Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
GPT-6.1 Sol via API: setup, pricing and caching in Zukko
5 min · · models
How to call GPT-6.1 Sol with a Zukko key, what it costs, how to check caching via cached_tokens, and which models to compare it with.
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.
LobeChat (LobeHub): connect Zukko via the UI and environment variables
7 min · · development
LobeChat, now LobeHub, works with any OpenAI-compatible API. We cover setup in the UI and via env, a cost estimate and the usual errors.
Cherry Studio: add Zukko as an API provider
5 min · · development
Cherry Studio connects third-party APIs as providers. Here is what to put in API Host, how to add models, and why you must switch the provider on.
Chatbox: connect your own Zukko API key
5 min · · development
Chatbox lets you add your own provider with your own key. We cover the API Host and API Path fields, adding models and typical errors.
LibreChat: Zukko as a custom endpoint in librechat.yaml
5 min · · development
LibreChat connects third-party providers through librechat.yaml. Here is a ready config for Zukko, the Docker mount and the usual errors.
Open WebUI: connect to Zukko via Docker and the admin panel
6 min · · development
Open WebUI works with any OpenAI-compatible API. Here is the launch command, the Connections setup, a cost estimate and a list of common errors.
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.
Qwen vs GLM — two cheap families and what separates them
3 min · · сравнение
Cheap models are plentiful now, and choosing between them is no longer about price. What actually separates Qwen from GLM in practice.
Kilo Code — custom API setup and model selection
2 min · · kilo code
Kilo Code lives inside VS Code and works with any compatible API. Setup is an address, a key, a model name.
OpenHands — connecting your own model through an API gateway
3 min · · openhands
OpenHands executes commands in an isolated container. The model underneath is your choice — address and key.
Goose — pointing it at your own API provider
3 min · · goose
Goose is an open-source agent with an extension system. The provider is yours to choose.
GLM 5.3 Flash — $0.04 per million, and where that fits
3 min · · glm
Four cents per million tokens. A model for work that needs speed and simplicity, not deep reasoning.
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.
Claude Code, opencode, Aider, Cline — how harnesses differ
3 min · · harness
They all read your project and edit code. The differences are in how much they ask, how much they spend, and where they live.
How to compare API gateways honestly — six checks in half an hour
3 min · · шлюз
Comparing price lists is easy and tells you little. Six checks you can run in half an hour that actually affect the bill.
A model vanished from the model list — why, and what to do
3 min · · диагностика
The model list isn't a year-long catalogue — it's a snapshot of what works right now. Here's why it changes.
GLM 5.3 vs Claude Opus 5.5 — when paying more pays off
3 min · · сравнение
$0.10 against $0.30 per million, 128K against a million of context. Where cheap wins and where it quietly costs more.
GLM 5.3 — setup and what it's actually good for
3 min · · glm
$0.10 per million tokens in and out, against $1.40 and $4.40 official. Where GLM 5.3 fits, and where it doesn't.
The agent says "I have no access to your files" — what broke
3 min · · harness
The model answers "I cannot access your project" even though the agent is configured. Almost always it's tool calls, not the model.
Connecting opencode to an API gateway in five minutes
3 min · · opencode
opencode is an open-source terminal agent. It works with any compatible API — you just supply the address and key.
What an agent harness is, and how it differs from an IDE plugin
3 min · · harness
A model on its own cannot read files or run commands. The harness does that. Here is how it works.