Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
opencode agents: setting up roles, models and tools
5 min · · агенты
A custom agent in opencode is a role, a model and a set of permissions. A working config where a cheap model handles routine work and a stronger one edits code.
Plan mode in Claude Code: plan first, then edit the code
6 min · · агенты
In plan mode Claude Code reads your code and proposes a plan but edits nothing until you agree. How to enable it, use it and what it costs.
Buying AI tokens: how a dollar balance works and what $5 gets you
5 min · · payments
Tokens at a gateway are not a package but a dollar balance. We look at what is charged to it and calculate how many requests $5 covers.
Paying for AI without a fee: is it possible and how to calculate the overpayment
5 min · · payments
There is almost always a fee when you top up. We show what it consists of, calculate it for SBP and card, and give a formula for how many rubles you need for N dollars.
Chatbot memory: how to store conversation history without paying twice
6 min · · development
The model does not remember earlier messages: you send the history with every request. We look at how dialogue cost grows and what keeps it in check.
How much an AI agent costs: a step-by-step model spend calculation
8 min · · агенты
Agent cost is set by the number of steps, context growth, cache and the model. A formula, three examples with arithmetic and a calculator you can plug your own numbers into.
Saving tokens in opencode: a checklist of settings and habits
6 min · · экономия
opencode spend comes from habits and a few lines of config. A checklist you can verify: what to turn on, what to remove, and how to see the result in the dashboard.
Claude Code with Qwen, GLM and DeepSeek models through one key
7 min · · IDE
Claude Code is not tied to Claude: the model is set by a variable. A configuration for Qwen, GLM and DeepSeek, a session calculated, and how to keep Opus for the hard parts.
How much Cline costs: the extension is free, you pay for tokens — a calculation
6 min · · экономия
With your own key Cline sells no model subscription: you pay for tokens. A workday on several models, calculated, and how to stay within budget.
Project rules in Qwen Code: context files and token savings
5 min · · агенты
How to explain project rules to Qwen Code once: QWEN.md, path-conditional rules, skills and MCP, and how many tokens each such file costs.
LangChain text splitters: how to cut text into chunks correctly
5 min · · development
How to choose chunk size and overlap in RecursiveCharacterTextSplitter, why you should count in tokens and how to check the count against an exact token number.
LangChain RAG: a working example with a model via a gateway
5 min · · development
We build a simple RAG with LangChain: documents, chunks, vector search and a model answer via a gateway. We count what a question costs and trim wasted tokens.
Paying for AI in rubles: SBP, a dollar balance and the exchange rate
5 min · · payments
Rubles paid via SBP turn into a dollar balance at the rate on the payment date plus the payment page fee. The formula, a top-up table and the price of requests in rubles.
Grok API price: cost of Grok 4.7, 4.6 and 4.5 with examples
6 min · · экономия
We price requests to Grok 4.7, 4.6 and 4.5 in Zukko on three scenarios and compare with official xAI prices. Formulas are shown and the arithmetic can be checked.
Codex limits: why they run out and how to keep working
6 min · · errors
Codex subscription limits are consumed by OpenAI's rules and cannot be reset. What drives usage, and how to continue on a key with a dollar limit.
Codex pricing on your own key: a per-token cost calculation
6 min · · экономия
Three workload profiles, one formula and a table by model. What drives the Codex bill and how to estimate it in advance.
Memory Bank in Cline: Setting Up Project Memory for the Agent
6 min · · агенты
Memory Bank gives Cline memory between sessions through a set of markdown files. Structure, setup via rules and the token price of that memory.
DeepSeek API for free: is there a free tier and what is the minimum cost
5 min · · экономия
We do not promise free access, but the minimum is very low. A formula-based count of how many requests fit into one dollar.
DeepSeek API price: cost of V4 Pro and V4.1 Flash worked through
5 min · · models
What requests to three DeepSeek models cost: the formula, three typical scenarios at 10,000 requests, the role of the cache and a usage-based cost script.
How much the Gemini API costs: 3.8 Flash and 3.7 Flash calculated on examples
6 min · · экономия
A price table for Gemini 3.8 Flash and 3.7 Flash and three calculations with formulas: a chatbot, bulk classification and a long document, with and without cache.
Claude Projects: What They Are and How to Build the Same Workflow via API
5 min · · API keys
Projects in claude.ai store instructions, documents and chat history. Through the API the same is built from a system prompt, documents in context and a cache.
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.
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.
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.