Cost per AI feature: tokens, GPUs and infrastructure in one number
Combine model API spend with the GPU and serving infrastructure behind each AI feature, then divide by usage for a true cost per request.
Runs in
Claude · Slack
First optimization recommendation
The next day
ROI
Pays for itself with the first recommendation you act on
Playbook
What the agent does
From what Costory notices to what you decide. Costory suggests the next step in conversation, and you decide whether to go ahead.
Costory notices
Monthly, or when a feature's unit cost moves.
Costory investigates
01
Allocate the feature
Model spend plus the infrastructure the feature runs on.
02
Bring usage
Requests or conversations per feature, as custom metrics.
03
Formula
Full cost per 1,000 requests.
04
Price it
Compare with what the feature earns.
Where you see it
Claude
You decide
Product decides on pricing, limits or optimization.
Why it matters
Token cost is only part of an AI feature's cost. Vector databases, GPUs, queues and retries can add a lot on top.
Who it’s for
AI product leads, CTOs
Where it runs
Claude · Slack
What you get
What lands in front of your team
Full cost, not just tokens
Infrastructure included.
A per-request unit
Comparable across features.
Pricing input
Know your AI margins.
Sources and assistants
What it connects
Data sources
Example prompts
Or drive it yourself
Compute
What is the full cost per 1,000 conversations of the support bot, including model APIs, the vector database and serving infrastructure?
FAQ
Questions about this playbook
Which AI providers can Costory import?
OpenAI, Anthropic (API and claude.ai Enterprise), Azure OpenAI, AWS Bedrock, Google Vertex AI, OpenRouter, Cursor, ElevenLabs, Kling AI and BytePlus.
How long does this playbook take to set up?
Connecting your billing data and the Costory MCP takes under 30 minutes with Terraform or CloudFormation. The playbook itself takes minutes: pick the scope, the trigger and the Slack channel. The first billing data lands the next day, and the agent starts from there.
Can we adjust what the agent does?
Yes. You choose the trigger, the scope (team, service, environment), the channel and the format, and you can pause or change it at any time.
Does Costory change anything in our cloud accounts?
No. Costory reads billing exports and the metrics you connect, and has no write access to your cloud. Actions it takes create Costory objects only: alerts, reports, dashboards and events. Your team stays in control of every change.
Step-by-step guide in the Costory docs
Related playbooks
Run these alongside it
Costory notices
Daily, as LLM provider costs refresh.
LLM cost allocation by team, feature and customer
Allocate model spend from OpenAI, Anthropic, Azure OpenAI, Bedrock, Vertex AI and OpenRouter to teams, features and customers.
See the playbook
Costory notices
A feature's model cost per request rises, or a new model ships.
Choose LLM models and routing based on cost per feature
The agent tracks per-model spend for each AI feature across OpenAI, Anthropic, Bedrock and Vertex AI, and recommends where a cheaper model or a routing change could fit.
See the playbook
Costory notices
Monthly, or when a unit cost drifts beyond your threshold.
Track cost per customer, per request or per active user
Combine allocated cloud cost with your business and usage metrics to build unit costs that leadership can track over time.
See the playbook
Put this playbook on call
Included in every plan, from €250/month. 30-day free trial: connect in under 30 minutes, get your first optimization recommendation the next day.
First optimization recommendation
The next day
ROI
Pays for itself with the first recommendation you act on
Setup
About 30 minutes
Data residency
EU
Access
Read-only on your cloud