OpenAI Format | cheapkeyai.com Docs

OpenAI-compatible is the most popular choice because many SDKs and frameworks support it out of the box. Simply change `baseURL` to cheapkeyai.com and use your API key.

Installation

npm install openai

Initialize Client

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: process.env.CHEAPKEYAI_API_KEY,
  baseURL: "https://cheapkeyai.com/v1"
});

const result = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello!" }]
});

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

Chat Completions

const stream = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Write a guide to deploy a React app." }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

const result = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{
    role: "user",
    content: [
      { type: "text", text: "Describe this image." },
      { type: "image_url", image_url: { url: "https://example.com/image.png" } }
    ]
  }]
});

const completion = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Weather in London?" }],
  tools: [{
    type: "function",
    function: {
      name: "get_weather",
      description: "Get weather by city",
      parameters: {
        type: "object",
        properties: { location: { type: "string" } },
        required: ["location"]
      }
    }
  }]
});

Responses API

curl https://cheapkeyai.com/v1/responses \
  -H "Authorization: Bearer " \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-mini",
    "input": "Create an SEO checklist for docs."
  }'

Images API

const image = await openai.images.generate({
  model: "gpt-image-1",
  prompt: "Modern docs dashboard, natural lighting",
  size: "1024x1024"
});

Videos API

Video generation is typically an asynchronous task. After creating a task, poll the status endpoint until it completes to retrieve the resulting URL.

Embeddings, Rerank, Moderations

Embeddings are used for search, RAG, and clustering.
Rerank is used to reorder documents by relevance.
Moderations are used to check input or output content.

Error Handling

try {
  await openai.chat.completions.create({
    model: "gpt-4o",
    messages: [{ role: "user", content: "Hello" }]
  });
} catch (error) {
  console.error(error.status, error.message);
}