This has no mention of what happens to the prompt cache, including the "learn more" link.
Knowing Anthropic, it wouldn't surprise me if it will result in a full cache miss/rewrite at fallback, with potentially up to 1M tokens in the context window.
You're paying in full for the "guardrails" embedded in the system prompt, prompt injections, refusals, fallbacks and everything else that may be caused by the service provider.
Knowing Anthropic, it wouldn't surprise me if it will result in a full cache miss/rewrite at fallback, with potentially up to 1M tokens in the context window.