How it works — thinker

USD at Claude Opus 5.5 API list prices: fresh input $4, one-hour cache writes $8, cache reads $0.20, output $20 per million tokens. Checked November 4, 2026. Subscription allowances are not dollar bills.

The session bill uses 20 calls at 10¢ each, holding the cost mix and 200k cached tokens fixed to show how costs add up. The repeated-cost counter isolates that original context at 4¢ per call; the growing bars illustrate additional context accumulating, whose cost is not included in the counter. These are illustrations, not a measured session. The compression example starts with 200k cached tokens, removes 120k net of placeholders, and assumes 40k retained tokens need rewriting. Each call adds the same $0.060 of fresh input, new writes, and output in both cases. The example isolates this context’s lifetime: it assumes a warm cache, no further cuts, no extra rereads, and identical work. Actual write size depends on reusable cache boundaries; recovery depends on later calls. Instruction and profile examples are separate illustrations and are not added to compression savings. Trimming 8k instruction tokens avoids 160k context-read tokens over 20 later calls in the same session; dollar savings depend on fresh input, writes, and reads. The trimming example assumes the removed context would otherwise remain in every later request, with no intervening compression. The profile example counts each correction it prevents as one extra call re-reading the 200k context; a real correction also costs the prompt, the new output and any rewrite, and a profile does not prevent every correction. “1 in 9 exchanges” is the share of exchanges on one machine, over 118 sessions, in which the person repeated a preference or lesson a previous session had already recorded; it is one machine, not a general figure. The profile itself is about 1.5k tokens, served once per session and after each compaction. Figures exclude the tokens spent reading sessions into the profile; they are illustrative read-token reductions, not measured outcomes or net dollar savings.

The final runway visual is conceptual: reducing repeated context can leave more of a token budget available for useful work. It does not specify an increase in tasks, subscription allowance, or session length. Rewrites and learning also consume tokens; actual results depend on the workload and agent.

Compression availability depends on the agent. Instruction trimming and the memory profile are separate features. See how Thinker works with your agent →