openapi: 3.0.3 info: title: Gradient Cloud AI Chat Completions API version: v1 description: OpenAI-compatible inference API for Gradient Cloud — the enterprise inference service of Gradient's Open Intelligence Stack, serving open models across a distributed compute network (Parallax) over Gradient's peer-to-peer data motion engine (Lattica). The API implements OpenAI-compatible interfaces for model listing, chat completion, and text completion (streaming and non-streaming). Generated by the API Evangelist enrichment pipeline from the provider's published API Reference Documentation; not an official provider OpenAPI. Verify against the live docs before production use. contact: name: Gradient url: https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation x-apievangelist-generated: true x-apievangelist-source: https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation.md servers: - url: https://apis.gradient.network/api/v1 description: Gradient Cloud production security: - AccessKey: [] tags: - name: Completions description: Text completion paths: /ai/completions: post: tags: - Completions operationId: createCompletion summary: Text completion description: Create a text completion request, supporting both streaming and non-streaming responses. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CompletionRequest' example: model: qwen/qwen3-coder-480b-instruct-fp8 prompt: Once upon a time temperature: 0.7 max_tokens: 100 responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/Completion' text/event-stream: schema: type: string description: 'Server-sent event stream, terminated by `data: [DONE]`.' '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' '402': description: Billing Check Failed content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: Model Not Found content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Rate Limit Exceeded content: application/json: schema: $ref: '#/components/schemas/Error' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: Usage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer Error: type: object properties: error: type: object properties: message: type: string type: type: string code: type: string Completion: type: object properties: id: type: string object: type: string created: type: integer model: type: string choices: type: array items: type: object properties: text: type: string index: type: integer finish_reason: type: string usage: $ref: '#/components/schemas/Usage' CompletionRequest: type: object required: - model - prompt properties: model: type: string prompt: oneOf: - type: string - type: array items: type: string suffix: type: string max_tokens: type: integer temperature: type: number default: 1 minimum: 0 maximum: 2 top_p: type: number default: 1 minimum: 0 maximum: 1 n: type: integer default: 1 stream: type: boolean default: false securitySchemes: AccessKey: type: http scheme: bearer description: 'Access Key passed as `Authorization: Bearer `.'