> ## 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.

# Generate Responses

> OpenAI `responses.create` compatible endpoint.

Accepts the same shape as `openai.responses.create` and returns a `Response` object.


**Request Body:**

- `model`: Model ID (required)
- `input`: User input — a plain string or array of `{"role": "system"|"user"|"assistant", "content": ...}` objects
- `instructions` (optional): System-level instructions (maps to a system message prepended to `input`)
- `max_output_tokens` (optional): Maximum tokens to generate
- `temperature` (optional): Sampling temperature 0–2 (default: 1.0)
- `top_p` (optional): Nucleus sampling parameter
- `stream` (optional): Stream partial output as SSE (default: true). Passing `null` is treated as `true`. Set `stream: false` for a single JSON response — the call must complete within the timeout or returns 504. For long generations, keep streaming on.

**Example Request:**

```json
POST /api/v3/inference/responses
Headers: {"Authorization": "Bearer <api_key>"}

{
  "model": "Qwen/Qwen2.5-0.5B-Instruct",
  "input": "What is the capital of France?",
  "instructions": "You are a helpful assistant.",
  "max_output_tokens": 200,
  "stream": false
}
```

**Example Response:**

```json
{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1704123600,
  "model": "Qwen/Qwen2.5-0.5B-Instruct",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [{"type": "output_text", "text": "The capital of France is Paris."}]
    }
  ],
  "usage": {"input_tokens": 18, "output_tokens": 9, "total_tokens": 27}
}
```

**Example Streaming Request (`stream: true`):**

```json
{
  "model": "Qwen/Qwen2.5-0.5B-Instruct",
  "input": "Write a short poem about the sea.",
  "stream": true
}
```

Streaming response (SSE):
```
data: {"type": "response.output_text.delta", "delta": "The sea is"}
data: {"type": "response.output_text.delta", "delta": " vast and deep,"}
data: {"type": "response.completed", "usage": {"input_tokens": 12, "output_tokens": 8, "total_tokens": 20}}
```



## OpenAPI

````yaml https://api.nugen.in/openapi-public.json post /api/v3/inference/responses
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, three capabilities.** An aligned model id serves
    chat 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, 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.


    **List responses.** Each list endpoint names its array after the resource,
    for example `documents`, `benchmarks`, `alignment_projects`, `evaluations`
    and `domain_aligned_models`. The lists of documents, benchmarks, alignment
    projects and evaluations accept `limit` and `offset` and return `total`,
    `limit` and `offset`.


    **Resource ids.** Treat every id as an opaque string. Ids issued earlier can
    differ in letter case from newer ones. Pass an id back exactly as the API
    returned it.


    **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 <api_key>`.
  contact:
    name: Nugen Intelligence
    url: https://nugen.in/signup
  version: 26.11.16
servers:
  - url: https://api.nugen.in
    description: Production
security: []
tags:
  - name: Alignment Projects
    description: >-
      Create, monitor, stop and delete alignment projects that fine-tune a base
      model on your documents
  - name: BYOC
    description: Bring Your Own Cloud model deployment
  - name: Benchmarks
    description: Upload or create benchmarks and read their questions and status
  - name: Documents
    description: Upload documents and track their processing
  - name: Evaluations
    description: Evaluate a model on a benchmark and read the results
  - name: Inference
    description: Chat completions, responses, embeddings and reranking
  - name: Models
    description: >-
      List base and aligned models, deploy or undeploy aligned models, import
      base models and export to Hugging Face
paths:
  /api/v3/inference/responses:
    post:
      tags:
        - Inference
      summary: Generate Responses
      description: >-
        OpenAI `responses.create` compatible endpoint.


        Accepts the same shape as `openai.responses.create` and returns a
        `Response` object.



        **Request Body:**


        - `model`: Model ID (required)

        - `input`: User input — a plain string or array of `{"role":
        "system"|"user"|"assistant", "content": ...}` objects

        - `instructions` (optional): System-level instructions (maps to a system
        message prepended to `input`)

        - `max_output_tokens` (optional): Maximum tokens to generate

        - `temperature` (optional): Sampling temperature 0–2 (default: 1.0)

        - `top_p` (optional): Nucleus sampling parameter

        - `stream` (optional): Stream partial output as SSE (default: true).
        Passing `null` is treated as `true`. Set `stream: false` for a single
        JSON response — the call must complete within the timeout or returns
        504. For long generations, keep streaming on.


        **Example Request:**


        ```json

        POST /api/v3/inference/responses

        Headers: {"Authorization": "Bearer <api_key>"}


        {
          "model": "Qwen/Qwen2.5-0.5B-Instruct",
          "input": "What is the capital of France?",
          "instructions": "You are a helpful assistant.",
          "max_output_tokens": 200,
          "stream": false
        }

        ```


        **Example Response:**


        ```json

        {
          "id": "resp_abc123",
          "object": "response",
          "created_at": 1704123600,
          "model": "Qwen/Qwen2.5-0.5B-Instruct",
          "output": [
            {
              "type": "message",
              "role": "assistant",
              "content": [{"type": "output_text", "text": "The capital of France is Paris."}]
            }
          ],
          "usage": {"input_tokens": 18, "output_tokens": 9, "total_tokens": 27}
        }

        ```


        **Example Streaming Request (`stream: true`):**


        ```json

        {
          "model": "Qwen/Qwen2.5-0.5B-Instruct",
          "input": "Write a short poem about the sea.",
          "stream": true
        }

        ```


        Streaming response (SSE):

        ```

        data: {"type": "response.output_text.delta", "delta": "The sea is"}

        data: {"type": "response.output_text.delta", "delta": " vast and deep,"}

        data: {"type": "response.completed", "usage": {"input_tokens": 12,
        "output_tokens": 8, "total_tokens": 20}}

        ```
      operationId: inference_responses
      parameters:
        - name: X-Session-ID
          in: header
          required: false
          schema:
            anyOf:
              - type: string
              - type: 'null'
            title: X-Session-Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ResponsesCreateRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResponsesCreateResponse'
            text/event-stream:
              schema:
                $ref: '#/components/schemas/ResponsesStreamEvent'
                description: >-
                  Server-sent events. Each data line is one JSON event, and the
                  stream closes after the response.completed event.
        '401':
          description: Invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Authorization header missing or not a Bearer token
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
        '429':
          description: Base model rate limit exceeded
          headers:
            Retry-After:
              description: Seconds to wait before retrying
              schema:
                type: integer
          content:
            application/json:
              example:
                detail: >-
                  Base model rate limit of 10 requests/minute reached. Use your
                  aligned model for higher throughput.
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '504':
          description: >-
            A non-streaming call did not finish before the deadline. Set stream
            to true for long generations.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security:
        - ApiKeyAuth: []
components:
  schemas:
    ResponsesCreateRequest:
      properties:
        model:
          type: string
          title: Model
          description: Model ID to use for the response
          examples:
            - model_01kmqm4nrn9fw6r
        input:
          anyOf:
            - type: string
            - items:
                $ref: '#/components/schemas/ResponsesInputMessage'
              type: array
          title: Input
          description: >-
            Input to the model — either a plain string or an array of message
            objects with "role" (system, user, or assistant) and "content"
        instructions:
          anyOf:
            - type: string
            - type: 'null'
          title: Instructions
          description: System-level instructions (maps to system message)
        max_output_tokens:
          anyOf:
            - type: integer
            - type: 'null'
          title: Max Output Tokens
          description: Maximum tokens to generate
        temperature:
          anyOf:
            - type: number
              maximum: 2
              minimum: 0
            - type: 'null'
          title: Temperature
          description: Sampling temperature
          default: 1
        top_p:
          anyOf:
            - type: number
            - type: 'null'
          title: Top P
          description: Nucleus sampling parameter
        stream:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Stream
          description: >-
            Stream partial output as server-sent events. Defaults to true; null
            means true. Set false for one JSON response, which must complete
            within 50 seconds or the call answers 504. Use true for long
            generations.
          default: true
        metadata:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          title: Metadata
          description: Optional metadata, ignored by the model
      type: object
      required:
        - model
        - input
      title: ResponsesCreateRequest
      description: A request in the OpenAI Responses API compatible format.
    ResponsesCreateResponse:
      properties:
        id:
          type: string
          title: Id
          description: Unique identifier of the response
          examples:
            - resp_9f2c1a7b3d4e5f60718293a4
        object:
          type: string
          const: response
          title: Object
          description: Always "response".
          default: response
        created_at:
          type: integer
          title: Created At
          description: Unix time in seconds when the response was created
        model:
          type: string
          title: Model
          description: Model used for the response
        output:
          items:
            $ref: '#/components/schemas/ResponsesOutputMessage'
          type: array
          title: Output
          description: Generated output messages
        usage:
          $ref: '#/components/schemas/ResponsesUsage'
          description: Token usage
      type: object
      required:
        - id
        - created_at
        - model
        - output
        - usage
      title: ResponsesCreateResponse
      description: A response in the Responses format.
    ResponsesStreamEvent:
      description: >-
        One server-sent event of a streamed response. Text arrives as
        response.output_text.delta events, and a final response.completed event
        carries the usage. The stream then closes.
      properties:
        type:
          description: Event kind
          enum:
            - response.output_text.delta
            - response.completed
          title: Type
          type: string
        delta:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          description: Text fragment, set on response.output_text.delta events
          title: Delta
        usage:
          anyOf:
            - $ref: '#/components/schemas/ResponsesUsage'
            - type: 'null'
          default: null
          description: Token counts, set on the response.completed event
      required:
        - type
      title: ResponsesStreamEvent
      type: object
    ErrorResponse:
      description: Body of an error response.
      properties:
        detail:
          anyOf:
            - type: string
            - $ref: '#/components/schemas/ErrorDetail'
          description: >-
            Human readable explanation of the error, or an object with a message
            and the id of the resource concerned
          examples:
            - Model not found
          title: Detail
      required:
        - detail
      title: ErrorResponse
      type: object
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
      description: Body of a request validation error.
    ResponsesInputMessage:
      properties:
        role:
          type: string
          enum:
            - system
            - user
            - assistant
          title: Role
          description: Message role
        content:
          anyOf:
            - type: string
            - items:
                additionalProperties: true
                type: object
              type: array
          title: Content
          description: Message content
      type: object
      required:
        - role
        - content
      title: ResponsesInputMessage
      description: A message in the input array of a Responses API request.
    ResponsesOutputMessage:
      properties:
        type:
          type: string
          const: message
          title: Type
          description: Always "message".
          default: message
        role:
          type: string
          const: assistant
          title: Role
          description: Always "assistant".
          default: assistant
        content:
          items:
            $ref: '#/components/schemas/ResponsesOutputText'
          type: array
          title: Content
          description: Generated content parts
      type: object
      required:
        - content
      title: ResponsesOutputMessage
      description: A message in the output of a response.
    ResponsesUsage:
      description: Token counts for a response.
      properties:
        input_tokens:
          type: integer
          title: Input Tokens
          description: Tokens in the input
        output_tokens:
          type: integer
          title: Output Tokens
          description: Tokens generated
        total_tokens:
          description: Input plus output tokens
          title: Total Tokens
          type: integer
      required:
        - input_tokens
        - output_tokens
        - total_tokens
      title: ResponsesUsage
      type: object
    ErrorDetail:
      additionalProperties: true
      description: >-
        Structured error detail: a message, with the id of the resource it
        concerns as an extra key.
      properties:
        message:
          description: Human readable explanation of the error
          title: Message
          type: string
      required:
        - message
      title: ErrorDetail
      type: object
    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
      description: One request validation problem.
    ResponsesOutputText:
      properties:
        type:
          type: string
          const: output_text
          title: Type
          description: Always "output_text".
          default: output_text
        text:
          type: string
          title: Text
          description: Generated text
      type: object
      required:
        - text
      title: ResponsesOutputText
      description: A piece of text in a response message.
  securitySchemes:
    ApiKeyAuth:
      type: http
      description: Your Nugen API key, sent as a Bearer token
      scheme: bearer
      bearerFormat: API key

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.