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.
How chat memory works (and how to keep it cheap)
AI APIs are stateless: you send the whole conversation every time. Here's how to manage history without exploding costs.
LangChain.js with a custom OpenAI-compatible endpoint
Configure ChatOpenAI in LangChain.js to use DEVSAIO, with streaming and a simple prompt template.
LlamaIndex with any OpenAI-compatible model (OpenAILike)
Use the OpenAILike class to run LlamaIndex RAG pipelines on Claude, GPT, Gemini or DeepSeek through DEVSAIO.
Build your own AI assistant for the terminal
A tiny shell command that explains errors, writes commands and answers questions, using any model.
Build a browser extension that summarises any page
A Chrome/Edge extension that sends page text to your own server for a summary, without exposing your API key.
Vercel AI SDK with a custom OpenAI-compatible provider
Use @ai-sdk/openai-compatible to stream responses from any DEVSAIO model in Next.js.
Discover available models with GET /v1/models
Use the models endpoint to list what's available, build a model picker, and avoid hard-coding model names.
Add an AI writing assistant to WordPress with PHP
A small WordPress plugin that generates excerpts and meta descriptions from post content using any model.
OpenAI Python SDK with a custom base URL: complete guide
Everything you need for production use: clients, streaming, async, timeouts, retries and error handling, with any model.
Timeouts and long AI responses: avoiding cut-offs
Long generations can exceed default HTTP timeouts. Here's how to set timeouts, stream, and design for slow responses.
Analyse CSV data with AI (without hallucinated numbers)
The right way to use AI on spreadsheets: let code do the maths and the model do the reasoning and writing.
OpenAI Node.js SDK with a custom base URL: complete guide
Set up the openai npm package for any model: streaming, timeouts, retries, and a minimal Express endpoint.
Turn meeting transcripts into notes and action items
Summarise transcripts into decisions, action items with owners, and open questions, in a consistent format.
Anthropic Python SDK: streaming and tool use with a custom base URL
Use the anthropic package with DEVSAIO for streaming responses and tool calling with Claude models.
Generate product descriptions in bulk for your store
Create consistent, on-brand product descriptions from specs, with a style guide prompt and a CSV workflow.
Anthropic TypeScript SDK with a custom base URL
Call Claude from Node.js or edge runtimes with @anthropic-ai/sdk pointed at DEVSAIO, including streaming.
Process thousands of AI requests reliably
Patterns for big jobs: concurrency limits, checkpoints, retries and cost tracking, so a crash halfway doesn't mean starting over.
Call AI models from PHP (cURL, no libraries)
A dependency-free PHP function for chat completions, plus streaming output and error handling.