Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
6 min · · API keys
Where free keys on GitHub come from, why using them is dangerous for you and for the owner, and how to protect your own key from the same leak.
5 min · · errors
A wrong model id, an overflowing 128K context, the key, the balance, limits: the typical causes of GLM API errors and a quick way to find yours.
4 min · · models
How to call grok-4.7 through an OpenAI-compatible API, what to do about the 256K context limit and what typical requests cost. Plus a comparison with Grok 4.6.
5 min · · errors
An Anthropic key suddenly answers "organization has been disabled". What the error is, what to check, and how to move the SDK and Claude Code to another provider.
4 min · · development
A small Express server between your frontend and the model API: the key stays on the server, and models, request size and rate are capped.
4 min · · development
Ready code for DeepSeek V4.1 Flash and V4 Pro on the OpenAI SDK: a request, streaming, JSON parsing and careful error handling.
6 min · · errors
Step-by-step Gemini API diagnostics: from checking status and region to a leaked key, 429 and 503 errors and a typo in the model name.
5 min · · сравнение
Google offers two doors to Gemini: an AI Studio key or a Google Cloud project. We compare them and show a third route through a gateway.
5 min · · development
A working Gemini API example in Python with no extra library: change base_url in the OpenAI SDK, add streaming and JSON, and compare with google-genai.
6 min · · API keys
Two request formats solve the same task but differ in details that break code when porting. A comparison of structure, tools, streaming, cache and headers.
5 min · · development
The official anthropic package for Python just needs a different address. We cover base_url, the key, streaming, token counting, caching and errors.
5 min · · errors
OpenAI clients send the key in Authorization, Anthropic clients in x-api-key. What the gateway accepts and how to tell from the response where the key got lost.
6 min · · development
The agent reads files and runs commands, so security settings belong before the first launch. A checklist: permissions, secrets, sandbox, a separate key with a limit.
5 min · · API keys
Step by step connection to Grok 4.7, 4.6 and 4.5 through a gateway: key, address, first request in curl and Python, streaming, images and payment by SBP or crypto.
5 min · · API keys
Which variable the SDK needs, which one Claude Code needs, where to get a key and how to set it on Windows, macOS and Linux without it reaching git.
5 min · · development
A short reference to the Chat Completions endpoint. Each parameter with an example, the response and usage format, gateway-specific notes, and the cost of one reply.
6 min · · errors
Claude Code cannot open a connection to the API. We check the address, proxy, DNS and network with three curl commands and find the cause from the result.
5 min · · development
Fix quality depends on what you show the model. The data to include about the error, a prompt template, asking for a minimal diff, and verifying with a test.
4 min · · development
How to point ChatOpenAI from LangChain.js at the Zukko gateway: one baseURL setting, streaming, tool calls and a spend check.
5 min · · автоматизация
DeepSeek V4 Pro accepts images, so it can read text from screenshots and scans. Python code, a JSON mode, accuracy checks and a cost calculation for 1,000 pages.
7 min · · автоматизация
Open WebUI lets you upload documents and ask questions about them. We show how to create a knowledge base, which settings affect answer accuracy, and what a single question costs.
6 min · · models
How to call claude-sonnet-5-5 from Python and curl, what a typical request costs with and without cache, and how it differs from Sonnet 5 and Sonnet 4.6.
6 min · · development
Schema, sample data and a query plan in the request to the model, an EXPLAIN check and read-only access. Working Python code and a cost estimate.
5 min · · development
The langchaingo library accepts any OpenAI-compatible address. We show the client, a request, streaming and a templated chain in Go, and estimate call costs.