Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
AI for Word documents: create and edit DOCX through an API
4 min · · автоматизация
A model cannot save a file into Word, but it can return structure and text. A practical python-docx plus API pipeline for creating and editing documents.
LM Studio vs Ollama: which to pick for running local models
6 min · · models
Both programs run models on your computer and expose an OpenAI-compatible API. We cover the differences and count when local running loses to the cloud.
Which AI is best for lawyers: tasks, risks and checking answers
6 min · · бизнес
There is no universal best AI for lawyers, but there is a method of choosing. We cover tasks, hallucination and data leak risks, and a way to check answers.
LangChain: what it is, what it consists of and when you really need it
5 min · · development
What LangChain is and which packages it consists of, which tasks it helps with and when the plain OpenAI SDK is enough. We compare code and spending.
OpenAI SDK: what it is and why it works with more than GPT models
5 min · · development
The OpenAI SDK is an ordinary wrapper around an HTTP API. That is why you can point it at another address and use Claude, Gemini or DeepSeek without changing your code. Here is how, and where the limits are.
GLM API free: what is really free and what GLM 5.3 Flash costs
6 min · · models
Free offers around GLM exist, but with caveats. We look at what usually hides behind the word free and calculate how many requests one dollar buys on GLM 5.3 Flash.
Claude Haiku vs Sonnet vs Opus: how the lines differ and what the API has
5 min · · models
Haiku, Sonnet and Opus set three levels of size, price and strength. We explain the lines, the Claude list in the gateway API and a light-model replacement when Haiku is not in the catalog.
Fine-tuning or RAG: what to choose to make a model work with your data
6 min · · models
Fine-tuning changes how a model behaves, while RAG and long context give it facts. We compare three approaches by cost, effort and freshness and give a rule for choosing.
RAG explained in plain words and when you really need it
5 min · · models
RAG adds found fragments of your documents to the request to the model. We explain the design without jargon and calculate when long context is simpler.
Cline: what this VS Code agent is and what it costs to run
6 min · · IDE
Cline reads your project, edits files and runs commands with your approval. Plan and Act modes, connecting your own key, and the cost of a typical task.
Claude Code: what this agent is and how it differs from a Claude chat
6 min · · агенты
Claude Code works not in a chat window but in your project folder: it reads files, edits them and runs commands. What it can do and what it costs in tokens.
OpenAI API key example: using a key in curl, Python and Node.js
5 min · · API keys
Ready examples of passing an API key in a header, environment variables and an SDK, the typical format mistakes, and a key check with a /v1/balance request.
Gemini API for free: what the free tier gives and its limits
6 min · · API keys
The Gemini API free tier explained from Google's documentation: limits, regions, data terms and the point where paying per token is simpler.
Vibe coding in Russia: which tools work and what they cost
6 min · · агенты
Which vibe coding tools you can connect to models through a gateway, how to set them up and what an hour of agent work costs.
OpenAI Python SDK: timeouts, retries, errors and raw responses
5 min · · development
The openai client for Python does more than create(). We cover timeouts, retries, exceptions, raw responses and streaming, using a gateway as the example.
Qwen API key: how to get one from Alibaba Cloud or via a gateway
5 min · · API keys
Two ways to a Qwen key: the official one in Model Studio and a single gateway key. Steps, addresses, model ids and a sample request.
OpenAI Batch API: what it is, when it pays off and what to use via a gateway
5 min · · экономия
A batch API trades instant answers for a discount. We explain how it works at OpenAI and Anthropic, which tasks it suits, and what to use instead when you work through a gateway.
AI document translation for Word files that keeps formatting
4 min · · автоматизация
Sending a whole DOCX to a model as plain text loses the formatting. We translate paragraph by paragraph, put the text back in place and estimate the cost.
Claude Desktop in Russia: What It Is and What to Use Instead
5 min · · payments
The Anthropic desktop app is tied to an account and a subscription. Here is what it does and three working replacements on a gateway key with payment from Russia.
Free AI for programming: what is actually available
5 min · · development
Free AI coding tools exist, but each one has a price in limits, hardware or time. We go through the options and calculate what a paid minimum costs.
DeepSeek context window: its size and how to use it without overpaying
5 min · · models
The window size of current DeepSeek models in Zukko, how it differs from the answer length, and how to measure a request in advance and price it without surprises.
Gemini API key: how to get one and what to do if it does not work
6 min · · API keys
Two ways to a Gemini API key: a Google AI Studio key and a Zukko gateway key. Steps, request examples, safe storage and common problems.
Claude Code in Russia: installation and use without an Anthropic subscription
5 min · · IDE
Install Claude Code, point it at a gateway with two variables and pay per token by SBP, MasterCard or crypto. Plus the first-run errors and how to fix them.
GLM API key: how to get a key for GLM 5.3 and which URL to use
5 min · · API keys
A GLM key can come from the Z.ai platform or from a gateway. We show both routes, the correct addresses, model ids and a cost comparison on an example.