Use gpt-4o or gpt-4o-mini through Claude Code, billed against your OpenAI account, with the key locked in macOS Keychain. ToolPiper injects it server-side — your dotfiles, shell history, and screenshots stay clean.
Open ToolPiper → Settings → Cloud Providers → OpenAI → Add Key. Paste the key. ToolPiper stores it in macOS Keychain (encrypted at rest, never written to disk in plaintext) and returns a Keychain reference. The actual key string is never available to JavaScript or to Claude Code.
In ToolPiper → Endpoints → Add Endpoint → OpenAI (cloud). Pick a model — gpt-4o-mini for cheap fast work, gpt-4o for harder tasks. Save. The endpoint references your Keychain key by id, not by value.
ToolPiper → Docs → Claude Code → Configure for Claude Code. We write ~/.claude/settings.json with a ToolPiper dev token (not your OpenAI key) and add your OpenAI endpoint to Claude Code's /model picker.
Open any terminal.
claude
# /model → "OpenAI gpt-4o-mini (your key)"
# Every prompt now bills against your OpenAI account.Ask "how much have I spent in this session?" — ToolPiper's LogPiper telemetry surfaces per-session token counts (pre-pricing rollup). For full billing, the OpenAI dashboard is the source of truth.
ToolPiper signs OpenAI requests server-side. Your dotfiles stay free of secrets, screenshots can't leak the key, and Claude Code never sees it.
No marketplace markup, no token routing through us. ToolPiper Pro is a flat subscription; the per-token cost goes straight to OpenAI on your card.
Same recipe works for Anthropic Console, Gemini, Groq, DeepSeek, OpenRouter, Mistral, xAI, and Perplexity. One BYOK pattern; ten providers.
Three reasons. (1) Your key stays in Keychain — Claude Code's default flow puts <code class="font-mono text-xs text-white/70">ANTHROPIC_API_KEY</code> in env vars and dotfiles. (2) You can switch providers mid-session ("use my local Qwen") without restarting. (3) ToolPiper's 147 MCP tools come along for free.
Yes. Same recipe, but pick <strong>Anthropic (cloud)</strong> as the endpoint provider. Your Anthropic API key is BYOK, billed against your console account. Claude Code talks to ToolPiper, ToolPiper talks to Anthropic.
Yes. Configure model-level permissions in ToolPiper → Settings → Cloud Providers. The OpenAI Responses API also supports key-level scoping; combine the two for defense in depth.
Revoke it on platform.openai.com and update ToolPiper's Keychain reference. No rebuild, no Claude Code restart needed — ToolPiper picks up the new key on the next request. Old key string never existed outside Keychain.
ToolPiper is a free download. Configure once and Claude Code routes through your Mac.