Get Warned Before Your LLM Balance Runs Out: Alert Levels, Email and Signed Webhooks
Pick an alert level from your real daily spend, choose email or a webhook, and run a small signed receiver in Node or Python that you can test with curl.
8 min read
7 posts
Use the Anthropic Messages Format Through a Compatible Gateway
Call Claude through a gateway with the Anthropic SDKs: base URL, headers, streaming, a tool-use loop and prompt caching, in Python, Node and curl.
7 min read
Give Every Project Its Own API Key and Spend Limit
One key per project and environment, each with a spend limit sized from real traffic, an expiry when it should end and an alert when it is blocked.
7 min read
Stream Tokens to a Browser with Server-Sent Events (Node and Python)
Relay a streaming LLM response from your server to the browser over SSE, keep the API key server-side, stop billing when the tab closes. Node and Python code.
8 min read
Switch an Existing OpenAI SDK App to a Different Base URL
Point a working OpenAI SDK app at another compatible endpoint with env vars or one line of code. Python, Node, curl, LangChain and the AI SDK, plus pitfalls.
6 min read
How to Estimate Your Monthly LLM API Cost (With Worked Examples)
A practical method to forecast LLM API spend: counting tokens, the hidden tokens people miss, how prompt caching changes the maths, and three worked examples.
7 min read
How to Use Claude Code with a Custom API Base URL (and Why You Would)
Point Claude Code at an Anthropic-compatible gateway with ANTHROPIC_BASE_URL: shell and settings.json setup, verifying with /status, model pinning and fixes.
8 min read
Setup guides
Connect a coding agent
Step-by-step setup for each tool, with the exact settings and known limits.
All setup guidesClaude Code
Run 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
Codex CLI
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
Cursor
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
Cline
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
Kilo Code
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
OpenCode
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
Aider
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
Zed
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