API Documentation

XHuoAPI speaks the OpenAI Chat Completions format, plus the Anthropic Messages format for Claude models. One key covers 70+ models.

Interactive API reference (try requests online) →

Base URL

https://api.xhuoapi.ai

Quick Start

Sign up at the console
Create an API key in the console
Point your Base URL to https://api.xhuoapi.ai
Start making requests

Supported endpoints

Every row below was tested with a real API key. Endpoints not listed here are not guaranteed to work, even if the path responds.

Last verified: 2026-10-05 · Base URL https://api.xhuoapi.ai

Endpoint	Format	Description
POST `/v1/chat/completions`	OpenAI	All chat models. stream, tools and response_format were verified on deepseek-v3.2; support on other models depends on the vendor.
POST `/v1/messages`	Anthropic	Claude models (tested with claude-sonnet-4-6). Authenticate with either x-api-key or Authorization: Bearer.
GET `/v1/models`	OpenAI	Lists every model available to your key.
POST `/v1/embeddings`	OpenAI	text-embedding-3-small returns 1536-dimension vectors. The catalogue also lists text-embedding-3-large and text-embedding-ada-002 (not separately tested).

For the OpenAI SDK set base_url to https://api.xhuoapi.ai/v1. For the Anthropic SDK use https://api.xhuoapi.ai; the SDK appends /v1/messages itself.

Authentication

Every request must include your API key in the HTTP header:

Authorization: Bearer YOUR_API_KEY

⚠️ Security notice: never expose your API key in client-side code. Proxy requests through your own backend instead.

Chat Completions

Create a chat completion. Works with every model on the platform.

POST /v1/chat/completions

Parameters

Parameter	Type	Required	Description
`model`	string	✅	Model ID, e.g. `gpt-4o`
`messages`	array	✅	List of conversation messages
`temperature`	number	❌	Sampling temperature (0-2), defaults to 1
`max_tokens`	integer	❌	Maximum number of tokens to generate
`stream`	boolean	❌	Stream partial results, defaults to false

Example Request

curl https://api.xhuoapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "user",
        "content": "Hello, introduce yourself"
      }
    ],
    "temperature": 0.7
  }'

Example Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I am an AI assistant..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 20,
    "total_tokens": 32
  }
}

List Models

Retrieve the list of every model available to your key.

GET /v1/models

Example Request

curl https://api.xhuoapi.ai/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Commonly used models (tested)

These models answered normally in the latest test run (date under "Supported endpoints"). The full list and per-tier prices are on the pricing page.

deepseek-v3.2

DeepSeek

qwen3.8-max

Alibaba · Qwen

glm-5.3

Zhipu · GLM

kimi-k3

Moonshot · Kimi

claude-sonnet-4-6

Anthropic

gpt-4.1-mini

OpenAI

gemini-2.5-flash

Google

Streaming

Set stream: true to receive tokens as they are generated.

Example Request

curl https://api.xhuoapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Tell me a joke"}],
    "stream": true
  }'

Response Format

Streamed responses use Server-Sent Events (SSE). Every line is prefixed with data:

data: {"id":"chatcmpl-123","choices":[{"delta":{"content":"Hel"}}]}

data: {"id":"chatcmpl-123","choices":[{"delta":{"content":"lo"}}]}

data: [DONE]

Tool calling and JSON mode

Pass tools in the OpenAI format and the model returns the function and arguments in message.tool_calls. The request below returned get_weather with {"city": "Paris"} in our test.

curl https://api.xhuoapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "deepseek-v3.2",
    "messages": [{"role": "user", "content": "What is the weather in Paris? Use the tool."}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather for a city",
        "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}
      }
    }],
    "tool_choice": "auto"
  }'

Send "response_format": {"type": "json_object"} and the model returns valid JSON only. Saying in the prompt that you want JSON makes the output more reliable.

curl https://api.xhuoapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "deepseek-v3.2",
    "messages": [{"role": "user", "content": "Return this JSON exactly: {\"ok\": true}"}],
    "response_format": {"type": "json_object"}
  }'

Anthropic Messages format

Claude models accept Anthropic's request format and work with the Anthropic SDK. Code already written against the Anthropic SDK only needs a new base_url and key.

POST /v1/messages

Both auth headers were verified: x-api-key: YOUR_API_KEY or Authorization: Bearer YOUR_API_KEY. The Anthropic SDK adds the anthropic-version header shown below automatically.

curl https://api.xhuoapi.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Python (anthropic SDK)

from anthropic import Anthropic

client = Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://api.xhuoapi.ai",
)

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

Embeddings

Same request and response format as OpenAI's /v1/embeddings. text-embedding-3-small returns 1536-dimension vectors.

POST /v1/embeddings

curl https://api.xhuoapi.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"model": "text-embedding-3-small", "input": "hello"}'

Error Handling

The API uses conventional HTTP status codes to indicate the result of a request.

Status Code	Description
`200`	Success
`400`	Invalid request parameters
`401`	API key missing or invalid
`429`	Rate limit exceeded
`404`	Path does not exist, usually a typo in the URL
`503`	No upstream is currently available for this model, or the model name does not exist. Retry later or switch models
`500`	Internal server error

Example Error Response

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

The wording of error.message can change. Handle errors by HTTP status code rather than matching the message text.

Code Examples

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.xhuoapi.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "user", "content": "Hello"}
    ]
)

print(response.choices[0].message.content)

Node.js

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.xhuoapi.ai/v1'
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello' }]
});

console.log(response.choices[0].message.content);

cURL

curl https://api.xhuoapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}]
  }'