Bitdeer AI Docs
GuidesAPI ReferenceGPU Cloud

Introduction

Welcome to Bitdeer AI — serverless inference APIs for self-deployed models.

Base URL

All API requests go to:

https://api-inference.bitdeer.ai/v1

For list of all available models, checkout Model Catalog

Calling the API

Endpoints follow common chat-completions JSON shapes (POST /v1/chat/completions, etc.). Use cURL, your own HTTP stack, or any client that lets you set a custom base URL. Step-by-step requests and Python / JavaScript snippets are in Get Started and SDKs.

curl https://api-inference.bitdeer.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_BITDEER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-ai/DeepSeek-V4-Pro","messages":[{"role":"user","content":"Hello!"}]}'

How this documentation is organized

SectionWhat it covers
Get StartedGet your API key and send a first request (cURL or client libraries)
LLMStreaming, Vision, Function Calling, Structured Outputs
IntegrationsCursor, LangChain, OpenAI Agents SDK, Dify, LiteLLM
Language clientsPython and JavaScript (openai client + Bitdeer base_url)
ExamplesComplete runnable examples
API ReferenceEndpoint-level documentation with schemas
GPU CloudDedicated GPU instances, networking, and Instance API reference

Quick start

Get an API key

Sign up at bitdeer.ai and generate a key from Model Studio → API Keys.

Install client libraries

pip install openai    # Python: community openai — set base_url to Bitdeer
npm install openai    # JavaScript: same package — set baseURL to Bitdeer

Make your first request

See the complete walkthrough in Get Started → First Request.

Last updated on

On this page