Anthropic halves Sonnet 5.5 cache-read price
- Source
- x.com
- Date
The change applies to the API only. Sonnet 5.5 cache reads now cost $0.10 per million tokens, while uncached input stays at $2 and output at $10. Agent loops reread the same system prompt, tool definitions and conversation history on every turn, so cached input is often the largest token category in an agentic workload. Halving the price of that category lowers the cost of long-running agent sessions more than the headline rate suggests. The gain depends on cache hit rate, so teams that reorder prompts, inject timestamps near the top, or rebuild tool lists per call will see less of it. Subscribers using Claude Code see no change, since usage limits stay the same. If you run Sonnet 5.5 through the API, check how much of your bill is cache reads before and after this week to see what the cut is worth for your traffic.
ICYMI we've cut the price of Sonnet 5.5 cache reads in half. In the Claude Platform, it's now $0.10 per million tokens (input is $2, output is $10). This means Sonnet 5.5 now runs ~20% cheaper on most agentic work. (API only, no change to Claude Code usage limits.)
Context
ClaudeDevs reported on October 8 that the Claude Platform price for Sonnet 5.5 cache reads is $0.10 per million , half the earlier rate, with input at $2 and output at $10 per million. A cache read is when a repeated part of a prompt, such as instructions and earlier conversation, is reused at a discount instead of being billed at the full input price. The post says this makes Anthropic's Sonnet 5.5 about 20% cheaper on most agentic work.
workflows often resend a large shared on every step, so the cache-read price can weigh heavily in their cost. The 20% figure is Anthropic's own estimate for most agentic work, not a measured result for any one job. The post also says the change is API-only and does not alter Claude Code usage limits.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…