Resources / AI Agent Cost Estimator
Describe one run of your agent and how often it runs. The estimator prices it on nine Claude, GPT and Gemini models at their official list prices, checked on 3 October 2026.
Your agent
Model cost per month
Same workload on every model, per month
The full report adds the cost at 2× and 10× volume and shows where caching and your choice of model save the most. It also lists the hosting and monitoring costs to budget next to the model bill.
Prices used
| Provider | Model | Input | Cached input | Output | Note |
|---|---|---|---|---|---|
| Claude Opus 5.5 | $4.00 | $0.200 | $20.00 | ||
| Claude Sonnet 5.5 | $2.00 | $0.200 | $10.00 | ||
| Claude Haiku 4.5 | $1.00 | $0.100 | $5.00 | ||
| Claude Fable 5.1 | $10.00 | $0.250 | $50.00 | ||
| gpt-6-astra | $10.00 | $1.000 | $50.00 | ||
| gpt-6.1-sol | $2.00 | $0.100 | $10.00 | ||
| gpt-6-luna | $0.10 | $0.010 | $0.50 | ||
| Gemini 3.1 Pro Preview | $2.00 | $0.200 | $12.00 | Prompts up to 200k tokens | |
| Gemini 3.8 Flash | $0.75 | $0.075 | $3.75 | Rate until 31 Dec 2026; $1.50 / $7.50 from 1 Jan 2027 |
US dollars, standard tier, checked 3 October 2026 on Anthropic, OpenAI and Google pricing pages. Cached input is the price for reading from the cache. The prices leave out the charge for writing to the cache, batch discounts and regional surcharges.
input tokens × (1 − cached share) × input price + input tokens × cached share × cached priceoutput tokens × output price(input + output per call) × calls per runper run × runs a monthFAQ
From each provider's official API pricing page, checked on 3 October 2026: Anthropic, OpenAI and Google. They are standard list prices in US dollars before any volume discount, batch discount or regional surcharge.
A model call is one request to the model and one answer back. An agent that looks something up, decides, then writes a reply makes one call for each of those steps. Each call sends the whole conversation so far as input again. That is why input tokens usually outnumber output tokens.
It sets how much of each call's input is billed at the lower cached rate. Most providers charge less for input they have seen recently, such as the long instructions (the system prompt) that every run repeats.
No. Each provider counts tokens its own way, so the same text comes to a different number of tokens on each model. Real runs also vary in length. Use the estimate to compare models and size a budget, then measure real usage in a pilot.
Keep going
We build a pilot on your data, measure the tokens each run actually uses, and give you the monthly cost before you scale it.
We use Google Analytics cookies to see which pages visitors read, so we can improve the site. Accept to allow them or reject to keep them off. Privacy policy