---
id: "nr-caching-now-decides-what-agents-cost-more-than-list-prices-do-8f0d19"
slug: "caching-now-decides-what-agents-cost-more-than-list-prices-do-8f0d19"
type: "raw_signal"
title: "Caching now decides what agents cost more than list prices do"
description: "Vercel cut the average cost of an Agent session by 67% just by reworking context and caching, with no change to billing rates."
observed_at: "2026-10-28"
record_date: "2026-10-28"
date_kind: "observed_at"
novelty: "notable"
source_platform: "newruntime.com"
topics: ["anthropic","claude"]
entities: ["Vercel","Vercel Agent","Vercel CLI","Slack","OpenAI","Anthropic","GPT-5.6 Luna","GPT-6.1 Sol","Claude Opus 5.5","DeepSeek Flash V4.1"]
related_patterns: ["agent-economics-moves-to-completed-work","harness-architecture-outlives-model-choice"]
source_url: "https://vercel.com/changelog/vercel-agent-sessions-now-cost-67-percent-less"
source_urls: ["https://vercel.com/changelog/vercel-agent-sessions-now-cost-67-percent-less","https://minimaxir.com/2026/10/cheap-llms","https://aws.amazon.com/blogs/machine-learning/groundhog-day-for-ai-agents-prompt-caching-patterns-for-using-openai-models-on-amazon-bedrock"]
why_it_matters: "Vercel cut the average cost of an Agent session by 67% just by reworking context and caching, with no change to billing rates. An analysis of OpenAI's and Anthropic's price cuts of up to 80% points to cache-read costs as an outsized part of agentic coding spend, and AWS published prompt-caching patterns for agent workloads on Bedrock. To cut agent bills, start with prompt structure and cache hit rates before switching models."
verification_level: "source-linked"
signal_type: "synthesis"
synthesis_of: [{"slug":"vercel-agent-sessions-now-cost-67-less-on-3cfbee","title":"Vercel Agent sessions now cost 67% less on average after context and caching rework","url":"https://newruntime.com/posts/vercel-agent-sessions-now-cost-67-less-on-3cfbee/"},{"slug":"a-dive-into-why-openai-anthropic-cut-llm-8966c7","title":"A dive into why OpenAI, Anthropic cut LLM prices by up to 80%","url":"https://newruntime.com/posts/a-dive-into-why-openai-anthropic-cut-llm-8966c7/"},{"slug":"groundhog-day-for-ai-agents-prompt-caching-patterns-3e941d","title":"Groundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock","url":"https://newruntime.com/posts/groundhog-day-for-ai-agents-prompt-caching-patterns-3e941d/"}]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:caching-now-decides-what-agents-cost-more-than-list-prices-do-8f0d19"
retrieval_nugget: "Vercel cut the average cost of an Agent session by 67% just by reworking context and caching, with no change to billing rates. An analysis of OpenAI's and Anthropic's price cuts of up to 80% points to cache-read costs as an outsized part of agentic coding spend, and AWS published prompt-caching patterns for agent workloads on Bedrock."
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/caching-now-decides-what-agents-cost-more-than-list-prices-do-8f0d19/","markdown":"https://newruntime.com/signals/caching-now-decides-what-agents-cost-more-than-list-prices-do-8f0d19.md","json":"https://newruntime.com/signals/caching-now-decides-what-agents-cost-more-than-list-prices-do-8f0d19.json"}
---

# Caching now decides what agents cost more than list prices do

## Retrieval answer

Vercel cut the average cost of an Agent session by 67% just by reworking context and caching, with no change to billing rates. An analysis of OpenAI's and Anthropic's price cuts of up to 80% points to cache-read costs as an outsized part of agentic coding spend, and AWS published prompt-caching patterns for agent workloads on Bedrock.

Vercel cut the average cost of an Agent session by 67% just by reworking context and caching, with no change to billing rates. An analysis of OpenAI's and Anthropic's price cuts of up to 80% points to cache-read costs as an outsized part of agentic coding spend, and AWS published prompt-caching patterns for agent workloads on Bedrock. To cut agent bills, start with prompt structure and cache hit rates before switching models.

From the Field Notes:

- [Vercel Agent sessions now cost 67% less on average after context and caching rework](https://newruntime.com/posts/vercel-agent-sessions-now-cost-67-less-on-3cfbee/) (2026-10-28)
- [A dive into why OpenAI, Anthropic cut LLM prices by up to 80%](https://newruntime.com/posts/a-dive-into-why-openai-anthropic-cut-llm-8966c7/) (2026-10-27)
- [Groundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock](https://newruntime.com/posts/groundhog-day-for-ai-agents-prompt-caching-patterns-3e941d/) (2026-10-27)

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Anthropic](https://newruntime.com/topics/anthropic.md): Explore the anthropic topic hub.
- topic hub: [Claude](https://newruntime.com/topics/claude.md): Explore the claude topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)