Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
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.
AI model API prices in October 2026: Claude, GPT, Gemini, DeepSeek
7 min · · сравнение
A price table for 21 models: the official vendor price and the Zukko price for input, output and cache as of October 7, 2026, how to read it, and what a typical monthly volume costs.
Free AI model API: what you can actually get without paying
5 min · · экономия
An honest look at free API access to AI models: a $0.50 bonus for subscribing to a channel, the cheapest models, how many requests that covers, and how to avoid overspending.
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.
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.
Which model to use in Claude Code: slots, prices and the index
6 min · · IDE
Claude Code takes its models from several environment variables. Here's what to put in each slot by price and index, and what a session costs.
Data labeling with an LLM: a 50,000-row dataset on a cheap model
6 min · · автоматизация
How to label a dataset with a cheap model: instruction, JSON output, a Python script, sample review and what 50,000 rows cost.
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.
LLM model cascade: cheap model first, strong model on escalation
5 min · · development
How to build a cascade: the cheap model answers first, hard cases go to the strong one. Python code, threshold calibration and a cost formula.
What a Claude Code agent costs: a step-by-step session with cache
7 min · · агенты
What an agent's bill is made of, a 30-step session worked out on Opus 5.5 and Sonnet 5, where to see actual spend and how to set a ceiling.
Claude Fable 5.1 or Opus 5.5: when the pricier model is worth it
6 min · · сравнение
Fable 5.1 costs 8.7 times more per token than Opus 5.5, and its strength index is lower. When it is still worth testing, and how to tell whether it pays off.
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.
Qwen 3.8 Flash via API: setup, pricing and bulk text tasks
5 min · · models
The junior model of the Qwen 3.8 line for text tasks at volume. How to connect it, what it costs, and what to compare it with before you launch.
GPT-6 Luna via API: the low-cost GPT-6 for bulk text tasks
6 min · · models
The cheapest GPT-6 model in the catalog. How to connect it, what it can't take as input, and what labelling 100,000 messages costs.
DeepSeek V4.1 Flash via API: setup from Russia and pricing
5 min · · models
How to connect DeepSeek V4.1 Flash with a Zukko key and pay from Russia, what typical workloads cost, and which tasks the model suits.
Claude via /v1/messages or /v1/chat/completions: what happens to caching
5 min · · экономия
Claude answers in both formats, but only the Anthropic format gives the cache discount. The cost difference and how to switch your code and tools.
Prompt caching: how cache reads and writes are billed in Zukko
7 min · · экономия
What the bill is made of when prompt caching works: fresh input, cache reads, cache writes and output. The formula and two examples at current prices.
The agent went in circles and burned the budget — catching it early
3 min · · агенты
One task ate a month's budget — nearly always a loop. The causes, and three ways to protect yourself.
Subscription or pay-per-token — how to find the break-even point
3 min · · цены
The subscription-versus-tokens argument is settled by arithmetic, not opinion. Here's the crossover point.
What an hour with an agent actually costs
3 min · · цены
An agent resends the whole conversation on every step. Why spend grows non-linearly, and what to do about it.
Saving on repeated requests: caching via X-Zukko-Cache and temperature:0
4 min · · API
The same request twice should not cost twice. Here is how response caching works and which scenarios actually benefit from it.
The cheapest model for a specific task
4 min · · models
A model's price can't be guessed from its name. How to check it, measure real per-request cost, and not overspend while testing.