datablocks API Documentation

Welcome to the datablocks API documentation. Get started building with our powerful API.

🚀

Quick Start

Get up and running with datablocks in under 5 minutes

📡

API Reference

Complete API documentation with interactive examples

📚

Guides & Tutorials

In-depth guides for common use cases and workflows

Introduction

datablocks is a modern API management platform that provides efficient access to LLM services with optimized performance and cost management. Our platform offers:

Pre-computed context blocks (datablocks) for faster processing
OpenAI-compatible API endpoints
Flexible pricing based on actual usage
Support for multiple LLM models
File upload and management
Fine-tuning capabilities

Available Models

Model	Context Window	Best For	Speed
qwen	32K tokens	General purpose, coding, multilingual	Fast
llama	8K tokens	Conversation, instruction following	Very Fast

Pricing

Model	Input	Output	Datablock
qwen	$0.60 / 1M tokens	$1.20 / 1M tokens	$0.10 / 1M tokens
llama	$0.40 / 1M tokens	$0.80 / 1M tokens	$0.05 / 1M tokens

Datablocks save costs: With datablocks, you pay the datablock rate instead of the input rate for pre-computed context, resulting in up to 85% cost savings on repeated queries.

Getting Started

1
Create an account
Sign up for a datablocks account to get started
2
Generate an API key
Go to your dashboard and create a new API key
3
Make your first request
Use your API key to make requests to our endpoints
curl /api/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{"model": "qwen", "messages": [{"role": "user", "content": "Hello!"}]}'

Key Features

⚡ Pre-computed Context

datablocks contain pre-processed content that eliminates the need for repeated context preparation, dramatically reducing response times and costs.

🔄 OpenAI Compatible

Drop-in replacement for OpenAI's API. Use existing SDKs and tools without modification.

💰 Cost Effective

Pay only for what you use. No hidden fees, no minimum commitments. Scale from zero to millions of requests.

🎯 Fine-tuning

Customize models for your specific use case with our fine-tuning capabilities.