3 posts
LLM API keys spend real money. How to keep them out of browsers and git, scope one key per app, rotate without downtime, rate-limit users and respond to a leak.
8 min read
Plain-language definitions of the LLM API terms on pricing pages and in SDK docs, with a worked cost example and the mistake each term commonly causes.
7 min read
A practical way to pick models for Claude Code, Codex CLI, Cline and other coding agents: what each tier is good at, cost per agent turn, and mixing tiers.
6 min read
Setup guides
Step-by-step setup for each tool, with the exact settings and known limits.
All setup guidesRun Claude Code on prepaid credits: set ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN, pin Opus, Sonnet and Haiku model ids, then verify with /status.
Anthropic format
Connect OpenAI Codex CLI to our gateway with a model_providers entry in ~/.codex/config.toml, a key env var and the Responses wire API, plus checks and fixes.
OpenAI format
Use Claude, GPT, Grok and DeepSeek in Cursor Chat and Agent via your OpenAI API key and Override OpenAI Base URL, with custom models, checks and known limits.
OpenAI format
Configure Cline in VS Code with the OpenAI Compatible provider: base URL, API key and model id for Claude, GPT, Grok or DeepSeek, then verify it and fix errors.
OpenAI format
Add our gateway to Kilo Code as a custom OpenAI Compatible provider in VS Code or in kilo.jsonc for the CLI, with model ids, auto-fetched models and fixes.
OpenAI format
Add our gateway to OpenCode as a custom provider in opencode.json with @ai-sdk/openai-compatible, store the key via /connect, pick models and fix errors.
OpenAI format
Run Aider through our OpenAI-compatible endpoint: set OPENAI_API_BASE and OPENAI_API_KEY, launch with openai/<model>, save it in .aider.conf.yml and fix errors.
OpenAI format
Add our gateway to Zed via language_models.openai_compatible in settings.json, enter your key, pick Claude, GPT, Grok or DeepSeek in the Agent Panel and fix errors.
OpenAI format