Skip to main content
Provides completions for all open source models that are text-generation, chat, audio-text-to-text, image-text-to-text, video-text-to-text, it also supports the closed source providers, openai, anthropic, mistral, cohere, and google. To specify a provider, prefix the model with the provider, e.g. gpt-4 should be passed in as openai/gpt4

Basic usage

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "BYTEZ_KEY",
  baseUrl: "https://api.bytez.com/models/v2/openai/v1",
  defaultHeaders: { Authorization: "BYTEZ_KEY" }
});

const response = await client.completions.create({
  model: "openai/text-davinci-003",
  prompt: "Write a short poem about AI",
  temperature: 0.7,
  top_p: 1,
  max_tokens: 150
});

console.log(response);

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "BYTEZ_KEY",
  baseUrl: "https://api.bytez.com/models/v2/openai/v1",
  defaultHeaders: { Authorization: "BYTEZ_KEY" }
});

const stream = await client.completions.create({
  model: "openai/text-davinci-003",
  prompt: "Write a short poem about AI",
  max_tokens: 150,
  temperature: 0.7,
  top_p: 1,
  stream: true
});

let text = '';
for await (const event of stream) {
  if (event.type === "response.output_text.delta") {
    text += event.delta;
    console.log(event.delta);
  }
}

console.log({ text });

const response = await client.completions.create({
  model: "openai/text-davinci-003",
  prompt: "Write a haiku about space exploration",
  max_tokens: 120,
  temperature: 0.3,
  top_p: 0.9,
  frequency_penalty: 0.5,
  presence_penalty: 0.2
});

console.log(response);
⌘I