Quick answers

AIGrow provides AI visibility monitoring, a business assistant, blog publishing and scoped automation services. Start with the free scan to inspect the output before paying.

Run the free scan

The scan is free and monitoring plans start at $29 a month. The operations audit is $290, the visibility audit is $490, and custom builds receive a written price before work starts.

See the plans

Run the free scan. It reads your site, asks several AI assistants what your customers ask, and points you at one thing. No signup required, and it will tell you if you do not need us.

Start now

Yes. Use the contact form for product, billing, support or project questions. Describe the goal and the system involved so the first reply can be specific.

Contact AIGrow
Agent cost calculator

What an AI agent costs to run

An agent is not one call. It takes a number of steps, and the context it reads grows with every one of them. Set the shape of your workload, pick a model, and the calculator prices the whole run at the maker’s published rate, step by step.

Free and without sign-up. The arithmetic runs in your browser, so nothing you type is sent anywhere.

$2 in and $10 out per million tokens, the price Anthropic publishes, read on 22 September 2026.

One model call each: a search, a read, a decision, a write. Capped at 40.

The instructions, the tools it is given and the request itself. Roughly 750 words per 1,000 tokens.

What the step brings back: the page it read, the rows it fetched, the result of the tool it called.

The answer only. Reasoning is the next field, because it is billed at the same rate.

Billed at the output rate. Leave it empty for 400, an assumption; set it to 0 for a model that does not think first.

Leave it empty to use 70%, an assumption. The first step is a cold read, so none of it is cached.

Leave it empty to use 5%, an assumption.

How often the whole workflow runs: per ticket, per lead, per document.

The rate

Anthropic publishes a batch rate of 50% off for work that does not have to answer now, usually returned within a day.

The month, worked out
$183What 1,000 runs of a 10-step agent cost a month on Claude Sonnet 5
Read over 10 steps
107,500 tokens
Of that, served from cache (70%)
72,450 tokens
Written: the answer and the reasoning
9,000 tokens
One run, 5% of steps retried
$0.1833
1,000 runs a month
$183

List price as Anthropic publishes it, read on 22 September 2026. Cache hits at $0.20 per million. Hosting, the tools the agent calls, embeddings and logging are not in it.

$183. What 1,000 runs of a 10-step agent cost a month on Claude Sonnet 5.

Step by step
StepReadsFrom cacheWritesCost
14,0000900$0.0170
25,5003,850900$0.0131
37,0004,900900$0.0142
48,5005,950900$0.0153
510,0007,000900$0.0164
611,5008,050900$0.0175
713,0009,100900$0.0186
814,50010,150900$0.0197
916,00011,200900$0.0208
1017,50012,250900$0.0219

Ten steps, a context that grows from 4,000 tokens, 70% of each read served from cache and 5% of steps retried: on Claude Sonnet 5 that run reads 107,500 tokens and costs $0.1833, so 1,000 runs a month cost $183. Its published batch rate halves that.

How the number is worked out

Every figure the calculator assumes is on this page, so the result can be checked with a pencil.

The prices
Input, output and cache-hit rates as each maker publishes them, read from data/models/2026-09/models.json, which records the pricing page and the day it was read (22 September 2026). The same figures are on our model pages. No price here comes from a reseller.
The steps
Step one reads the starting context. Every step after it reads what the step before read plus the tokens that step added, so the input billed over a run is the sum of the steps, not one prompt. The per-step table prints each line.
The cache
The share you set is served at the maker’s cache-hit rate; the first step is a cold read, so nothing of it is cached. Where a maker publishes no cache price, cached tokens are billed at the full input rate and the result says so.
Reasoning and retries
Reasoning tokens are billed at the output rate, so they are added to the answer for every step. The retry rate is the share of steps that fail and run again: it multiplies the run by one plus the rate. Both defaults are assumptions.
The batch rate
Where the maker publishes a batch discount in its price notes, the calculator offers it and prints the share: half off on Anthropic, OpenAI and Google, a fifth off on Grok 4.3, and nothing where the maker does not sell one.
What it leaves out
Hosting, tools the agent calls, embeddings, logging, and the long-context surcharges that start above 200,000 or 272,000 tokens in a single request on some models. Keep a step under that band and the base rate is the one that applies.

It depends on steps, context and model. A ten-step run that reads 107,500 tokens and writes 9,000 costs $0.1833 on Claude Sonnet 5, which is $183 for 1,000 runs a month. The same workload on a small model costs a fraction of that.

Because each step reads everything before it. Ten steps starting at 4,000 tokens and adding 1,500 a step read 107,500 tokens in total, not 40,000. Caching is what keeps that from being billed at the full input rate every time.

They are billed at the output rate, which is the most expensive rate a model has. A model that thinks for 400 tokens before writing 500 is billed for 900 output tokens on that step.

A cheaper queue for work that does not have to answer now, usually returned within a day. Anthropic, OpenAI and Google publish 50% off; xAI publishes 20% off on Grok 4.3 and none on Grok 4.7. The calculator uses only rates the maker publishes.

Have the run priced on your own workflow

The audit measures the real steps, the real context and the real volume before anything is built, so the number you plan with is measured rather than assumed.