AI coding agent pricing compared (2026): what 12 agents charge

The plan price is the least useful number in AI coding agent pricing. Nine of the twelve products below have a tier at or near $20 a month, and those nine tiers buy nine different things: a seat, a number of tasks running at once, a pool of credits, a rate limit, a share of a prepaid balance, or $20 of usage at a marked-up rate. Two $20 plans can differ by a factor of ten once the agent starts reading a large repository. This post lines the twelve up on what actually varies, which is what the meter counts and whether a key or subscription you already pay for is allowed to do the work.

Competitor prices and mechanics were checked in October 2026 against each vendor's own pricing and docs pages. The linked pages are the source; the rows are a snapshot. Sinatra's entry reflects its current plans and own-credential requirement.

Sinatra is our product, so that row is a vendor describing itself. Every other row links to where we read it, and where the number is unpublished we say so rather than guess.

Agent	Paid entry	What the meter counts	Your key or subscription runs the cloud agent	Free tier
Sinatra	Pro $20/mo for the whole workspace, any number of people	How many agents work at once and how many can wait (Pro: 3 agents at a time, plus 10 waiting), with no daily task limit; provider usage billed separately or covered by your own subscription	Yes: Anthropic or OpenRouter key, Claude, ChatGPT or SuperGrok subscription	1 agent at a time, plus 1 waiting, no daily limit, up to 60 minutes per agent, with your own credentials and no card
GitHub Copilot coding agent	Pro $10/mo; Business $19 a seat	AI credits at $0.01 each, drawn per token at published rates, plus Actions minutes	No: BYOK covers editors and the CLI, not the cloud agent	Copilot Free excludes the agent
OpenAI Codex cloud	ChatGPT Plus $20/mo; Business $20 a user billed yearly	A rate limit per plan tier, not a rate; credits past it on Plus and Pro	Only a ChatGPT plan; an API key turns cloud features off	None for the cloud agent: ChatGPT Free gets Codex in the desktop app only
Google Jules	Google AI Pro, $19.99/mo	Tasks per day: 15, 100, or 300 depending on plan	No: Gemini only, no key	15 tasks a day, 3 concurrent
Cursor Cloud Agents	Premium $30/mo; Teams from $30 a seat	Cursor's own models from a weekly usage pool; third-party models at API list price from prepaid credit, plus $0.25 per million tokens on Teams and Enterprise	Partial: your own keys work on Premium and up, but the docs don't say Cloud Agents use them; Teams charges the token rate on your key too	Free and Plus ($8/mo) have no Cloud Agents
Claude Code (Action and web)	Nothing beyond your credential	Your Anthropic bill at token rates, or your Claude subscription; Actions minutes on GitHub	Yes: API key, Pro/Max/Team/Enterprise subscription, or Bedrock, Google Cloud or Foundry on the Action; web sessions need a Claude subscription	No managed tier, so no free tier
Linear coding sessions	Linear Basic $10 a user; Business $16	Prepaid dollars: model tokens at provider-published rates, no markup, plus $0.25 per 20 minutes of sandbox	No: a workspace-selected model, billed from the credit balance	None; you top up first
Devin	Pro $20/mo; Teams $80/mo plus $40 a full seat on the pricing page (the billing docs count two seats inside the $80)	An included daily and weekly allowance of unpublished size, then on-demand credits; Enterprise is metered in ACUs at an order-form rate	No API key; a linked ChatGPT Go, Plus, or Pro plan can cover only its OpenAI calls	Free has no cloud sessions; they start at Pro
OpenHands	$0 to self-host (single user or shared identity); Teams $499/mo self-hosted, up to 10 users (+$50/mo per seat), 5,000 sessions a month; Enterprise custom	Built-in model provider at provider rates, no markup	Yes for keys; subscriptions only where the CLI login already sits on the machine	Free self-hosted (single user or shared identity); no published hosted free tier
Factory	Pro $20/mo; Teams $60/mo plus $40 a seat	Rolling 5-hour, 7-day, and 30-day rate limits plus prepaid credits	Partial: CLI and desktop only, and free only up to an allowance	None
Kiro	Pro $20 a user	Credits: 1,000 on Pro, add-ons $0.04 each, no published token conversion	No	50 credits a month, without the cloud agent
Augment Code	Standard $20/mo for up to 50 seats	$20 of usage, with a flat 40% fee on model usage	No	None

The twelve sort into four billing shapes, and the shape tells you more than the price.

Your provider's invoice, plus a fee for the machinery

Sinatra, Claude Code, and OpenHands all leave the model bill with your model provider. You hold the key or the subscription, the tokens land on that account at whatever rate you already have, and the vendor charges for something else or for nothing.

Claude Code charges nothing at all. You supply the credential, Anthropic bills the tokens, and GitHub bills the Actions minutes if you run it as an Action. There is no managed tier, which is why it has no free tier either: someone always has to bring a key.

OpenHands is free to run on a laptop or shared VM for a single user or a shared identity, and Teams is $499 a month self-hosted for up to 10 users, capped at 5,000 sessions a month. Where it bills models on your behalf, its docs say provider rates with no markup. That is the cleanest price list in this market and we would rather say so than pretend otherwise.

Sinatra charges a flat monthly price per workspace for orchestration: Pro at $20, Team at $99, Scale at $249. A workspace connects at most one GitHub organization or personal account, and the price does not change with the number of people in it. The plan sets how many agents work at once and how many can wait, not how many you can run in a day. Every account, free or paid, requires its own model credentials. Anthropic or OpenRouter API usage is billed by your provider. Personal subscriptions cover usage within their owner's provider limits; workspace API keys are shared with authorized members. Sinatra never bills for model usage. Token and cost diagnostics are estimates, not Sinatra invoices, including when a subscription covers usage.

Published per-token rates, billed by the vendor

Copilot, Cursor, and Linear publish a rate and bill you for it themselves. You can see what a session cost after it runs, at a price you could have looked up beforehand. You cannot bring a relationship you already have with a model provider, though; the vendor holds that one.

GitHub moved Copilot to usage-based billing in June 2026. Each plan includes a pot of AI credits at a cent each (1,500 a month on Pro, counting a 500-credit flex allotment, and 1,900 per user on Business, pooled across the organization), and the credits drain per token at published per-model rates that match Anthropic's own list prices row for row on the day we checked. The agent also burns Actions minutes, because it runs inside a GitHub Actions environment with a 59-minute cap per session. Copilot's bring-your-own-key covers editors, the CLI, and the SDK; the agent on GitHub.com is not on that list.

Cursor is more transparent than most, and it has just changed shape. Since it became part of The X Subscription, alongside Grok and X, Cloud Agents start on Premium at $30 a month. Cursor's own models come out of a weekly usage pool, and third-party models are charged at their API list price from prepaid credit, so a Claude-run task costs what Anthropic would charge you. The catch sits on the team plans. Teams and Enterprise add a Cursor Token Rate of $0.25 per million tokens on top of model API pricing, and the docs say that applies to BYOK usage as well. Small and published, but still a per-token fee on a key you bought yourself.

Linear coding sessions draw on a prepaid balance in dollars, with model tokens at provider-published rates with no markup and sandbox runtime at $0.25 per 20-minute block. That is the only pricing on this list where you can estimate a session before running it. There is no free allowance and no way to point it at a subscription you hold; you top up and the balance does the paying.

A rate limit instead of a rate

Codex, Factory, and Devin sell tiers, and what a tier buys is throughput.

Codex cloud comes with a ChatGPT plan. OpenAI publishes an estimate rather than a price: 15 to 160 local messages per five hours on Plus with GPT-6.1 Sol, the model it recommends, with the caveats that cloud tasks may use more of the allowance and that the estimates are not fixed limits. We went through the whole plan table in a separate post on Codex cloud pricing. When Plus is not enough, the answer is Pro at $100 or credits bought on top, rather than a bill that tracks usage. There is a per-token path through an API key, and OpenAI's pricing page says that path has no cloud features. You get published pricing or the cloud agent, not both.

Factory's plans run $20, $100, and $200 for individuals, or $60 a month plus $40 a seat for Teams, against three rolling rate-limit windows of unpublished size. Its own docs say bring-your-own-key is free up to an allowance, after which usage is charged according to your plan. A key lowers the bill without decoupling it from usage, which is the thing a key is usually brought to do.

Devin's Pro plan is $20 and its Teams plan is $80 plus $40 per full seat on the pricing page, though the billing docs read the $80 as a minimum that already covers two seats. Cognition's self-serve billing page says Pro and Teams seats have a daily and weekly allowance, Max has a weekly one, and usage past that comes from on-demand credits. None of the allowances is given as a number. Two tickets that look identical when written can cost different amounts, and you learn which afterwards.

Jules belongs here too, though it meters something simpler: tasks. Fifteen a day free, 100 on Google AI Pro, 300 on Ultra, with no separate model bill. For an individual on GitHub who is happy with Gemini, that is generous and easy to reason about.

A unit the vendor defines

Kiro's credits, Devin's Enterprise ACUs, and Augment's fee are the shape to read most carefully, because the unit is the product.

Kiro publishes plenty: 50 free credits a month, 1,000 on Pro at $20, up to 10,000 on Power at $200, and add-ons at $0.04 each. Its pricing page says a simple prompt can use less than a credit and a spec task usually more, and its models page gives per-model multipliers, but nowhere does Kiro say what a credit is in tokens. You find out how big the unit is by spending it.

Augment publishes something few others do: a flat 40% fee on model usage, with no fee on compute. The $20 Standard plan buys $20 of usage for up to 50 seats, which at low volume may be the cheapest thing on this page. The percentage is the part to sit with, because it scales with exactly the thing you are trying to do more of. A team that doubles its agent usage doubles the fee.

The number you actually want is the cost of one task, and only Linear lets you estimate it before you run it. Copilot and Cursor tell you afterwards at a rate you could have looked up. Codex and Factory tell you when you hit a window. Kiro and Devin tell you in a unit you cannot convert.

The way around that is to stop reading pricing pages, including this one. Take five tickets you would actually hand to an agent, run the same five through each product on your shortlist, and read the invoices next to the pull requests. Where the model bill lands on your own provider account, count that too. An afternoon of that beats any table, and some of these vendors have a free tier that covers it; for the rest it's a month of the entry plan.

Two numbers, both published. The plan is a flat monthly price for the whole workspace: Pro is $20 for 3 agents at a time, plus 10 waiting; Team is $99 for 10 agents at a time, plus 25 waiting; and Scale is $249 for 25 agents at a time, plus 100 waiting. It does not move when a week gets busy or when someone new joins. There is no daily task limit. Assign as many tickets as you want: the plan sets how many agents work at once; the rest wait and start on their own as soon as one finishes, and if the queue is full, Sinatra says so on the ticket instead of starting it. Model usage is billed by your provider or covered within the limits of a Claude or ChatGPT subscription you already hold. For a small team the cheapest honest path is the subscriptions they already pay for, plus $20 a month for the whole workspace. The free tier is 1 agent at a time, plus 1 waiting, with your own credentials and no card; on Free each agent works up to 60 minutes, then stops and saves its work, and finishing it takes an upgrade. We wrote up the tradeoffs of holding your own key separately, and the alternatives hub has a page against each product above.

If you want to run the five-ticket test on Sinatra, start for free and the model bill stays on whatever you already pay for. The pricing page has the rest of the terms.