Claude API

Claude Haiku 5.5 - claude haiku 5 5 launch sonnet 5 5 cache price cut a open folding hand fan standing upright

Anthropic Launches Claude Haiku 5.5 and Reduces Sonnet 5.5 Caching Costs

Anthropic has launched Claude Haiku 5.5, its cheapest and fastest small model, at up to 90% lower per-token prices than Haiku 4.5, and halved the cache read price on Sonnet 5.5. We explain the two price tiers, the tokenizer catch, the benchmarks and early customer results, the arithmetic behind the 20% Sonnet saving, the new monthly API credits for Max and Team plans, and the breaking changes developers must handle before switching.

Read more
distillation attacks anthropic charge rejected requests a parking meter on a post

Anthropic to Charge for Rejected Requests to Prevent Distillation Attacks

Distillation attacks are the reason Anthropic has started billing again for some requests Claude refuses before answering. From 24 September 2026, blocked requests in three categories, bio, frontier_llm and reasoning_extraction, are charged at the refusing model’s input rates. This article explains what each category covers, the 114 days when refusals were free, what a billed block costs and what developers should change.

Read more
anthropic playground workbench claude api testing a jointer plane lying flat with a closed loop handle

Anthropic Rebrands Workbench as Playground for Claude API Testing

Anthropic retired the legacy Workbench on 17 August 2026 and shipped Playground the next day. The replacement is stateless: no saved prompts, no version history, no variables, no evals and no sharing, with nothing stored on Anthropic’s servers. In exchange it supports every Messages API parameter, ships templates for server-side features such as code execution and web search, shows the full SDK request alongside the response for every run, and exports to code. Three experimental prompt endpoints were retired alongside it, and the export window for Workbench data closed permanently on 1 September 2026.

Read more
CHAT