> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zerogpu.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# deberta-v3-small

> Model details for deberta-v3-small.

> Microsoft's DeBERTa-v3-small is a fast, lightweight zero-shot text classifier for high-volume routing, filtering, and tagging. Hand it any text alongside your own candidate labels and it returns a confidence score for each. No training data and no fixed taxonomy, just the categories you define at request time. Because it scores every label rather than forcing one choice, you get soft probabilities to threshold, rank, or route on however your pipeline needs. Purpose-built and CPU-optimized, it runs faster and cheaper than asking a general-purpose frontier model to classify.

**References:** [Model docs](https://github.com/microsoft/DeBERTa/tree/master/docs) • [Terms](https://github.com/microsoft/DeBERTa/blob/master/SECURITY.md) • [Privacy](https://github.com/microsoft/DeBERTa/blob/master/LICENSE)


## OpenAPI

````yaml api-reference/openapi/playgrounds/deberta-v3-small.openapi.json POST /responses
openapi: 3.1.0
info:
  title: deberta-v3-small playground
  version: '1.0'
  description: >-
    Interactive playground for **deberta-v3-small**.

    Model is always `deberta-v3-small` on this page (shown in the form, not
    editable).

    Use the **request example** selector to switch use cases (JSON, NER, PII,
    etc.).

    Authentication: `x-api-key` (required) and `x-project-id` (optional).
servers:
  - url: https://api.zerogpu.ai/v1
    description: Production
security:
  - ApiKey: []
paths:
  /responses:
    post:
      tags:
        - deberta-v3-small
      summary: 'deberta-v3-small: Responses'
      operationId: createResponse_deberta-v3-small
      parameters:
        - name: x-project-id
          in: header
          required: false
          schema:
            type: string
          description: >-
            Optional project identifier. Scopes the request to a specific
            project when provided.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              allOf:
                - $ref: '#/components/schemas/CreateResponseRequest'
                - type: object
                  properties:
                    model:
                      type: string
                      const: deberta-v3-small
                      default: deberta-v3-small
                      example: deberta-v3-small
                      description: >-
                        Model identifier (fixed for this playground). Use
                        request examples to change use cases.
            examples:
              default:
                summary: Default
                value:
                  input: >-
                    Apple is expected to unveil its next-generation M5 chip at
                    WWDC this June, promising a 40% boost in GPU performance and
                    a new dedicated AI core for on-device machine learning
                    tasks.
                  model: deberta-v3-small
                  instructions: '[sports, finance, politics]'
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Response'
              examples:
                default:
                  summary: Default
                  value:
                    technology: 0.971784
                    politics: 0.011858
                    sports: 0.01175
                    finance: 0.004608
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '403':
          description: Forbidden
        '420':
          description: Insufficient quota
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal server error
components:
  schemas:
    CreateResponseRequest:
      type: object
      required:
        - model
        - input
      properties:
        model:
          type: string
          const: deberta-v3-small
          default: deberta-v3-small
          example: deberta-v3-small
          description: >-
            Model identifier (fixed for this playground). Use request examples
            to change use cases.
        input:
          type: string
          minLength: 1
          format: textarea
          maxLength: 131072
          description: Multi-line text or document content to send to the model.
        instructions:
          type: string
          example: '[sports, finance, politics]'
          description: >-
            Candidate categories for zero-shot classification, passed as a
            comma-separated array (e.g. `[sports, finance, politics]`). A
            maximum of 10 categories is supported; response time increases with
            the number of categories provided.
    Response:
      type: object
      additionalProperties: true
    ErrorResponse:
      type: object
      additionalProperties: true
  securitySchemes:
    ApiKey:
      type: apiKey
      in: header
      name: x-api-key

````