Skip to main content

Documentation Index

Fetch the complete documentation index at: https://doc.hitopen.com/llms.txt

Use this file to discover all available pages before exploring further.

Newapi gives you a single OpenAI-compatible endpoint to call any AI model — chat, images, audio, video, embeddings, and more. Instead of managing separate API keys and integrations for OpenAI, Gemini, Qwen, and other providers, you configure channels in Newapi and make all requests through one consistent interface.

​
What you can do with Newapi

Chat completions

Call any chat model using the familiar OpenAI /v1/chat/completions format.

Image generation

Generate and edit images with DALL-E, GPT Image, Gemini, and Qwen models.

Audio & speech

Convert text to speech and transcribe audio files with AI.

Video generation

Create videos using Sora, Kling, and Jimeng models through a unified API.

Embeddings

Generate text embedding vectors for search and semantic similarity.

AI app integrations

Connect Cherry Studio, Claude Code, Codex CLI, and other tools in minutes.

​
How it works

Newapi sits between your application and AI providers. You send standard OpenAI-format requests to your Newapi endpoint, and Newapi routes them to the appropriate upstream provider (called a channel). This means:
  • One API format — write code once, use any model
  • Centralized billing — manage credits and usage from one dashboard
  • Token management — issue scoped API keys to team members or applications
  • Usage logging — track every request, token count, and cost

​
Next steps

1

Create an API token

Go to the Newapi console → Token Management and generate your first API key. See Authentication.
2

Make your first API call

Follow the Quickstart to send a chat completion request in under 5 minutes.
3

Connect an AI application

Browse AI Applications to integrate with Cherry Studio, Claude Code, and more.