> ## Documentation Index > Fetch the complete documentation index at: https://docs.nugen.in/llms.txt > Use this file to discover all available pages before exploring further. # Update Inference Capture Settings > Turn capture on or off for your organisation. Send `enabled` to move the default, `models` to set per model exceptions, or both. Aligned models you do not mention keep the setting they already have. Whether Nugen keeps the instructions you send and the responses your aligned models return. Capture is off for every organisation until you turn it on, and it covers aligned models only. Base model traffic is never kept, and a base model id is rejected by this endpoint. Kept pairs become training data for `POST /api/v3/alignment-projects/{alignment_id}/auto-align`, so a model that gets used improves from that use. Turning capture off stops collection from the next request onwards and leaves already kept pairs in place. **Returns:** - `enabled`: your organisation's default - `models`: aligned models that differ from that default, keyed by model id ## OpenAPI ````yaml https://api.nugen.in/openapi-public.json patch /api/v3/inference/capture openapi: 3.1.0 info: title: Nugen Intelligence API description: >+ Nugen Intelligence: Powering Specialized Intelligence At Scale. **Need an API key?** Sign up, log in to the platform and generate an API key. **Need help?** Sign up, log in to the platform and raise a support ticket. **What this API does.** Align models to your domain corpus and run them with confidence. Train-time alignment builds domain-aligned adaptors through proprietary methods spanning pre-training, supervised and reinforcement stages. Inference-time alignment quantifies uncertainty across the full generation trajectory, producing confidence scores and keeping every response on domain. **Workflow.** Upload documents, create or generate a benchmark, create an alignment project, receive an aligned model id. That one id serves chat completions, completions, embeddings and reranking, and its embeddings carry your domain's representation space, making retrieval domain aware. You define the success criteria for your domain; the platform handles the deep learning, the GPUs and the data preparation. **Authentication.** Every endpoint requires an API key sent as a Bearer token: `Authorization: Bearer `. contact: name: Nugen Intelligence - Customer Support url: https://nugen.in/signup email: support@nugen.in version: 25.4.20 servers: - url: https://api.nugen.in description: Production security: [] paths: /api/v3/inference/capture: patch: tags: - Inference summary: Update Inference Capture Settings description: >- Turn capture on or off for your organisation. Send `enabled` to move the default, `models` to set per model exceptions, or both. Aligned models you do not mention keep the setting they already have. Whether Nugen keeps the instructions you send and the responses your aligned models return. Capture is off for every organisation until you turn it on, and it covers aligned models only. Base model traffic is never kept, and a base model id is rejected by this endpoint. Kept pairs become training data for `POST /api/v3/alignment-projects/{alignment_id}/auto-align`, so a model that gets used improves from that use. Turning capture off stops collection from the next request onwards and leaves already kept pairs in place. **Returns:** - `enabled`: your organisation's default - `models`: aligned models that differ from that default, keyed by model id operationId: update_inference_capture requestBody: content: application/json: schema: $ref: '#/components/schemas/InferenceCaptureRequest' required: true responses: '200': description: Returns the settings as they stand after the change. content: application/json: schema: $ref: '#/components/schemas/InferenceCaptureResponse' '400': description: Empty body, or a model id that is not an aligned model content: application/json: example: detail: >- not aligned models, so capture cannot apply to them: Qwen/Qwen2.5-0.5B-Instruct '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - HTTPBearer: [] components: schemas: InferenceCaptureRequest: properties: enabled: anyOf: - type: boolean - type: 'null' title: Enabled description: Org default for aligned model inference models: anyOf: - additionalProperties: type: boolean type: object - type: 'null' title: Models description: Per aligned model exceptions to the default, keyed by model_id examples: - model_01k4x9m2p7q3r9d1: true type: object title: InferenceCaptureRequest description: |- Send either field. enabled moves the org default, models merges the listed aligned models as exceptions to it. InferenceCaptureResponse: properties: enabled: type: boolean title: Enabled description: Org default, false unless it has been turned on models: additionalProperties: type: boolean type: object title: Models description: Aligned models that differ from the default type: object required: - enabled title: InferenceCaptureResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError 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 securitySchemes: HTTPBearer: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.