OpenAI-compatible embeddings endpoint returning vector representations of text for retrieval, clustering, and semantic search, served by models such as Qwen3 Embedding.
openapi: 3.0.1
info:
title: Nscale Serverless Inference API
description: >-
OpenAI-compatible serverless inference API for Nscale. Provides chat
completions, text completions, embeddings, image generation, and model
discovery against open models (Llama, Qwen, DeepSeek, GPT OSS, Mistral,
Flux) served on Nscale GPU infrastructure. Authenticate with a Bearer API
key issued from the Nscale console.
termsOfService: https://www.nscale.com/legal/terms-of-service
contact:
name: Nscale Support
url: https://docs.nscale.com
version: '1.0'
servers:
- url: https://inference.api.nscale.com/v1
description: Serverless Inference API
security:
- bearerAuth: []
tags:
- name: Chat
description: OpenAI-compatible chat completions.
- name: Completions
description: OpenAI-compatible legacy text completions.
- name: Embeddings
description: Vector embeddings of text input.
- name: Images
description: Text-to-image generation.
- name: Models
description: Model catalog discovery.
paths:
/chat/completions:
post:
operationId: createChatCompletion
tags:
- Chat
summary: Create a chat completion
description: >-
Generates a chat completion response for the provided model and chat
history. Supports streaming via Server-Sent Events when stream is true.
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
responses:
'200':
description: A chat completion (or an SSE stream when stream=true).
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionResponse'
text/event-stream:
schema:
type: string
description: Server-Sent Events stream of ChatCompletionChunk objects.
'401':
$ref: '#/components/responses/Unauthorized'
'429':
$ref: '#/components/responses/RateLimited'
/completions:
post:
operationId: createCompletion
tags:
- Completions
summary: Create a completion
description: Generates a completion response for the provided model and prompt.
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionRequest'
responses:
'200':
description: A text completion.
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionResponse'
'401':
$ref: '#/components/responses/Unauthorized'
'429':
$ref: '#/components/responses/RateLimited'
/embeddings:
post:
operationId: createEmbedding
tags:
- Embeddings
summary: Create embeddings
description: >-
Returns a vector representation of a given input that can be consumed by
machine learning models and retrieval systems.
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingRequest'
responses:
'200':
description: A list of embedding vectors.
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingResponse'
'401':
$ref: '#/components/responses/Unauthorized'
'429':
$ref: '#/components/responses/RateLimited'
/images/generations:
post:
operationId: createImage
tags:
- Images
summary: Create an image
description: Creates one or more images based on the provided text prompt.
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ImageGenerationRequest'
responses:
'200':
description: The generated image(s).
content:
application/json:
schema:
$ref: '#/components/schemas/ImageGenerationResponse'
'401':
$ref: '#/components/responses/Unauthorized'
'429':
$ref: '#/components/responses/RateLimited'
/models:
get:
operationId: listModels
tags:
- Models
summary: List models
description: >-
Returns a list of serverless models available for inference, including
identifiers and metadata such as context length and pricing.
responses:
'200':
description: A list of available models.
content:
application/json:
schema:
$ref: '#/components/schemas/ModelList'
'401':
$ref: '#/components/responses/Unauthorized'
/models/{model}:
get:
operationId: retrieveModel
tags:
- Models
summary: Retrieve a model
description: Returns metadata for a single model by identifier.
parameters:
- name: model
in: path
required: true
description: The model identifier.
schema:
type: string
responses:
'200':
description: The requested model.
content:
application/json:
schema:
$ref: '#/components/schemas/Model'
'401':
$ref: '#/components/responses/Unauthorized'
'404':
description: Model not found.
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: >-
Nscale API key issued from the console, sent as
`Authorization: Bearer $NSCALE_API_KEY`.
responses:
Unauthorized:
description: Missing or invalid API key.
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
RateLimited:
description: Too many requests; back off and retry.
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
schemas:
ChatCompletionRequest:
type: object
required:
- model
- messages
properties:
model:
type: string
description: Model identifier, e.g. meta-llama/Llama-4-Scout-17B-16E-Instruct.
messages:
type: array
items:
$ref: '#/components/schemas/ChatMessage'
temperature:
type: number
format: float
minimum: 0
maximum: 2
default: 1
top_p:
type: number
format: float
minimum: 0
maximum: 1
default: 1
max_tokens:
type: integer
description: Maximum number of tokens to generate.
stream:
type: boolean
default: false
description: If true, partial deltas are sent as Server-Sent Events.
stop:
oneOf:
- type: string
- type: array
items:
type: string
frequency_penalty:
type: number
format: float
minimum: -2
maximum: 2
default: 0
presence_penalty:
type: number
format: float
minimum: -2
maximum: 2
default: 0
tools:
type: array
items:
type: object
tool_choice:
oneOf:
- type: string
- type: object
ChatMessage:
type: object
required:
- role
- content
properties:
role:
type: string
enum:
- system
- user
- assistant
- tool
content:
description: Text content or an array of multimodal content parts.
oneOf:
- type: string
- type: array
items:
type: object
name:
type: string
ChatCompletionResponse:
type: object
properties:
id:
type: string
object:
type: string
example: chat.completion
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
max_tokens:
type: integer
temperature:
type: number
format: float
top_p:
type: number
format: float
stream:
type: boolean
default: false
stop:
oneOf:
- type: string
- type: array
items:
type: string
CompletionResponse:
type: object
properties:
id:
type: string
object:
type: string
example: text_completion
created:
type: integer
model:
type: string
choices:
type: array
items:
type: object
properties:
index:
type: integer
text:
type: string
finish_reason:
type: string
usage:
$ref: '#/components/schemas/Usage'
EmbeddingRequest:
type: object
required:
- model
- input
properties:
model:
type: string
description: Embedding model identifier, e.g. Qwen/Qwen3-Embedding-8B.
input:
description: Text or array of text to embed.
oneOf:
- type: string
- type: array
items:
type: string
encoding_format:
type: string
enum:
- float
- base64
default: float
EmbeddingResponse:
type: object
properties:
object:
type: string
example: list
data:
type: array
items:
type: object
properties:
object:
type: string
example: embedding
index:
type: integer
embedding:
type: array
items:
type: number
format: float
model:
type: string
usage:
$ref: '#/components/schemas/Usage'
ImageGenerationRequest:
type: object
required:
- model
- prompt
properties:
model:
type: string
description: Image model identifier, e.g. BlackForestLabs/FLUX.1-schnell.
prompt:
type: string
n:
type: integer
default: 1
description: Number of images to generate.
size:
type: string
description: Output dimensions, e.g. 1024x1024.
response_format:
type: string
enum:
- url
- b64_json
default: b64_json
num_inference_steps:
type: integer
description: Number of diffusion steps (affects per-megapixel cost).
ImageGenerationResponse:
type: object
properties:
created:
type: integer
data:
type: array
items:
type: object
properties:
url:
type: string
b64_json:
type: string
ModelList:
type: object
properties:
object:
type: string
example: list
data:
type: array
items:
$ref: '#/components/schemas/Model'
Model:
type: object
properties:
id:
type: string
object:
type: string
example: model
created:
type: integer
owned_by:
type: string
context_length:
type: integer
pricing:
type: object
description: Per-1M-token pricing metadata where exposed.
additionalProperties: true
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