Claude API11 min read
Claude Prompt Caching: Cut API Costs and Latency
Claude prompt caching stores a stable prompt prefix so cached reads bill at ~10% of input price — how cache_control works, the TTLs, and the gotchas.
Claude prompt caching stores a stable prompt prefix so cached reads bill at ~10% of input price — how cache_control works, the TTLs, and the gotchas.
Claude API pricing per million tokens: Opus 4.8, Sonnet and Haiku rates, batch's 50% cut, prompt caching, and worked cost examples.
Learn how to use Claude API: get an API key from the Anthropic Console, understand the Messages API, and make your first request in curl or Python.
Claude API error 500 from api.anthropic.com: what api_error and 529 mean, exponential backoff with jitter, retry caps and request_id logging.