GradientJ API

openapi: 3.1.0
info:
  title: GradientJ API
  version: '2026-10-20'
  description: 'GENERATED FROM DOCUMENTATION by API Evangelist on 2026-10-20: 3 operation(s) read from 2 public documentation page(s) (each operation
    names its page in x-source). This is not the provider''s published contract; GradientJ has published no machine-readable contract that the
    pipeline could find. Engine: local.'
  x-evidence-tiers:
    code-example: 0
    documentation: 3
    pages-with-code: 0
    pages-read: 2
  x-generated-from: documentation
  x-provenance: generated
  x-authored-by: API Evangelist
  x-generated: '2026-10-20'
  x-generator: generate-contract-from-docs.py
  x-engine: local
  x-sources:
  - https://docs.gradientj.com/deployment/batch-api
  - https://docs.gradientj.com/deployment/inference-api
servers:
- url: https://api.sandbox.gradientj.com
paths:
  /api/v0/deploy/check-batch-inference:
    post:
      operationId: post_api_v0_deploy_check_batch_inference
      tags:
      - Api
      summary: Check the status of an existing batch inference job
      x-source: https://docs.gradientj.com/deployment/batch-api
      parameters:
      - name: x-api-key
        in: header
        required: true
        schema:
          type: string
        description: API key
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostApiV0DeployCheckBatchInferenceRequest'
      responses:
        '200':
          description: Success (status as documented)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PostApiV0DeployCheckBatchInferenceResponse'
      x-evidence:
        kind: documentation
  /api/v0/deploy/create-batch-inference:
    post:
      operationId: post_api_v0_deploy_create_batch_inference
      tags:
      - Api
      summary: Create a new batch inference job
      x-source: https://docs.gradientj.com/deployment/batch-api
      parameters:
      - name: x-api-key
        in: header
        required: true
        schema:
          type: string
        description: API key
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostApiV0DeployCreateBatchInferenceRequest'
      responses:
        '200':
          description: Success (status as documented)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PostApiV0DeployCreateBatchInferenceResponse'
      x-evidence:
        kind: documentation
  /api/v0/deploy/inference:
    post:
      operationId: post_api_v0_deploy_inference
      tags:
      - Api
      summary: Run inference on a model deployment
      x-source: https://docs.gradientj.com/deployment/inference-api
      parameters:
      - name: x-api-key
        in: header
        required: true
        schema:
          type: string
        description: API key for authentication
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostApiV0DeployInferenceRequest'
      responses:
        '200':
          description: Success (status as documented)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PostApiV0DeployInferenceResponse'
      x-evidence:
        kind: documentation
components:
  schemas:
    PostApiV0DeployCheckBatchInferenceRequest:
      type: object
      properties:
        batch_id:
          type: string
          description: The UUID of the batch job to check.
      required:
      - batch_id
    PostApiV0DeployCheckBatchInferenceResponse:
      type: object
      properties:
        result:
          type: object
          description: Batch job status and results if completed.
    PostApiV0DeployCreateBatchInferenceRequest:
      type: object
      properties:
        model:
          type: string
          description: The UUID of the model to be used for the inference job.
        batches:
          type: object
          description: A list of batches containing inference parameters and chat history.
      required:
      - model
      - batches
    PostApiV0DeployCreateBatchInferenceResponse:
      type: object
      properties:
        result:
          type: object
          description: Batch job details.
    PostApiV0DeployInferenceRequest:
      type: object
      properties:
        model:
          type: string
          description: The UUID of the model to be used for inference.
        deployment_version:
          type: string
          description: The ID of the specific deployment version to use. If not provided, the default version will be used.
        params:
          type: object
          description: Parameters for the inference job.
        chat_history:
          type: array
          description: Optional chat history to provide context for chat-based models.
      required:
      - model
      - params
    PostApiV0DeployInferenceResponse:
      type: object
      properties:
        result:
          type: object
          description: The response object containing the inference results.
tags:
- name: Api