Language clients

JavaScript client

Call Bitdeer AI from Node or the browser with the community openai package and a custom baseURL.

This guide uses the openai npm package as a typed client. Set baseURL to Bitdeer and use your Bitdeer API key.

Install

npm install openai

Configure

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.BITDEER_API_KEY,
  baseURL: 'https://api-inference.bitdeer.ai/v1',
});

Chat completion

const response = await client.chat.completions.create({
  model: 'deepseek-ai/DeepSeek-V4-Pro',
  messages: [{ role: 'user', content: 'Hello!' }],
  max_tokens: 256,
});

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

Streaming

const stream = await client.chat.completions.create({
  model: 'deepseek-ai/DeepSeek-V4-Pro',
  messages: [{ role: 'user', content: 'Tell me a joke.' }],
  max_tokens: 256,
  stream: true,
});

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

Error handling

import OpenAI from 'openai';

try {
  await client.chat.completions.create({ ... });
} catch (err) {
  if (err instanceof OpenAI.RateLimitError) {
    // back off and retry
  } else if (err instanceof OpenAI.APIError) {
    console.error(err.status, err.message);
  }
}

See Errors for the full error reference.

Last updated on

Python client

Call Bitdeer AI from Python using the community openai package and a custom base URL.

Overview

End-to-end code examples using Bitdeer AI APIs.

JavaScript client · Bitdeer AI