Quickstart

Make your first request to api14 with the official OpenAI SDK. It takes three steps and about a minute.

Create an API key

Sign in and open API keys. Click Create key, give it a name and copy the key. Keys start with sk-api14- and are shown only once, store it somewhere safe, such as an environment variable:

export API14_API_KEY="sk-api14-..."

New accounts start with a small free USD balance on the Free plan, enough to try cheap models. Add funds or pick a plan on the pricing page whenever you need more.

Install the SDK

Use the official OpenAI SDK for your language. Nothing else is needed.

npm install openai

pip install openai

Other languages (Go, PHP, Java, C#, Ruby and Rust) are covered in the SDK guides, for example Go and C# /.NET.

Make a request

Point the client at https://api14.com/api/v1 and pass your key. This example streams the answer token by token:

import OpenAI from "openai";

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

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

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

That's it, every other model works the same way. Change model to any id from the models page, for example anthropic/claude-sonnet-4.5 or google/gemini-2.5-flash.

Model ids use the provider/model format, for example openai/gpt-5-mini, and support variants like :free, :online and :nitro. See Model ids & variants.

Without streaming

Leave out stream to get the full answer in one JSON response:

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);

The response follows the OpenAI chat completion shape:

{
  "id": "gen-1759571234-abc123",
  "object": "chat.completion",
  "model": "openai/gpt-5-mini",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Requests fly,\nJSON returns..." },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 14, "completion_tokens": 21, "total_tokens": 35, "cost": 0.0000455 }
}

usage.cost is the price of the request in USD, the amount debited from your balance.

Next steps

• Chat completions, every request parameter.
• Streaming, the event format and how to handle it.
• Images, Video, Speech, other capabilities.
• Errors, handle 402 insufficient_balance and 429 rate_limited.