Novita AI

Novita AI is an AI inference cloud offering serverless LLM, image, video, and audio generation APIs alongside on-demand GPU rentals and serverless GPU endpoints. Hosts open-source models with both native and OpenAI-compatible chat surfaces, plus an agent sandbox and MCP server for tool-using agents.

2 APIs 0 Features

AILLMInferenceGPUOpenAI CompatibleImage GenerationVideo GenerationAudioEmbeddingsSandboxMCP

APIs

Novita AI Platform API

LLM chat completions (OpenAI-compatible), embeddings, reranking, batch, image generation (FLUX.1, Seedream 3.0/4.0, Qwen), image editing (upscale, background removal/replacement...

Novita AI GPU API

On-demand GPU instance management and templates plus serverless GPU endpoints. Create, start, stop, and delete instances; list products and templates; query usage-based and fixe...

Collections

Novita API

OPEN

Pricing Plans

Novita Ai Plans Pricing

1 plans

PLANS

Rate Limits

Novita Ai Rate Limits

1 limits

RATE LIMITS

FinOps

Novita Ai Finops

FINOPS

Event Specifications

Novita AI Streaming & Webhook API

AsyncAPI 2.6 description of the asynchronous surfaces of the Novita AI platform: 1. **Server-Sent Events (SSE) streaming** for OpenAI-compatible chat completions (`POST /openai/...

ASYNCAPI

Resources

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Novita API
  version: 1.0.0
items:
- info:
    name: List models
    type: http
  http:
    method: GET
    url: https://api.novita.ai/openai/v1/models
  docs: List available OpenAI-compatible models.
- info:
    name: Create chat completion
    type: http
  http:
    method: POST
    url: https://api.novita.ai/openai/v1/chat/completions
  docs: Create an OpenAI-compatible chat completion.
- info:
    name: Create completion
    type: http
  http:
    method: POST
    url: https://api.novita.ai/openai/v1/completions
  docs: Create an OpenAI-compatible text completion.
- info:
    name: Create embeddings
    type: http
  http:
    method: POST
    url: https://api.novita.ai/openai/v1/embeddings
  docs: Create OpenAI-compatible embeddings.
bundled: true