Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
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.
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 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-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.
How to build an AI agent in Python from scratch: tool calling, loop, budget
5 min · · агенты
A minimal AI agent in Python with no frameworks: tools, a call loop, step and budget limits. Full code on the OpenAI SDK and an estimate of what one task costs.
Vibe coding: what it is, the tools, and what an hour of agent work costs
7 min · · development
Where vibe coding came from, what to use, where the catch is, and what an hour of AI agent work really costs — with a formula and limits that keep your budget intact.
What is an MCP server, why agents need it, and how to add one to Claude Code
7 min · · агенты
The Model Context Protocol in plain words: how it is built, how to add an MCP server to Claude Code, and why every connected server costs tokens.
Best AI model for programming: how to choose by the numbers
7 min · · development
Which criteria to compare coding models on, which catalog models make good candidates, what an agent session costs at October 7, 2026 prices, and how to test models on your own repository.
AI model API: what it is and how to send your first request
6 min · · API keys
How an AI model API differs from a browser chat, what a key and a base URL are, what you pay for, and how to send your first request in ten minutes.
Claude API key in Russia: Anthropic SDK and Claude Code on a Zukko key
5 min · · API keys
The Anthropic Console doesn't serve Russia, but a Zukko key works with the Anthropic SDK and Claude Code. Steps: the key, code, prompt caching, Opus 5.5 and Sonnet 5 prices.
OpenAI API key in Russia: why it's hard and how to replace it, step by step
5 min · · API keys
Why an OpenAI key is hard to get from Russia and how to replace it with a Zukko key for the official OpenAI SDK. Step by step: key, variables, code, errors.
AnythingLLM with Zukko: document chat on your own OpenAI-compatible API
5 min · · development
AnythingLLM connects third-party models through the Generic OpenAI provider. We cover the fields, the settings that drive answer cost, and typical errors.
Flowise and Zukko: an OpenAI-compatible API for AI workflows
5 min · · development
In Flowise, third-party models are connected through the ChatOpenAI Custom node and the Base Path parameter. Step-by-step setup, a chat example and errors.
Connecting Zukko to Dify: an OpenAI-compatible API for LLM apps
5 min · · development
In Dify, a third-party API is connected through the OpenAI-API-compatible plugin. We go through every form field, model choice per node and common errors.
RAG on a cheap model: knowledge base search without a vector DB
5 min · · development
Knowledge base search without a vector database or a cloud service: BM25 locally, answers from a cheap model, per-query cost by formula.
AI code review in GitHub Actions: a workflow with curl and gh CLI
5 min · · автоматизация
One YAML file, and every pull request gets a comment with the model's findings. The workflow step by step, token permissions, fork limitations, and the cost of a single review.
LLM API error handling: retries, 429, 503 and a fallback model
5 min · · errors
Not every error is worth retrying, and not every one can be survived on the same model. Zukko error codes, backoff between attempts, and a fallback model chain in code.
Anthropic API from Russia: moving your code and Claude Code to Zukko
6 min · · development
Anthropic SDK code and Claude Code move to the gateway with an address and key change. Where the /v1 trap is, which Claude models are available, and how caching works.
An OpenAI API alternative from Russia: what to change in your code
6 min · · development
Code built on the OpenAI SDK moves to an OpenAI-compatible gateway with very few edits. Which lines to change, what to check in streaming and the Responses API, and how to pay from Russia.
How to OCR a PDF with an AI model: pages to images, then one API call
6 min · · development
Scans without a text layer can't be parsed the usual way. Render pages to images, send them to a model, and work out what a document will cost.