Bitdeer AI · Developer DocumentationServerless AI Inference,
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.
Documentation
Find the right entry point
Navigate by the shape of what you need — learn, integrate, or reference.
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 openaiPython
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)