Self-Hosted AI Agent
The back of a Mac mini: power, Ethernet, HDMI and three Thunderbolt ports

How much does OpenClaw cost? Pricing and monthly running costs

OpenClaw doesn't cost anything to download or use. It's free, open-source software (MIT licence), and the OpenClaw Foundation sells no paid plan. What you pay for is the AI model it talks to, the computer it runs on and that computer's electricity. The three illustrative monthly budgets below come to about $14 a month for light use on a laptop you already own, $27 for an owned mini PC with assumed cached usage, excluding its purchase price, and $271 for heavy use of a top model on a rented server. These are worked examples, not a minimum-to-maximum price range or measured typical costs.

The short answer: four costs, and one is much bigger than the rest

Running OpenClaw has four costs, and the AI model is usually the biggest. Setup help is a fifth, optional one.

CostTypical range (September 2026)How you pay
Software (OpenClaw or Hermes Agent)$0Free, MIT licence
AI model$0 on free tiers to hundreds of dollarsPer token, or a flat subscription
Computer$0 if you own one; about $6 to $24 a month to rentOne-off purchase, or monthly rent
ElectricityAbout $0.50 to $9 a month for one small computerYour power bill
Setup help (optional)$0 if you do it yourself; about $200 to $600 from paid servicesOne-off

The software: free

OpenClaw costs nothing to download or use. Its code is on GitHub under the MIT licence, held by the OpenClaw Foundation, which has no paid tier, hosted service or token. Hermes Agent, from Nous Research, is also MIT-licensed. Paid "OpenClaw plans" you see advertised, such as Hostinger's, are other companies bundling hosting, setup or model credits around the free software. If you're choosing between the two agents, see Hermes vs OpenClaw. If you're still deciding whether to use OpenClaw at all, the OpenClaw alternatives are free too.

The AI model: where most of the money goes

You pay for the model every time the agent thinks. You can pay per token with an API key or, with some providers, use a flat monthly subscription.

Pay-per-token prices

Prices are in US dollars per million tokens. A token is about four characters of English text, according to OpenClaw's docs. Input is what the agent sends; output is what the model writes back.

ModelInputOutputCached input
Claude Opus 5.5 (Anthropic)$4.00$20.00$0.20
Claude Sonnet 5.5 (Anthropic)$2.00$10.00$0.10
Claude Haiku 4.5 (Anthropic)$1.00$5.00$0.10
GPT-6.1 Sol (OpenAI)$2.00$10.00$0.10
GPT-5.4 mini (OpenAI)$0.75$4.50$0.075
Gemini 3.8 Flash (Google)$0.75$3.75$0.075
DeepSeek Flash, peak hours$0.30$1.20$0.006

Google's Gemini 3.8 Flash prices double on 1 January 2027, to $1.50 input and $7.50 output. DeepSeek charges half its peak rates outside peak hours.

Agents use far more input than output. OpenClaw rebuilds its instructions on every run, and its standing files (such as AGENTS.md and MEMORY.md) can add up to 60,000 characters, roughly 15,000 tokens, before any conversation or tool results. That is why cached-input prices matter. Anthropic charges 10% of the normal input price to re-read a cached prompt (5% on Opus 5.5 and Sonnet 5.5) and 1.25 times the input price to write one to its 5-minute cache.

Flat subscriptions: what's allowed

Some subscriptions work with OpenClaw and some are unsettled. As of September 2026:

A subscription includes a usage allowance; its monthly fee is not always the limit on your bill. Claude's usage-credit documentation says enabled credits are charged separately at API rates after included usage runs out. Check optional credits, spending limits and auto-reload before relying on a fixed monthly budget.

Free models and paid fallbacks

On OpenRouter, :free works only for a model with a listed free entry. Free variants can have different availability and rate limits from paid variants. A free route that worked earlier is not proof it is available for your next request.

OpenRouter's free-variant documentation also warns that a paid model in your fallback array is billed at its own price if the free model cannot handle the request. A free first choice does not make that fallback free. Inspect the exact model ID, error and fallback configuration before changing billing or buying more credits.

I rechecked the per-token table against each provider's pricing page on 11 November 2026. Every row matched except Claude Sonnet 5.5's cached input, which Anthropic lists at $0.10, not the $0.20 shown here before, so the middle budget below is recalculated. Usage-credit and free-fallback rules were checked 20 October 2026. DigitalOcean's server prices also still match. Subscription, Hetzner, Hostinger, electricity and setup prices are still September 2026 figures.

The computer: one you own, or one you rent

Any computer that stays on will do. OpenClaw runs on macOS, Linux and Windows. Its docs put the minimum at 1 CPU core, 1 GB of memory and about 500 MB of disk, with 2 GB of memory or more recommended.

Own it. A computer you already have costs nothing extra except power. OpenClaw's FAQ says you don't need a Mac mini; a small VPS, home server or Raspberry Pi-class box works too. There are short answers for an old laptop, a mini PC and a Raspberry Pi. If you're thinking of buying one, read whether a Mac mini is worth it for OpenClaw or try Which computer should run your agent?

A small black Dell OptiPlex Micro desktop
Dell OptiPlex 7070 Micro, refurbishedabout $237

Cloud-model agent, always on, cheapest box with 16 GB that doesn't feel slow. Intel Core i5-9500T (6-core), 16 GB memory, 256 GB NVMe SSD.

A small square mini PC with USB and network ports on its side
Beelink EQ14$385

Cloud-model agent on a new, quiet N150 box with 16 GB and a built-in power supply; the popular homelab pick. Intel N150 (4-core), 16 GB memory, 500 GB SSD.

A silver Mac mini on a wooden table
Mac mini M6, 16 GB$899

Always-on cloud-model agent on macOS (needed for OpenClaw's iMessage), silent and 4 W at idle. Apple M6, 12-core CPU, 12-core GPU, 153 GB/s, 16 GB memory, 256 GB SSD.

Amazon links on this site are affiliate links: if you buy, I may earn a commission, at no cost to you. As an Amazon Associate I earn from qualifying purchases. Nobody pays to be picked.

Rent it. A virtual private server (VPS) swaps the one-off cost for a monthly bill (see OpenClaw on a VPS). OpenClaw's FAQ notes the trade-off: a VPS is often headless (it has no screen), while a computer you own can show a real browser window.

OptionPrice a monthNotes
DigitalOcean Basic, 1 vCPU, 1 GiB$6Meets OpenClaw's minimum
DigitalOcean Basic, 1 vCPU, 2 GiB$12Meets the recommended 2 GB
DigitalOcean Basic, 2 vCPUs, 4 GiB$24More headroom; OpenClaw's FAQ says browser automation can be resource-hungry
Hetzner CX23$6.49Germany or Finland; excludes VAT and IPv4; prices rose 15 June 2026
Hetzner CX33$9.99As above
Hostinger managed AI apps (OpenClaw or Hermes)$5.99 to $10.99$5.99 on a 24-month plan, $10.99 month to month; renews at $11.99

Electricity: usually a few dollars

A small computer left on all month costs between about 50 cents and $9 in power at the US average price. That average was 18.31 cents per kilowatt-hour in July 2026, according to the US Energy Information Administration (EIA). It ranged from 12.72 cents in Louisiana to 48.00 cents in Hawaii.

The arithmetic: watts × 730 hours ÷ 1,000 = kilowatt-hours a month. Kilowatt-hours × $0.1831 = dollars a month.

ComputerPower drawkWh a monthCost a month
Mac mini (M6), idle4 W (Apple)2.92$0.53
Mac mini (M6), maximum70 W (Apple)51.10$9.36
Intel N100 mini PC, idle4.8 W (Notebookcheck)3.50$0.64
Intel N100 mini PC, average load13 W (Notebookcheck)9.49$1.74
Laptop, switched on19 to 32 W (LBNL)13.87 to 23.36$2.54 to $4.28
Desktop, switched on66.1 W (LBNL)48.25$8.84

When the model runs in the cloud, the computer mostly waits for replies, so expect a dedicated agent machine to sit nearer its idle figure than its maximum. The laptop and desktop figures come from a Lawrence Berkeley National Laboratory (LBNL) study of home computers metered in 2012, and the earlier studies it compares, so treat them as rough numbers for older machines. A plug-in power meter will tell you what yours draws.

Setup: your time, or someone else's

Setup costs your time, or money if you pay someone to do it. I found no independent survey of setup prices, so these are examples, not a market average. As of September 2026, US services advertise one-off setup from $199 (OpenClawPro, which also offers a $99-a-month managed plan) and $299 for a one-hour session or around $600 for four hours (OpenClaw Install). In China, the South China Morning Post reported in March 2026 that after users paid to have OpenClaw installed, sellers on the Xianyu marketplace began charging to remove it, one for 299 yuan ($43.55). I sell setup too, from a $150 call to a $750 done-for-you setup: the packages.

Whoever sets it up, keep time for upkeep: updates, and checking what the agent can reach. Is OpenClaw safe? covers the risks.

Three worked budgets

These examples show the arithmetic with September 2026 prices. The usage figures (how many model calls, and how big each one is) are my assumptions for illustration, not measurements. Your own use will differ, so check your provider's dashboard after the first week.

Light: a laptop you already own and a cheap model

From 1 January 2027 the same Gemini use would cost $20.25 ($18.00 + $2.25). DeepSeek Flash at peak rates would cost $3.96 ($3.60 + $0.36).

Owned mini PC with assumed cached usage

Without caching, the same model use would cost $67.50 (30 × $2 + 0.75 × $10). Treating every uncached token as a cache write slightly overstates the cached figure. With ChatGPT Plus instead of an API key, the model line becomes a flat $20, within Plus's usage limits.

Heavy: a rented server and a top model all day

Without caching, the model alone would cost $630 (135 × $4 + 4.5 × $20). A ChatGPT Pro plan at $100 or $200 would cap the model line instead, if its limits fit your use.

What Hermes Agent costs

Hermes Agent has the same cost structure: the software is free, and you pay for a model, a computer and power. Nous Research recommends its Nous Portal subscription. As of September 2026 the Portal has a free tier (free models only) and paid tiers of $20, $100 and $200 a month, which include $22, $110 and $220 of monthly credits. The Portal also lets you connect an eligible ChatGPT plan without a paid Nous subscription. Hermes can also sign in with ChatGPT/Codex or GitHub Copilot, or use pay-per-token API keys from Anthropic, OpenAI, Google, DeepSeek, OpenRouter and many others.

How to keep model costs down

The cheapest savings come from sending fewer, smaller and better-cached requests.

Questions

Is OpenClaw free, or does it cost money?

The software is free. OpenClaw is open-source software under the MIT licence, so it costs nothing to download or use. You still pay for the AI model it uses, the computer it runs on and that computer's electricity.

How much does OpenClaw cost per month?

It depends almost entirely on the model and how much you use it. The worked examples on this page come to about $14 a month for light use on a laptop you own, $27 for a mini PC you own with a cached Claude Sonnet 5.5, and $271 for heavy Claude Opus 5.5 use on a rented server. Those are examples with assumed usage, not a measured average.

Is there an official OpenClaw paid plan?

No. The OpenClaw Foundation is a non-profit and sells no paid tier or hosted service. Paid "OpenClaw" plans come from other companies that bundle hosting or setup around the free software. Hostinger's managed app was $5.99 to $10.99 a month in September 2026.

Can I run OpenClaw for nothing?

Nearly. On a computer you already own, Google's Gemini API has a free tier, though it has limits and Google may use free-tier content to improve its products. You still pay for electricity. OpenClaw's FAQ says small local models are usually a poor fit: they truncate context and raise prompt-injection risk.

Can I use my ChatGPT subscription with OpenClaw?

Yes. OpenClaw supports signing in with ChatGPT or Codex, and its docs say OpenAI explicitly allows it. Usage counts against your plan's limits: Plus is $20 a month, Pro $100 to $500, as of September 2026.

Can I use my Claude Pro or Max subscription with OpenClaw?

Only through OpenClaw's Claude CLI route, which runs your own Claude Code login, and Anthropic's rules have changed several times in 2026. OpenClaw's docs say this currently draws from your plan's usage limits and recommend an Anthropic API key for predictable spending.

Do I need to buy a Mac mini to run OpenClaw?

No. OpenClaw's FAQ says a small VPS, home server or Raspberry Pi-class box works too. You need a Mac only for macOS-only features such as iMessage. See Mac mini for OpenClaw.

How much does Hermes Agent cost?

The software is free (MIT licence). Nous Portal, the subscription Nous Research recommends, costs $0, $20, $100 or $200 a month as of September 2026. You can also bring a ChatGPT plan or pay-per-token API keys instead.

Sources

How to use this guide

The recommendations in this guide draw on the linked documentation, stated requirements and dated price examples. They are not a scored performance benchmark or a promise that a particular setup will work for every task. Check the source date beside a claim before buying or changing a system.

Start with the task, the software it needs and a computer you already own. Compare the whole cost: hardware, model usage and time to check the work. Hardware purchases may earn this site an affiliate commission; paid setup is optional.

Updated : rechecked the per-token price table, corrected Claude Sonnet 5.5's cached-input price and recalculated the middle budget. Subscription, Hetzner, Hostinger, electricity and setup prices are still the September 2026 snapshot.