Bitdeer AI · Developer Documentation

Serverless AI Inference,one API call away.

Access self-deployed AI models — GLM, Kimi, Qwen, MiniMax, Nemotron, DeepSeek, and MiMo — through a single HTTPS API. Text, vision, and audio chat completions on NVIDIA GPU infrastructure.

Featured Models

AI models ready for production

Thinking, vision, video, and audio — self-deployed models through one hosted API.

Quick Start

Make your first API call in under five minutes

Get an API key, call the REST endpoints (or use our language examples), and start generating.

Install
# Optional: community Python/JS client packages
pip install openai
# or
npm install openai
Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api-inference.bitdeer.ai/v1",
    api_key="YOUR_API_KEY",  # https://www.bitdeer.ai/en/model/apikeys
)

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

print(response.choices[0].message.content)