What
The price table built into Claude Code adds a $2 per million input, $10 per million output tier and moves Sonnet 5 onto it from the previous $3/$15 tier. /cost and usage estimates bill against this table, so reported Sonnet 5 spend drops by about a third. Unconditional, with no flag involved.
Details
- The new tier also sets cache writes at 2.5 (5-minute) and 4 (1-hour) and cache reads at 0.2 per million tokens.
- This is a static data table shipped in the build, not a figure fetched from the API, so it applies immediately on upgrade.
Evidence
pricing: "tier_2_10"
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Names in the bundle/cost
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on Speed up responses with fast mode touched a line naming /cost after this was published.
* **Usage credits turned on for subscription plans**: on a Pro, Max, Team, or Enterprise plan, your account must have [usage credits](/docs/en/costs#add-usage-credits-to-your-subscription) turned on, which allows billing beyond your plan's…fast-mode see the edit
Confirmed since
Anthropic's documentation has since written up /cost, on Claude Code changelog.
* Added to the Claude apps gateway: with `pricing:` set in `gateway.yaml`, signed-in Claude Code clients receive the same rates through managed settings, so `/cost` and telemetry match the spend meterchangelog see the edit
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agrees
Anthropic's documentation has since written up /cost, on Claude Code changelog.
Anthropic's release notes agree
Cost estimates (/cost, status line, --max-budget-usd) now include the 1.1× US-only-inference premium for data-residency workspaces