Build with every AI model.
Practical guides for developers and creators: connect your tools, pick the right model, write better prompts and keep your AI bill down.
Call AI models from Go with net/http
A small, dependency-free Go client for chat completions with typed requests and responses.
Call AI models from Java with HttpClient
Use Java 11+'s built-in HttpClient to send chat requests to any model through DEVSAIO.
Call AI models from C# / .NET
Use HttpClient and System.Net.Http.Json to talk to any DEVSAIO model from .NET.
Call AI models from Rust with reqwest and serde
An async Rust example for chat completions against DEVSAIO, with proper error handling.
Call AI models from Ruby (net/http)
A small Ruby helper for chat completions with any DEVSAIO model, plus a Rails usage tip.
Use the Chatbox desktop app with a custom OpenAI-compatible API
Set up Chatbox on Windows, macOS, Linux or mobile to chat with any DEVSAIO model.
AI API curl cheat sheet: chat, streaming, images, embeddings
Copy-paste curl commands for every common AI API call, useful for testing and debugging.
Add an =AI() function to Google Sheets with Apps Script
Write a custom Google Sheets function that sends a prompt to any model, perfect for bulk writing, tagging and cleaning data.
Function calling (tool use) explained with a working example
How models call your functions: define tools, run them, send results back. A complete Python example with a weather tool.
Build a streaming AI chat app with Next.js
A Next.js App Router chat page with a server route that streams from any model, keeping your key off the client.
Reasoning (thinking) models: when they're worth it
Reasoning models think before they answer. Learn how they differ, what they cost, and which tasks actually benefit.
How to write a good system prompt
The system prompt sets your assistant's role, rules and style. Here's a template and the mistakes to avoid.
Streaming AI responses with Server-Sent Events (SSE), explained
Why streaming makes AI apps feel fast, what the SSE stream looks like, and how to parse it correctly in Python, Node and the browser.
Claude Code workflow tips that save time and tokens
Practical habits for using Claude Code on real projects: CLAUDE.md, small tasks, the right model, and reviewing diffs.
How prepaid, per-request AI billing works
No subscription, no invoice at the end of the month: here's exactly how your balance is held, charged and refunded for each request.
Why use one API key for every AI model?
Managing separate accounts for Anthropic, OpenAI, Google and DeepSeek is slow. Here is what a single gateway changes, and when it's the right choice.
Set up OpenAI Codex CLI with a custom provider
Configure Codex CLI's config.toml to use DEVSAIO, choose a model, and keep your key in an environment variable.
How to estimate AI API costs before you build
A simple formula and worked examples for estimating monthly costs of chatbots, summarisers and batch jobs.