Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
Comment moderation with AI: Python example
3 min · · development
Spam, insults, ads, genuine comments — the model labels them and sends unclear cases to a moderator. Here's the code and what it costs.
Generate product descriptions for Wildberries and Ozon via AI
5 min · · бизнес
A Python script that takes product specs from a CSV, generates descriptions via Zukko, flags texts with violations, and saves the result.
AI integration in amoCRM for auto-replies and lead analysis
4 min · · бизнес
A new lead in amoCRM sends a webhook to your server, the model assesses the request, and a hint for the manager appears as a note on the card.
AI integration in Bitrix24 via webhooks and API
5 min · · бизнес
A new lead in Bitrix24 fires a webhook, your server asks the model, and a hint for the manager appears as a comment on the lead card.
Integrating AI Models into 1C:Enterprise via API
5 min · · бизнес
A 1C code template that sends text to Claude, GPT, or GLM and returns the answer: email classification, draft replies, and data extraction.
Python: parallel requests to Claude via AsyncOpenAI
4 min · · development
How to process thousands of texts in parallel without hitting limits: AsyncOpenAI, a semaphore, retries, stopping on an empty balance, and cost tracking.
FastAPI: proxying Claude stream response via SSE
4 min · · development
How to send a model's answer to the browser as it's generated: FastAPI keeps the key on the server, and the frontend receives text over SSE.
Spring AI: connecting Claude API via OpenAI provider
4 min · · development
Spring AI talks to Claude and GPT through its OpenAI module. The key detail is the base-url: it differs between Spring AI 1.x and 2.x.
Claude API in PHP: Guzzle and curl for Zukko
4 min · · development
How to call Claude and GPT from PHP: Guzzle, built-in curl, error handling, streaming, and Laravel integration.
Claude API in Go: HTTP requests with SSE streaming
3 min · · development
A Claude and GPT client on the Go standard library: a plain request, error handling, SSE streaming, and bounded parallel requests.
Jan AI with cloud models: Zukko as a remote provider
6 min · · development
Jan runs both local and cloud models. Here is how to add Zukko as a custom endpoint, pick a model by price and fix the most common errors.
SillyTavern with Zukko: connect Claude and GPT through your own API
5 min · · development
SillyTavern connects third-party APIs through the Custom (OpenAI-compatible) source. Step-by-step setup, the cost of long chats and common errors.
How to connect an AI model to your app: key, SDK, streaming, errors
6 min · · development
A step-by-step guide for developers: where to keep the key, how to call a model from Python and Node.js, how to stream answers correctly, which errors to handle, and how to track the cost of each request.
Which AI model to choose for a chatbot: dialog cost, cache, testing
8 min · · models
A chatbot pays not per question but for the whole dialog with its history. We go through the model selection criteria, price 1,000 dialogs on three models with and without caching, and show how to measure latency yourself.
AI for email processing: sorting messages and drafting replies via API
6 min · · автоматизация
A working inbox triage setup: messages over IMAP, category, priority and a draft reply as JSON, masking personal data, human review, and the cost per 1,000 emails.
AI for spreadsheet analysis: CSV and Excel via API without wrong numbers
6 min · · автоматизация
How to analyze CSV and Excel with a model via API: pandas computes the numbers, the model looks for patterns and writes findings as JSON, and code checks that each finding rests on a real metric.
OpenAI API proxy: how to choose an API gateway and what to ask
7 min · · API keys
How an API gateway differs from a network proxy, the criteria for choosing one, questions to ask before your first payment, and how to check yourself that charges match the math.
OpenAI compatible API: what it is, why base_url matters, how to test it
6 min · · development
What an "OpenAI-compatible API" really means, why a client only needs a new base_url and key, how the Anthropic format differs, and how to test the connection in five minutes.
An AI chatbot for your website: architecture, streaming code and cost
6 min · · development
Building a website chatbot: the key stays on the server, a FastAPI backend with streaming, a cheap model, a cost estimate and limits against abuse.
GPT or Claude in 2026: comparing price, index, caching and API format
6 min · · сравнение
Comparing Claude and GPT models on what can be measured: price, intelligence index, caching, API format and tool support — and how to decide on your own data.
GPT-6 via API: Astra, 6.1 Sol, 6 Sol and Luna — prices and setup
5 min · · models
The whole GPT-6 lineup in one place: prices, intelligence index, caching, when to use which model, and how to connect with Python and curl.
AI for writing texts: choosing a model, writing the prompt, pricing it
6 min · · models
How to write with AI models via chat and API: choosing a model, the brief, the draft, editing, fact-checking and the cost of one article.
Cursor alternatives in 2026: eight tools that work with your own API key
6 min · · IDE
Eight AI coding tools: how they differ according to their own docs, and how to connect each one to a single API key.
How much Claude Code costs per month via API: three usage profiles
7 min · · экономия
We price a month of Claude Code by tokens: three load profiles, a formula with caching, a comparison with subscriptions, and ways to stay on budget.