Node.js

Use the official openai npm package with api14. Nothing else changes: only baseURL and apiKey point at api14, and every model id works as model.

Install

npm install openai

Store your key in an environment variable:

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

Configure

import OpenAI from "openai";

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

With no options, the SDK reads OPENAI_BASE_URL and OPENAI_API_KEY. Setting those two variables switches an existing app to api14 without code changes:

export OPENAI_BASE_URL="https://api14.com/api/v1"
export OPENAI_API_KEY="sk-api14-..."

const client = new OpenAI(); // picks up both variables

Chat

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);

Streaming

const stream = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-4.5",
  messages: [{ role: "user", content: "Write a haiku about APIs." }],
  stream: true,
});

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

See Streaming for the event format.

Tool calling

Send tools, run the calls the model asks for, append the results and call again until it answers with text:

const tools = [{
  type: "function",
  function: {
    name: "get_weather",
    description: "Current weather for a city",
    parameters: {
      type: "object",
      properties: { city: { type: "string" } },
      required: ["city"],
    },
  },
}];

const messages = [{ role: "user", content: "What's the weather in Istanbul?" }];
let res = await client.chat.completions.create({ model: "openai/gpt-5-mini", messages, tools });

while (res.choices[0].finish_reason === "tool_calls") {
  const msg = res.choices[0].message;
  messages.push(msg);
  for (const call of msg.tool_calls) {
    const args = JSON.parse(call.function.arguments);
    const result = await getWeather(args.city); // your function
    messages.push({ role: "tool", tool_call_id: call.id, content: JSON.stringify(result) });
  }
  res = await client.chat.completions.create({ model: "openai/gpt-5-mini", messages, tools });
}

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

See Tool calling.

Structured output

The parse helper turns a Zod schema into a json_schema response format and parses the reply (npm install zod):

import { z } from "zod";
import { zodResponseFormat } from "openai/helpers/zod";

const Person = z.object({ name: z.string(), born: z.number().int(), city: z.string() });

const res = await client.chat.completions.parse({
  model: "openai/gpt-5-mini",
  messages: [{ role: "user", content: "Extract: Ada Lovelace, born 1815 in London." }],
  response_format: zodResponseFormat(Person, "person"),
});

console.log(res.choices[0].message.parsed); // { name: "Ada Lovelace", born: 1815, city: "London" }

See Structured outputs.

Image input

Pass content as an array of parts. Use a public URL or a base64 data URL:

import { readFileSync } from "node:fs";

const image = readFileSync("photo.png").toString("base64");

const res = await client.chat.completions.create({
  model: "google/gemini-2.5-flash",
  messages: [{
    role: "user",
    content: [
      { type: "text", text: "What is in this picture?" },
      { type: "image_url", image_url: { url: `data:image/png;base64,${image}` } },
    ],
  }],
});

See Vision & files for PDFs, audio and video.

Embeddings

const result = await client.embeddings.create({
  model: "openai/text-embedding-3-small",
  input: ["The quick brown fox", "Lorem ipsum"],
});

console.log(result.data.map((d) => d.embedding.length));

Endpoints without an SDK method

Video jobs and rerank are not part of the OpenAI SDK surface. Use the client's generic post / get helpers, they reuse the base URL, key and retries:

const ranked = await client.post("/rerank", {
  body: {
    model: "cohere/rerank-v3.5",
    query: "What is the capital of France?",
    documents: ["Paris is the capital of France.", "Berlin is in Germany."],
    top_n: 1,
  },
});
console.log(ranked.results);

Errors

Errors arrive in the OpenAI shape and are thrown as OpenAI.APIError. Branch on status and code:

try {
  await client.chat.completions.create({ model: "openai/gpt-5-mini", messages: [{ role: "user", content: "Hi" }] });
} catch (err) {
  if (err instanceof OpenAI.APIError) {
    if (err.status === 402) console.error("Balance too low, add funds:", err.code); // insufficient_balance
    else if (err.status === 429) console.error("Retry after", err.headers?.["retry-after"], "s:", err.code); // rate_limited
    else throw err;
  }
}

See Errors for every code.

Timeouts and retries

The SDK retries connection errors, 408, 409, 429 and 5xx responses twice by default, with exponential backoff that honours Retry-After. The default timeout is 10 minutes per attempt. Set both on the client, or override them per request:

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
  timeout: 60_000, // ms per attempt
  maxRetries: 4,
});

await client.chat.completions.create(params, { timeout: 300_000, maxRetries: 0 });

A retry cannot fix daily_limit_reached or insufficient_balance. For long batch jobs, stop on those codes instead of retrying. See Rate limits.

All capabilities

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);