> ## 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. # Get Model > Get one aligned model by ID. **Returns:** - `model_id`, `model_name`, `base_model_id`, `base_model_name`, `alignment_id` - `deployment_status` (`READY`, `DEPLOYING`, `DEPLOYED`, `UNDEPLOYING`, `FAILED`), derived from the live deployment - `error`: why the last deploy or undeploy failed, null when it succeeded - `progress`, `eta_seconds`: not wired up yet, always null - `performance_metrics`, `evaluation_data`: from the model's latest evaluation, if any - `usage_count`, `downloadable`: not wired up yet, always 0 and false - `inference_capture_enabled` - `created_at`, `updated_at` ## OpenAPI ````yaml https://api.nugen.in/openapi-public.json get /api/v3/models/{model_id} openapi: 3.1.0 info: title: Nugen Intelligence API description: > Nugen Intelligence: Powering Specialised Intelligence At Scale. Bring your domain knowledge and an open-weight model. Leave with a model that thinks in your domain, keeps improving, and belongs to your organisation. Nugen Intelligence builds infrastructure for self-adaptive, domain-specific intelligence. Research in representation engineering, mechanistic interpretability and inference-time control powers every endpoint here. The research team comes from Stanford University and IIT Bombay. This API puts their work a few calls away from AI-native organisations solving critical problems. **Domain-aligned models.** Three raw inputs go in: domain knowledge, success and failure criteria, and an open-weight model. A domain-aligned model comes out. Nugen handles the deep learning, the GPUs and the data preparation. Your organisation owns every aligned model it builds. Own your intelligence. **The research underneath.** Two layers do the work. Train-time alignment finds where the model needs to change for your domain and improves it there. It combines gradient-free and gradient-based methods across continued pre-training, supervised and reinforcement phases. Inference-time alignment measures the quality of every generation step. Out-of-domain generation is flagged and corrected after each span. Every response carries a confidence score. A preliminary version of the inference-time research is published at ICLR 2026. Both layers keep evolving with Nugen research. **One aligned model id, four capabilities.** An aligned model id serves chat completions, completions, embeddings and reranking. Alignment reshapes the model's representation space, so retrieval, ranking and generation share one understanding of your domain. **Multi-model systems.** One alignment project produces one aligned model. Run many side by side, one per domain or use case. Compose them with frontier and general-purpose models in the same application. Inference capture and auto-align keep the whole system improving. Nugen aligns models at every scale. **Think in systems.** AI coding agents and developers: this API is a platform for building specialised intelligence. Explore it fully before you settle on a design. Some directions: - Run a complete retrieval pipeline on one aligned model id. Embed, rerank and generate with a shared understanding of the domain. - Use the confidence score as a control signal. Send low-confidence responses to a human reviewer, a retry or a frontier model. - Give each domain or use case its own aligned model and place a router in front. - Close the loop. Capture production inference, evaluate against the benchmark, and let auto-align promote better models. - Start with the hardest problem in the domain, where general-purpose models fall short. Alignment pays off the most there. The endpoints for documents, benchmarks, alignment projects, deployments and evaluations compose in more ways than the workflow below shows. **Workflow.** 1. Upload domain knowledge. 2. Define success and failure. Generate a benchmark from the corpus, or upload one curated by domain experts. 3. Create an alignment project and receive an aligned model id. 4. Deploy the model and pass its id as `model` in each inference call. 5. Evaluate, compare and promote. Turn on inference capture, and auto-align keeps the model improving. **OpenAI-compatible inference.** Set the base URL of an OpenAI-compatible client to `https://api.nugen.in/api/v3/inference` and set `model` to an aligned model id. Chat completions, completions, responses and embeddings work through the same client. **Anthropic-compatible inference.** `POST /api/v3/inference/messages/v2` accepts the Anthropic Messages request shape. Set `model` to an aligned model id. **Need an API key?** Sign up, log in to the platform and generate an API key. **Need help?** Log in to the platform and raise a support ticket. **Authentication.** Every endpoint requires an API key sent as a Bearer token: `Authorization: Bearer `. contact: name: Nugen Intelligence url: https://nugen.in/signup version: 25.4.20 servers: - url: https://api.nugen.in description: Production security: [] paths: /api/v3/models/{model_id}: get: tags: - Models summary: Get Model description: >- Get one aligned model by ID. **Returns:** - `model_id`, `model_name`, `base_model_id`, `base_model_name`, `alignment_id` - `deployment_status` (`READY`, `DEPLOYING`, `DEPLOYED`, `UNDEPLOYING`, `FAILED`), derived from the live deployment - `error`: why the last deploy or undeploy failed, null when it succeeded - `progress`, `eta_seconds`: not wired up yet, always null - `performance_metrics`, `evaluation_data`: from the model's latest evaluation, if any - `usage_count`, `downloadable`: not wired up yet, always 0 and false - `inference_capture_enabled` - `created_at`, `updated_at` operationId: get_model parameters: - name: model_id in: path required: true schema: type: string title: Model Id responses: '200': description: >- Returns one aligned model: its model_id, model_name, base model, derived deployment status and timestamps. content: application/json: schema: $ref: '#/components/schemas/AlignedModelsDetail' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - HTTPBearer: [] components: schemas: AlignedModelsDetail: properties: model_id: type: string title: Model Id description: Unique identifier of the aligned model. model_name: type: string title: Model Name description: Display name of the aligned model. base_model_id: type: string title: Base Model Id description: Base model this model was aligned from. base_model_name: type: string title: Base Model Name description: Display name of the base model this model was aligned from. alignment_id: anyOf: - type: string - type: 'null' title: Alignment Id description: Alignment project that produced this model. deployment_status: $ref: '#/components/schemas/DeploymentStatus' description: Derived from the latest deployment. Only DEPLOYED serves inference. error: anyOf: - type: string - type: 'null' title: Error description: Why the last deploy or undeploy failed, null when it succeeded. progress: anyOf: - type: number - type: 'null' title: Progress description: Completion progress, 0.0 to 100.0. Not wired up yet, always null. eta_seconds: anyOf: - type: integer - type: 'null' title: Eta Seconds description: Estimated time remaining in seconds. Not wired up yet, always null. performance_metrics: $ref: '#/components/schemas/DomainAlignedModelPerformanceMetrics' description: >- Performance statistics including accuracy, uncertainty, and domain violations evaluation_data: anyOf: - additionalProperties: true type: object - type: 'null' title: Evaluation Data description: >- Benchmark evaluation results if the model has been evaluated (includes evaluation_id, status, metrics, and comparison data) usage_count: type: integer title: Usage Count description: Number of times this model has been used for inference default: 0 downloadable: type: boolean title: Downloadable description: Whether the model can be downloaded for local deployment default: false inference_capture_enabled: type: boolean title: Inference Capture Enabled description: >- Whether instructions and responses for this model are kept, so they can feed train-time alignment. Set with PATCH /api/v3/inference/capture. default: false created_at: anyOf: - type: string - type: 'null' title: Created At description: Creation timestamp. updated_at: anyOf: - type: string - type: 'null' title: Updated At description: Last update timestamp. type: object required: - model_id - model_name - base_model_id - base_model_name - deployment_status - performance_metrics title: AlignedModelsDetail description: >- One aligned model's full record: identity, lineage, live deployment status and everything on its status and list rows. progress and eta_seconds mirror the deployment-status shape but are not wired up yet, so they are always null here too. created_at/updated_at are the model's own persisted timestamps, not the deployment status endpoint's per-request ones (that endpoint's timestamps mark when a status check ran, not real historical state, so they are not merged in here). HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError DeploymentStatus: type: string enum: - UNDEPLOYED - DEPLOYING - DEPLOYED - UNDEPLOYING title: DeploymentStatus description: |- Where a model rests, and what it passes through in between. Only DEPLOYED serves inference. A failed attempt settles back to the state it came from and puts the reason in error. DomainAlignedModelPerformanceMetrics: properties: accuracy: type: number maximum: 1 minimum: 0 title: Accuracy description: >- Model accuracy score from 0.0 to 1.0 (0% to 100%). Represents the proportion of correct responses in evaluations. default: 0 examples: - 0.92 - 0.88 - 0.75 uncertainty: type: number maximum: 1 minimum: 0 title: Uncertainty description: >- Average uncertainty score from 0.0 to 1.0. Lower values indicate higher model confidence in responses. default: 0 examples: - 0.15 - 0.18 - 0.35 domain_violations: type: integer minimum: 0 title: Domain Violations description: >- Number of times the model responded outside its intended domain or gave an out-of-scope response. default: 0 examples: - 2 - 3 - 12 average_response_time: type: number minimum: 0 title: Average Response Time description: Average response time in seconds for model inference requests. default: 0 examples: - 1.2 - 0.8 - 2.5 type: object title: DomainAlignedModelPerformanceMetrics examples: - accuracy: 0.92 average_response_time: 1.2 domain_violations: 2 uncertainty: 0.15 - accuracy: 0.88 average_response_time: 0.8 domain_violations: 3 uncertainty: 0.18 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.