Overview & Authentication

YouQi AI provides a unified, OpenAI-compatible API. A single API key lets you call models from OpenAI, Anthropic, Google, DeepSeek, and more. Just point your existing OpenAI client's base URL and API key to YouQi AI — no code changes required.

Endpoint

Item	Value
Base URL (OpenAI-compatible / Claude native)	https://ai.youqi.tech/v1
Base URL (Gemini native)	https://ai.youqi.tech/v1beta
Content type	application/json (except binary uploads for audio / images)

Use the Gateway only

All client traffic (LLM, GET /v1/models, Ark Seedance, assets) must use the Gateway Base from the console. Bypassing the Gateway will not list Seedance and cannot reach video/asset routes.

A few vendor-specific video formats use their own path prefix

Ark Seedance (/api/v3/..., video API key) and the asset library (/openapi/volcengine/..., AK/SK HMAC), Kling (/kling/...), and Jimeng (/jimeng/...) are not under /v1 — see each page.

Authentication

A single sk-... key works for every endpoint, but different formats pass the key differently:

Format	Auth	Example
OpenAI-compatible (default)	Authorization: Bearer <KEY>	Authorization: Bearer sk-YOUR_API_KEY
Claude native (Messages)	x-api-key: <KEY> + anthropic-version header	x-api-key: sk-YOUR_API_KEY
Gemini native (/v1beta)	query param ?key=<KEY> or x-goog-api-key header	...:generateContent?key=sk-YOUR_API_KEY

For most use cases the OpenAI-compatible format is all you need:

Authorization: Bearer sk-YOUR_API_KEY

Create a key (formatted sk-...) on the API Keys page in the console. The full key is shown only once at creation — store it securely.

Quickstart

cURL

curl https://ai.youqi.tech/v1/chat/completions \
  -H "Authorization: Bearer sk-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      { "role": "user", "content": "Introduce yourself in one sentence." }
    ]
  }'

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://ai.youqi.tech/v1",
    api_key="sk-YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://ai.youqi.tech/v1",
  apiKey: "sk-YOUR_API_KEY",
});

const resp = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);

Response format

A successful response returns HTTP 200 with a JSON body. Streaming requests ("stream": true) return chunks as Server-Sent Events, ending with data: [DONE].

Error handling

Errors return a standard HTTP status code plus a JSON error body:

{
  "error": {
    "message": "A human-readable message",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

Status	Meaning
400	Invalid request parameters
401	Missing or invalid API key
403	No access to the model or resource
404	Model or endpoint not found
429	Rate limited or insufficient balance
5xx	Server / upstream error, retry later

Billing

You are billed from your account balance based on actual usage (tokens / duration / count, depending on the endpoint), with no minimum spend. See live per-model pricing on the Models page in the console.