Get Started in Minutes

The WorkChi API is fully compatible with OpenAI. Just change the base URL and you're done.

Quick Start

Get your API key

Create a key with the gateway:invoke scope in your API keys dashboard.

Change the base URL

Update your code to use the WorkChi endpoint:

# OpenAI (before)
https://api.openai.com/v1

# WorkChi (after)
https://benchmarks.datachi.ai/api/v1

Use "auto" for intelligent routing

Set model: "auto" to let the router select the optimal model, or specify a specific model.

Code Examples

import OpenAI from "openai";

// Fully OpenAI-compatible — just change the base URL + key.
const client = new OpenAI({
  apiKey: process.env.WORKCHI_API_KEY, // wcb_live_...
  baseURL: "https://benchmarks.datachi.ai/api/v1",
});

const response = await client.chat.completions.create({
  model: "auto", // router picks the optimal model, or pass a model id
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain quantum computing in simple terms." },
  ],
  max_tokens: 1000,
});

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

Framework Support

🔗

LangChain

Native Python and JS support

📚

LlamaIndex

RAG and indexing support

🤖

AutoGPT

Autonomous agent support

🪟

Semantic Kernel

Microsoft ecosystem

Advanced Options

Custom Routing Rules

Define your own routing logic based on task type, language, or user tier.

{
  "model": {
    "task": "code",
    "language": "de",
    "tier": "premium"
  }
}

EU Data Residency

Route all requests to EU-hosted models for compliance.

{
  "model": "auto",
  "region": "eu"  // Forces EU providers
}

Ready to integrate?

Get your API key and start using the WorkChi Router today.

Loading…