Quick Start

AI Station is a unified model gateway built on NewAPI. The API is OpenAI-compatible, and additionally supports Anthropic, Gemini, Midjourney, and a range of video/audio plugin tasks.

Endpoint

Item	Value
Base URL	https://test.kailin.com.cn
Auth	Authorization: Bearer sk-xxxx (request header)
Protocol	HTTPS — REST, SSE streaming, and WebSocket (Realtime)

Get an API Key

1. Sign in to the Console.
2. Create a new token on the Tokens / API Keys page. Tokens look like sk-xxxxxxxx.
3. Keep your token safe. Never commit it to a repository or expose it in client-side code.

Your First Request

Every endpoint is authenticated with the Authorization: Bearer <your token> header. Chat completion example:

curl https://test.kailin.com.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-token" \
  -d '{
    "model": "deepseek-v4-1-flash-261017",
    "messages": [
      { "role": "user", "content": "Hello, introduce yourself" }
    ]
  }'

RequestREQUEST

POSThttps://test.kailin.com.cn/v1/chat/completions

API KeyStored only in your browser, never uploaded

Body (JSON)SSE stream · rendered live{ "model": "deepseek-v4-1-flash-261017", "messages": [ { "role": "user", "content": "Hello, introduce yourself" } ], "stream": true }

ResponseRESPONSE

Fill in the request and hit Send — the response shows up here

Official SDKs

The API is OpenAI-compatible, so the official SDKs work out of the box — just point base_url at this site:

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-token",
    base_url="https://test.kailin.com.cn/v1",
)

resp = client.chat.completions.create(
    model="deepseek-v4-1-flash-261017",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-your-token',
  baseURL: 'https://test.kailin.com.cn/v1',
});

const resp = await client.chat.completions.create({
  model: 'deepseek-v4-1-flash-261017',
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(resp.choices[0].message.content);

The Anthropic SDK works too (point base_url at this site). See Anthropic Messages.

Streaming

Most text endpoints accept "stream": true and respond with SSE (Server-Sent Events) — text/event-stream, each event prefixed with data: , terminated by data: [DONE]:

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"Hi"},"index":0}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":" there"},"index":0}]}

data: [DONE]

Set stream=True (Python) or stream: true (Node.js) in the SDK and it handles the parsing for you.

Error Format

Errors are returned as JSON. type is usually new_api_error (gateway-level) or an upstream error such as invalid_request_error:

{
  "error": {
    "message": "Invalid token (request id: 2026xxxx)",
    "type": "new_api_error",
    "code": ""
  }
}

HTTP Status	Meaning	Common Causes
401	Auth failed	Token invalid, deleted, or Authorization header missing
403	Forbidden	Token lacks model access, group mismatch, or IP restriction
404	Not found	Wrong model name or task ID
429	Rate limited	RPM/TPM limit hit — retry later
5xx	Server error	Upstream channel issue — retry or switch models

note

The request id in an error message is the key to troubleshooting. Include it when reporting issues.

List Available Models

Call List Models to see which models your token can access:

curl https://test.kailin.com.cn/v1/models \
  -H "Authorization: Bearer sk-your-token"

API Overview

Category	Endpoint	Description
Models	GET /v1/models	List available models
Text	POST /v1/chat/completions	Chat completion (multimodal / tools / reasoning)
Text	POST /v1/completions	Legacy text completion
Text	POST /v1/responses	Responses API
Text	POST /v1/messages	Anthropic format
Embeddings	POST /v1/embeddings	Text embeddings
Images	POST /v1/images/generations	Image generation
Audio	POST /v1/audio/transcriptions etc.	Transcription / translation / TTS
Realtime	WS /v1/realtime	Realtime voice conversation
Ranking	POST /v1/rerank	Text reranking
Safety	POST /v1/moderations	Content moderation
Video	POST /v1/video/generations	Video generation task
Images	/mj/*	Midjourney proxy
Tasks	POST /v1/tasks	Generic plugin tasks (Suno/Kling etc.)