AI agents · How Founders Use AI
How much do AI agents cost to run, and how do I keep the bill under control?
Token prices for equivalent quality fall roughly 10x a year, yet agent bills keep rising because agents burn about 50 times the tokens of a chat: every step re-sends the whole history. A simple task can cost a fraction of a cent while a long agent session runs several dollars. The levers that matter: prompt caching (up to 90% off repeated context), routing easy steps to cheap models (GPT-6 Luna, Claude Haiku 5.5), sending yes/no steps to a decision model like Jev, trimming history, and measuring cost per completed task rather than per token.
On the AI map, 29 October 2026 Decision modelsCoding agentsAgents that do tasks for youAI browsersNo-code automation with AI steps
Go deeper20 sources
-
Decisions API guide
OpenAI · Guide · Sep 2026
OpenAI's endpoint for probability, choice and score answers on GPT-6 Luna, about 10x faster than the Responses API, for routing and triage steps.
-
Jev means structured output is interesting again
Sean Goedecke · Article · Sep 2026
A clear, sceptical explainer of decision models: why answering with a choice instead of text is fast and cheap, and where ordinary structured output already does the job.
-
Welcome to LLMflation: LLM inference cost is going down fast
a16z (Guido Appenzeller) · Article · Nov 2024
The single chart that explains why what is unaffordable today is cheap next year.
-
LLMflation: 10x cheaper per year
a16z · Thread · Nov 2024
The headline numbers in thread form for a two-minute read.
-
AI Token Cost Over Time: Down 99.7%, Bills Up 3x
NavyaAI · Article · 2026
Names the paradox every founder hits: cheaper tokens, bigger bills.
-
AI Agents Burn 50x More Tokens Than Chats
LeanOps · Article · 2026
Explains the quadratic context growth that quietly multiplies agent costs.
-
Agentic AI Enterprise Token Cost
EY · Article · 2025
How large buyers model agent economics, useful when selling to them.
All 20 sources
-
AI Agent Cost: Token Economics & Optimization Guide
Cowork · Article · 2026
Concrete per-task cost ranges from cheap chatbot turns to $5+ agent runs.
-
Token Cost Trap: Why Your AI Agent's ROI Breaks at Scale
Klaus Hofenbitzer · Article · 2025
Walks through the exact math of an agent whose unit economics collapse.
-
Prompt caching with Claude
Anthropic · Article · Aug 2024
The feature that cuts up to 90% off repeated context, table stakes for agents.
-
Prompt Caching with OpenAI, Anthropic, and Google Models
PromptHub · Guide · 2024
One page comparing how each provider's caching discount actually works.
-
Context Engineering for AI Agents: Lessons from Building Manus
Yichao 'Peak' Ji (Manus) · Article · Jul 2025
Why KV-cache hit rate is the one production metric that decides agent margins.
-
AI Token Calculator
TokenCalculator · Tool · 2025
Estimate a task's cost across models before you commit to one.
-
AI Token Pricing Tracker
UsagePricing · Tool · 2026
Live per-model pricing so your cost model never goes stale.
-
AI Token Costs: Why Enterprise AI Bills Keep Rising
Optimum Partners · Article · 2026
Shows 72% of production cost sits outside the model invoice.
-
Inference Unit Economics: The True Cost Per Million Tokens
Introl · Article · 2025
The full stack of costs behind a token price, for founders selling AI products.
-
Prompt Caching for Anthropic and OpenAI Models
DigitalOcean · Guide · 2025
A hands-on implementation guide with before-and-after cost numbers.
-
What Is an AI Agent? (pricing and economics discussion)
a16z · Podcast · May 2025
Investors debate agent pricing and unit economics in plain language.
Listen here
-
Why 'Cheaper Tokens' Isn't a Good Reason to Own Your LLMs
ML6 · Article · 2025
Saves you from the premature self-host-a-model cost trap.
-
AI's Plummeting Prices Are a Software Story, Not a Hardware One
Weighty Thoughts · Article · 2025
Why the price curve should keep falling, and what that means for your roadmap.