Use Inference APIs with OpenAI Node.js SDK

Set baseURL on the official openai npm package. Works in Node, Bun, Deno and edge runtimes.

Settings

Setting	Value
Base URL	`https://api.inferenceapis.com/v1` (also `/openai/v1`)
API key	From API Keys; send as `Authorization: Bearer …`
Chat model ids	`openai/gpt-oss-120b`, `deepseek-ai/DeepSeek-V4-Flash`, `zai-org/GLM-5.3-Flash`, `meta-llama/Llama-3.3-70B-Instruct-Turbo` — all models
Audio model ids	`openai/whisper-large-v3` (transcription), `hexgrad/Kokoro-82M` (speech)

Configuration

Install

npm install openai

Chat with streaming

import OpenAI from "openai";

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

const stream = await client.chat.completions.create({
  model: "openai/gpt-oss-120b",
  messages: [{ role: "user", content: "Hello" }],
  max_tokens: 400,
  stream: true,
});
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");

Speech

import fs from "node:fs";
const audio = await client.audio.speech.create({ model: "hexgrad/Kokoro-82M", voice: "af_heart", input: "Hello there" });
fs.writeFileSync("hello.mp3", Buffer.from(await audio.arrayBuffer()));

Transcription

const result = await client.audio.transcriptions.create({ model: "openai/whisper-large-v3", file: fs.createReadStream("hello.mp3") });
console.log(result.text);

Verify

Smoke test

node -e "import('openai').then(async ({default: OpenAI}) => console.log((await new OpenAI({baseURL:'https://api.inferenceapis.com/v1', apiKey: process.env.INFERENCE_API_KEY}).models.list()).data.length + ' models'))"

Gotchas

In browsers, never ship your key; call through your own backend.

If something fails

401 — key missing or wrong · 402 insufficient_balance — add credits on Billing · 404 model_not_found — check the id against the model list (aliases such as gpt-oss-120b work too) · 503 model_unavailable — the model is being enabled. Full details in the API docs.