Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
How to test prompts: a simple eval harness in Python
4 min · · development
"Works for me" is not a test. We build a small script that runs a prompt over a test set and several models and shows whether it actually got better.
Temperature and top_p: what they do and where you can no longer set them
4 min · · development
Temperature and top_p control how varied answers are. How they work, why newer Claude models no longer accept them, and what to use instead.
How to list available models via the API and survive model changes
3 min · · models
The model catalog changes: new models arrive, old ones are switched off. How to fetch the current list and write code that survives a model change.
GPT-5.6 Luna: when a low-cost model is enough for bulk tasks
5 min · · models
For bulk classification and extraction, cost per request matters. We calculate what Luna costs at real volumes and show how to test it on your own data.
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.
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.
Local LLM or API: hardware, quality, cost, and privacy
6 min · · сравнение
Ollama on your own machine or a model through an API? A comparison by hardware, context, quality, cost, and privacy — with a calculation and one codebase for both.
Claude 529 overloaded error: what it means and how to handle it
6 min · · errors
A Claude 529 error isn't your limit or your balance, it's API overload. How to retry, when to switch to a fallback model, and what you'll see through a gateway.
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 ranking 2026: intelligence index and price as of October
6 min · · models
A ranking of Claude, GPT, Gemini, DeepSeek, Qwen and GLM models by intelligence index, with per-token prices as of October 7, 2026 — and why a composite score doesn't replace testing on your own tasks.
What tokens are in neural networks and how they add up to a price
6 min · · models
A token is the unit a model reads text in and the unit you pay in. We cover input, output, cache and context, and work out the cost of a request with a formula.
DeepSeek in Russia: V4 Pro, V4.1 Flash and V4 Flash on one key
5 min · · models
Three DeepSeek models on one key and balance with Claude, GPT and Gemini. We compare V4 Pro, V4.1 Flash and V4 Flash by price, index and image input, and do a budget.
Gemini in Russia via API: Gemini 3.8 Flash and 3.7 Flash on one key
5 min · · models
Google does not support the Gemini API in Russia, but Gemini 3.8 Flash and 3.7 Flash are available through Zukko with payment in rubles. Setup code, prices and limits.
Claude in Russia: how to use it in a chat, via API and in Claude Code
6 min · · models
Anthropic does not support Russia, but Claude models are available through Zukko: a browser chat, the API and Claude Code on one key, paid in rubles. Setup and prices.
ChatGPT in Russia: how to use GPT models in a web chat and via API
6 min · · models
Official ChatGPT does not support Russia, but GPT models are available through Zukko: a browser chat, an API and payment in rubles. Models, prices and first steps.
Chinese LLMs via API: DeepSeek, Qwen and GLM with one key
6 min · · models
Seven DeepSeek, Qwen and GLM models in one table: prices, context, images and index. Plus paying from Russia and switching between them with one key.
GPT-6 Sol or GPT-6.1 Sol: choosing by price, cache and index
6 min · · models
Two models from one line with the same context window and different prices. We compare the table and work out plain requests and a cached agent.
Reasoning tokens: what model reasoning costs and how to keep it in check
6 min · · models
A short answer, yet thousands of output tokens in your stats — that's model reasoning. Where it comes from, what it costs, and how to control it in OpenAI and Anthropic format.
Claude Opus 5.5 or GPT-6 Astra: prices, index and agent session cost
7 min · · сравнение
Two flagships compared on what can be checked: price list, cache, strength index and the cost of one long agent session, with formulas.
GPT-6.1 Sol or Claude Sonnet 5: price, cache, API format, choice
6 min · · сравнение
Sonnet 5 is cheaper on input and output, Sol on cache. We work out where each one costs less and show how to compare quality on your own tasks.
DeepSeek or Gemini Flash: V4.1 Flash vs 3.8 Flash on price and strength
6 min · · сравнение
Two popular low-cost models with a 1M context. What prices and the intelligence index say, where caching changes the math, and how to decide on your data.
The cheapest models for bulk tasks: prices, math and how to choose
6 min · · экономия
The six cheapest models in the catalog in one table: what tens of thousands of requests cost, and which criteria decide between them.