OpenAI-compatible inference API for Gradient Cloud — model listing, chat completion, and text completion (streaming and non-streaming) served across Gradient's distributed compute network. Authenticated with an access key (HTTP Bearer); the List Models endpoint is public.
openapi: 3.0.3
info:
title: Gradient Cloud AI 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
tags:
- name: Models
description: Model listing and management
- name: Chat
description: Chat completion
- name: Completions
description: Text completion
security:
- AccessKey: []
paths:
/ai/models:
get:
tags: [Models]
operationId: listModels
summary: List all models
description: List of all available AI models. No authentication required.
security: []
responses:
'200':
description: Success
content:
application/json:
schema:
$ref: '#/components/schemas/ModelList'
example:
object: list
data:
- id: qwen/qwen3-coder-480b-instruct-fp8
object: model
created: 1640995200
owned_by: qwen
permission: []
root: qwen/qwen3-coder-480b-instruct-fp8
parent: null
'500':
description: Internal Server Error
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
/ai/chat/completions:
post:
tags: [Chat]
operationId: createChatCompletion
summary: Chat completion
description: >-
Create a chat completion request, supporting both streaming and
non-streaming responses.
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
example:
model: qwen/qwen3-coder-480b-instruct-fp8
messages:
- role: user
content: Hello, how are you?
temperature: 0.7
max_tokens: 100
responses:
'200':
description: Success
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletion'
text/event-stream:
schema:
type: string
description: "Server-sent event stream of chat.completion.chunk objects, 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'
/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:
securitySchemes:
AccessKey:
type: http
scheme: bearer
description: "Access Key passed as `Authorization: Bearer <access-key>`."
schemas:
Model:
type: object
properties:
id: { type: string }
object: { type: string }
created: { type: integer }
owned_by: { type: string }
permission: { type: array, items: { type: object } }
root: { type: string }
parent: { type: string, nullable: true }
ModelList:
type: object
properties:
object: { type: string }
data:
type: array
items: { $ref: '#/components/schemas/Model' }
ChatMessage:
type: object
required: [role, content]
properties:
role: { type: string, enum: [system, user, assistant] }
content: { type: string }
ChatCompletionRequest:
type: object
required: [model, messages]
properties:
model: { type: string, description: The ID of the model to use }
messages:
type: array
items: { $ref: '#/components/schemas/ChatMessage' }
stream: { type: boolean, default: false }
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 }
stop:
oneOf:
- { type: string }
- { type: array, items: { type: string } }
presence_penalty: { type: number, default: 0, minimum: -2, maximum: 2 }
frequency_penalty: { type: number, default: 0, minimum: -2, maximum: 2 }
logit_bias: { type: object }
user: { type: string }
ChatCompletion:
type: object
properties:
id: { type: string }
object: { type: string }
created: { type: integer }
model: { type: string }
choices:
type: array
items:
type: object
properties:
index: { type: integer }
message: { $ref: '#/components/schemas/ChatMessage' }
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 }
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' }
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 }