "model" }`). The monitor references the key, so rotating it applies at once. A different provider or model bumps the monitor version and resets its alert; another key of the same provider does not. Usage on an organization key is billed by the provider plus Zelto's bring-your-own platform fee, not the plan's evaluation allowance. Owner or admin only; an organization key is refused in PHI mode. The same operation as the `set_monitor_model` MCP tool. operationId: setMonitorModel requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/MonitorModelSet' responses: '200': description: The model the monitor now runs on. content: application/json: schema: $ref: '#/components/schemas/MonitorModel' '400': description: >- `invalid_input` (neither body shape), `provider_pipeline_unsupported` (the monitor's stages aren't supported by the selected evaluator, such as TypeSafe), or `invalid_json`. content: application/json: schema: $ref: '#/components/schemas/Error' '401': $ref: '#/components/responses/Unauthorized' '403': description: >- Not an owner or admin (`{ "error": "Owner or admin access required" }`), or `phi_mode_blocked`: the organization is in PHI mode. content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: >- `not_found` (no such monitor in this organization) or `ai_key_not_found` (no such key, or it isn't an LLM key). content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: MonitorModelSet: description: >- Either the platform model (optionally a tier) or one of the organization's AI provider keys plus that provider's model id. oneOf: - type: object title: Platform model additionalProperties: false required: - provider properties: provider: type: string const: bedrock modelTier: type: string enum: - fast - balanced - advanced description: Defaults to `fast`. - type: object title: Organization AI provider key additionalProperties: false required: - aiKeyId - model properties: aiKeyId: type: string format: uuid description: >- An OpenAI, Anthropic, OpenRouter, Vercel AI Gateway or TypeSafe key from `GET /v1/ai-keys`. model: type: string minLength: 1 maxLength: 200 description: >- The provider's own model id, such as `gpt-5`, `claude-sonnet-4-5`, `anthropic/claude-sonnet-4.5` or `jev-latest`. MonitorModel: type: object required: - monitorId - provider - model - aiKeyId - version - versionChanged properties: monitorId: type: string format: uuid provider: type: string enum: - bedrock - openai - anthropic - openrouter - vercel_gateway - typesafe description: >- `bedrock` is the platform model; anything else is the provider of the organization key. model: type: string description: The tier for `bedrock`, otherwise the provider's model id. aiKeyId: type: - string - 'null' format: uuid description: >- The organization key the monitor runs on, or `null` for the platform model. version: type: integer description: The monitor's version after the change. versionChanged: type: boolean description: >- `true` when the provider or model changed, which opens a new version and resets the monitor's alert. Switching to another key of the same provider keeps the version. 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: 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' 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.