aiapicostcalcUnit economicsPricesBrandsCompareBenchmarksSkills & PluginsFind my modelGuidesChanges

Browser Use token cost: per step and per task

Short answer: Browser Use burns about 30K input tokens (30% cached) and 2K output tokens per typical task, so one task costs $0.0585 on Grok 4.7. At 300 tasks a month that is $17.55; without caching the same task would cost $0.0720. Evidence: documented.

Last verified 2026-11-18 · Sources: src/tools.json (Browser Use token basis, documented) and src/prices.json (rates) · Report an error

By Shangyi Duan · Tool token basis: Documented

Tool token data: src/tools.json (reviewed 2026-11-05) · Model rates: src/prices.json (checked 2026-11-18) · Evidence: Documented

Cost per task, three price points

One row per scenario from our tool data. The three price columns price the identical token counts on the cheapest, mid and premium reference models, so the difference is the model rate, not the workload.

ScenarioInput tokensCached inputOutput tokensCheapest current modelMid-tier reference modelPremium reference model
Light task
one short request with a small context and one or two tool calls
5K20%500$0.00066$0.0115$0.1320
Typical task
one coding or agent task with several tool calls and a medium context
30K30%2K$0.00319$0.0585$0.6380
Heavy session
a multi-turn agent session with a large repo or long history; input counts all tokens re-sent across turns
120K40%8K$0.0117$0.2160$2.34

Rates: input $2 / cached $0.5 / output $6 per 1M on Grok 4.7. Prices checked 2026-11-18.

Monthly budget

Scenario at 300 tasks / monthCheapest current modelMid-tier reference modelPremium reference model
Light task$0.1980$3.45$39.60
Typical task$0.9570$17.55$191
Heavy session$3.50$64.80$701

At 300 tasks a month, one task at the typical size costs $0.0585 on Grok 4.7, so $100 covers about 1709 tasks. The same budget buys 157 tasks on the premium reference and 31348 on the cheapest one.

Recalculate this page in your browser

Server-rendered from the typical task on Grok 4.7 at 300 tasks a month. Change a field to recalculate; nothing is sent anywhere and the formula is the one under Method.

Cost per task
$0.0585
Cost per 1,000 tasks
$58.50
Monthly
$17.55

Where the tokens go

The provider basis behind these numbers

Browser Use's official pricing page states one credit balance covers browser time, traffic and model tokens; V4 agents are token-priced (default GPT-5.6 Luna at $0.24 input / $0.024 cached / $1.44 output per 1M tokens), BYOK adds a 0.2x orchestration fee, and legacy V2 charges from $0.006 per agent step plus $0.01 per task. Browser Use does not publish tokens per task, so we model 3 steps (light), 12 steps (typical) and 40+ steps (long-horizon) at roughly 2-3k input tokens per step as the page state and step history are re-sent.

What caching is worth here

Our data does not assume a cached prefix for this tool (30% cached share), so the task price above is already the uncached input price. If the tool does repeat a stable prefix, adding it to the provider cache cuts the input side to $0.5 per 1M on Grok 4.7.

How to reduce it

Each tip changes a different part of the formula: caching changes the input rate, trimming history changes the input count, and routing simple steps to a cheaper model changes the rate for part of the work.

Sources and evidence

SourceRead onWhat it establishes
browser-use.com2026-11-04Official Browser Use pricing: credit model, V4 token rates, BYOK orchestration fee and legacy per-step pricing.
docs.browser-use.com2026-11-04Browser Use Cloud agent model list and per-model token rates.

Evidence label: Documented

Browser Use's official pricing page states one credit balance covers browser time, traffic and model tokens; V4 agents are token-priced (default GPT-5.6 Luna at $0.24 input / $0.024 cached / $1.44 output per 1M tokens), BYOK adds a 0.2x orchestration fee, and legacy V2 charges from $0.006 per agent step plus $0.01 per task. Browser Use does not publish tokens per task, so we model 3 steps (light), 12 steps (typical) and 40+ steps (long-horizon) at roughly 2-3k input tokens per step as the page state and step history are re-sent.

Method

The formula

Cost per task = (uncached input × input rate + cached input × cached rate + output × output rate) ÷ 1,000,000. Rates are the standard list prices in the price table (checked 2026-11-18); token counts come from src/tools.json (tool data reviewed 2026-11-05).

Why three reference models

The columns are the cheapest, median and most expensive current models by the cost of one typical agent task, named above so you can check each rate. They are a range, not a prediction of which model Browser Use uses.

What the monthly figure assumes

300 tasks a month (the tasks-per-month field in our tool data), the same count for every scenario, at the standard rate with no batch discount. A heavy session can count as several tasks, so replace the number with your own before you put it in a budget.

Official links

Related skills & plugins

Other entries in the AI coding agents category. Each name links to its token-cost page or its official site.

Related models

The three reference models in the cost table, with their full price tiers.

More

Related

Questions

How much does Browser Use cost per task?

One typical task costs $0.0585 on Grok 4.7, $0.00319 on the cheapest reference model (GPT-6 Luna) and $0.6380 on the premium reference (GPT-6 Cyber). The spread is the model rate: the token counts are identical in all three columns.

What does Browser Use cost per month at 300 tasks?

$17.55 a month on Grok 4.7 at the typical task size. Without the 30% cached input assumption it would be $21.60. Per 1,000 tasks the token bill is $58.50.

Why does Browser Use use so many input tokens?

Every browser step sends the current page state (accessibility tree or DOM extract), the task instructions and the prior step history, then returns actions and extracted text. Long-horizon tasks and pages with large DOMs are the main token drivers; browser and proxy time is billed separately from model tokens. The token shape is 30K input tokens (30% cached) against 2K output per typical task; input is resent every step, output is not.

Are the Browser Use token numbers measured or estimated?

The evidence label is "Documented". Browser Use's official pricing page states one credit balance covers browser time, traffic and model tokens; V4 agents are token-priced (default GPT-5.6 Luna at $0.24 input / $0.024 cached / $1.44 output per 1M tokens), BYOK adds a 0.2x orchestration fee, and legacy V2 charges from $0.006 per agent step plus $0.01 per task. Browser Use does not publish tokens per task, so we model 3 steps (light), 12 steps (typical) and 40+ steps (long-horizon) at roughly 2-3k input tokens per step as the page state and step history are re-sent. Sources and read dates are in the table above; if a number is an estimate, the basis says what it assumes, and it is never described as a measurement.

Next step → See every tool cost side by side

Price data last checked 2026-11-18 against official sources · how we verify

Price-change alerts

One short email when a provider changes a price or a promo ends. No spam, unsubscribe any time.