Call XiuRouter with an SDK

Use XiuRouter with an OpenAI-compatible SDK by setting its Base URL to https://router-api.xiu.ai/v1, providing a dedicated XiuRouter API key, and copying an exact model ID from the current catalog.

Before you start

• Create a dedicated key using the quickstart.
• Copy a model ID from Models and pricing.
• Install the OpenAI SDK used by your project.

Keep the key out of source files, lockfiles, frontend bundles, and Git. These examples read environment variables:

export XIUROUTER_API_KEY="YOUR_XIUROUTER_API_KEY"
export XIUROUTER_MODEL="YOUR_MODEL_ID"

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["XIUROUTER_API_KEY"],
    base_url="https://router-api.xiu.ai/v1",
)

response = client.chat.completions.create(
    model=os.environ["XIUROUTER_MODEL"],
    messages=[
        {"role": "user", "content": "Reply only: Python SDK connected"}
    ],
)

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

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.XIUROUTER_API_KEY,
  baseURL: "https://router-api.xiu.ai/v1",
});

const response = await client.chat.completions.create({
  model: process.env.XIUROUTER_MODEL,
  messages: [
    { role: "user", content: "Reply only: JavaScript SDK connected" },
  ],
});

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

Common parameters

The gateway can parse these fields without every model accepting them. Keep the original error and request ID, remove optional parameters, then add them back one at a time.

Gemini reasoning levels

The pricing page groups compatibility suffixes into one Gemini model family. For Gemini 3.x SDK requests, prefer the base model ID and send reasoning_effort; -low, -medium, and -high remain accepted compatibility IDs. Gemini 3.8 Flash can select tiers through native thinkingLevel; use exact Argon IDs when a low, medium, or high tier must be guaranteed because the base Argon name can fall back to high through upstream mapping.

After changing a level, start a new request and check the final model, protocol, service group, and charge in Usage. Do not use the pricing family label as a request ID, and do not treat one text reply as proof that tool calling works.

Native Gemini SDK

For native reasoning, image sizes, image editing, or Gemini tool calls, use Gemini GenerateContent with Base URL https://router-api.xiu.ai and x-goog-api-key. Put image size in generationConfig.imageConfig; OpenAI size and quality fields are not equivalent. Verify returned pixels and usage records.

from google import genai

client = genai.Client(
    api_key=os.environ["XIUROUTER_API_KEY"],
    http_options={"base_url": "https://router-api.xiu.ai", "api_version": "v1beta"},
)
response = client.models.generate_content(
    model="gemini-3.1-flash-image",
    contents="Create a square blue robot icon with no text.",
    config={
        "response_modalities": ["TEXT", "IMAGE"],
        "image_config": {"aspect_ratio": "1:1", "image_size": "2K"},
    },
)

Verify the result

1. Confirm that the program receives complete text, rather than only passing authentication.
2. In XiuRouter usage logs, check the model, service group, tokens, cost, and status.
3. Record the x-oneapi-request-id response header for troubleshooting.

Troubleshoot

Sources and review date

The Chat Completions and Gemini GenerateContent routes, request fields, and OpenAI/Gemini SDK Base URL settings were reviewed on November 7, 2026. Verify parameter support and returned image dimensions with the actual target model.