Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
Saving tokens in Codex: a checklist for working through the API
6 min · · экономия
Nine habits and settings that cut Codex spend when you pay per token: from AGENTS.md and task size to model choice and cache.
Aider: what this AI coding assistant is and how it works with git
6 min · · агенты
Aider is a command-line tool that edits your repository on request and commits every change. Here is how it works and what a session costs.
Embeddings in plain words: what they are and why search needs them
5 min · · models
An embedding turns text into a set of numbers you can use to find similar meaning. We explain without math, where embeddings come from, and when you do not need a vector database.
DeepSeek not working in Russia: what to check and how to keep working
5 min · · errors
The chat will not open or the API is silent. How to tell a service outage from a network or key problem, and how to avoid stopping work.
Qwen Code: what it is and which models you can run in it
5 min · · агенты
Qwen Code is often confused with the Qwen Coder model. We explain that it is a separate program, how it works and which models it can use.
Creating Excel tables with a neural network: structure, formulas and an XLSX file
4 min · · автоматизация
The model describes the table as JSON, and an openpyxl script builds a finished XLSX with formulas, formats and totals. The schema and the code.
Translating books with a neural network: keeping style and names over hundreds of pages
5 min · · автоматизация
How to translate long texts in chunks without losing names, terms and tone: a glossary, the tail of the previous translation, cache and the price of a whole book.
Qwen API price: a calculation for Qwen 3.8 Max and 3.8 Flash on typical tasks
6 min · · экономия
Three typical tasks, formulas and totals for Qwen 3.8 Max and Qwen 3.8 Flash, plus a note on how cache behaves.
GitHub Copilot in VS Code: setup and connecting your own models
6 min · · IDE
Enable GitHub Copilot in VS Code, then connect your own models through Custom Endpoint with an API key, and see what works without a subscription.
Claude Opus: what the senior model is for and when it pays off
5 min · · models
Opus 5.5 in Zukko costs twice as much as Sonnet 5.5. When the extra spend is justified, when the smaller model is enough, with a worked example.
Cline or opencode: an agent in VS Code or in the terminal
6 min · · сравнение
Cline lives in VS Code, opencode in the terminal. A comparison by scenarios, context control, connecting your own models and cost.
Roo Code not working or hanging on API Request: what to check
6 min · · errors
Roo Code stays silent, hangs on API Request or throws errors. We go from simple to complex: key, address, model, context, timeouts and limits.
Cline vs Roo Code: comparing the two VS Code agents in 2026
6 min · · IDE
Roo Code grew out of Cline, then the paths split. We compare modes, rules and token spend, and cover what the Roo Code shutdown changes.
OpenAI Codex: what it is, its parts and how to use it
6 min · · агенты
Codex is a coding agent that reads a project, edits files and runs commands. Its parts, how it differs from ChatGPT and the payment options.
Cursor AI pricing: the subscription vs paying per token on your own key
6 min · · экономия
A Cursor subscription and per-token billing on your own key are calculated differently. Here is the formula and a worked week of agent work across several models.
Is Qwen Code free: what changed and how to keep working
5 min · · payments
Qwen Code itself costs nothing, but model access is now paid. We cover what ended, which options remain and what working on your own key costs.
Free Qwen API: Alibaba Cloud quotas and the price after them
6 min · · экономия
A free Qwen quota exists, but it has an expiry date and is tied to a region and a model. We go through the terms and count what comes after.
DeepSeek API key: how to get one and which base_url to use
5 min · · API keys
Two ways to a DeepSeek key: the official platform and the Zukko gateway. API addresses, model names, checking the key and common connection errors.
DeepSeek API: what it is and how it differs from the DeepSeek chat
5 min · · models
A chat is for people, an API is for programs. What the DeepSeek API is, which models exist, how tokens are billed and how to send a first request.
Neural network API key: what it is, where to get it and how not to lose money
5 min · · API keys
A key is a password to your balance, not to a chat. Where keys come from, how to test one, and how limits protect your money.
Vibe coding: how to start and ship a first project in an evening
5 min · · development
A beginner plan: pick a small utility, set up an agent, phrase the task, check the result and keep everything in git.
Grok API key: getting an xAI key and calling Grok 4.7 through a gateway
5 min · · API keys
Two routes to Grok: an xAI console key, or a gateway key paid by SBP, MasterCard or crypto. Steps, a request example and what it costs.
Vibe coding for free: what you can do without money and what comes next
6 min · · экономия
An honest look at free options for vibe coding, their limits, and the arithmetic of what an hour on cheap models via API costs.
How to register at DeepSeek from Russia and get API access
5 min · · payments
Registering on the DeepSeek platform and getting API access from Russia: the steps, where people usually get stuck and how to reach DeepSeek models through a gateway with SBP payment.