Introduction

api14 is an OpenAI-compatible API gateway for hundreds of AI models. One API key, one base URL and one USD balance give you text, image, video, speech, transcription, music, embeddings and rerank models from every major provider. You keep using the official OpenAI SDKs; only baseURL and apiKey change.

https://api14.com/api/v1

What you get

• Every major model, around 650 models, updated automatically. Model ids use the provider/model format, such as anthropic/claude-sonnet-4.5 or openai/gpt-5-mini. See Model ids & variants.
• The OpenAI request and response shapes, chat completions, Responses, embeddings, images, audio and more, so existing code works unchanged. See OpenAI SDK compatibility.
• Clear prices in USD, every model shows its price, and each request is debited from your USD balance. Free credit on signup; plans add more usage than they cost. See Pricing & billing.
• Advanced features passed through, streaming, tool calling, structured outputs, reasoning, web search, prompt caching, provider routing and model fallbacks.

Endpoints at a glance

How a request flows

1. Your client sends a request with Authorization: Bearer sk-api14-....
2. The gateway checks the key, that the model is available and allowed for your key and plan, your rate limit and your balance.
3. The request body is forwarded unchanged to the upstream provider.
4. The response is returned to you unchanged, streamed byte for byte when stream: true.
5. The exact cost of the request is debited from your USD balance. Failed requests are not charged.

A first request

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
});

const result = await client.chat.completions.create({
  "model": "openai/gpt-5-mini",
  "messages": [
    {
      "role": "user",
      "content": "Explain vector databases in two sentences."
    }
  ]
});
console.log(result.choices[0].message.content);

Next steps

• Quickstart, create a key and make a request in a minute.
• Authentication, how keys work and how to keep them safe.
• Errors and Rate limits, what to handle in production.
• Browse all models and their prices on the models page.