Setup guides

Switching an existing integration to a different billing route is usually a base URL change, not a rewrite. These walk through it tool by tool.

Two environment variables, verification via curl, and the four errors people actually hit.

Where the base URL override lives, and how to confirm requests are routing.

One base_url argument. Python, Node and curl examples.

OpenAI and Anthropic SDKs from Node: the capitalisation trap, doubled paths and a dependency-free fetch version.

Use one client across vendors, and read the exact model ID off /models.

Using Claude inside your tools

Add your own key, override the base URL, and pick a model per task.

Sync, streaming, async and raw HTTP examples — plus the headers that cause most 401s.

Request/response mapping table, tool calling differences, and a shadow-mode cutover plan.

Set the endpoint on the chat model; chains, agents and parsers stay unchanged.

What actually drives the bill — and why it is usually context resends, not message count.

Eight levers ranked by effect, with code for the two that matter most.

Which parts of the contract are portable, and the three features that are not.

Log usage per request, attribute it, and alert on change rather than totals.

What the 50% batch discount and 10% cached-input rate really buy — and when waiting 24 hours saves nothing.

401, 404, 429 and 529 — what each actually means and the exact fix.

Three axes enforced per model, correct backoff, and why parallelism causes most throttling.

Own-key failures diagnosed: restart behaviour, doubled paths, quota that will not move.