Account
Plans and limits
What your company's plan covers, what is measured against it, what is simply on or off, and what happens the moment you cross either line.

Product trial and introductory pricing
A company can start a no-card 14-day product trial from its Billing page
when the trial is available. It includes one project, 25 prompt
slots across five engines (Perplexity, Google AI Overviews, Google AI
Mode, ChatGPT and Gemini), three
competitors,
one article draft for the entire trial, and up to three page recommendations
per weekly run. Once the trial is available at all, three things can rule
it out, checked in this order: the company has already used its trial;
you have already started a trial in another company, since each person can
start one trial ever; or the company has paid before, since a company with
a previous paid subscription is not eligible
(api/routers/billing.py#start_product_trial, #_trial_offer).
The trial ends on Free without a charge unless you choose a paid subscription.
The single article allowance belongs to the company: it does not reset at
the start of a week or when you delete a project or article, and you can
retry the same draft (api/services/limits.py#reserve_trial_article). Saved
data remains after expiry; only the oldest active projects and prompt slots
within the company's current plan are monitored. Pause those to choose
which others run (api/services/limits.py#monitored_target_ids).
When the Starter introductory offer is displayed, new paid subscribers pay
the introductory rate for their first three paid months, then the standard monthly price shown on Pricing. Trial
days do not count as paid months. The offer needs no paid history in the
company and none in any other company of the person checking out, so
cancelling and resubscribing does not restart the discount, and neither
does opening a second company. Moving from introductory Starter to another
paid plan follows the normal timing below, and the discount stops applying,
since it covers Starter only. Growth and Pro retain their standard prices.
Offer availability is shared between the pricing website and checkout
(api/routers/billing.py#public_offers, api/services/billing_offers.py#intro_available,
#has_paid_history, #person_has_paid_history).
What one plan covers
Every project belongs to exactly one company, and the plan belongs to the
company: one subscription and one set of limits for every project in it
(api/services/plan.py#get_company_plan, #get_project_plan). Who created
a project, and who is looking at it, play no part. A person who belongs to
two companies, one on Free and one on a paid plan, sees each project on its
own company's plan.
Some limits pool across the company, and the rest apply to each project on its own:
- Pooled per company: prompt slots and the number of active projects.
A prompt counts against the company's pool whichever of its projects it
belongs to, and a paused project counts toward neither
(
api/services/limits.py#get_active_prompt_slot_count,#active_project_count). - Per project: competitors, articles per week, personas, AI crawler hits and every other per-project limit, each read from the company's plan.
- Seats: unlimited, on every plan; see Team.
Two kinds of people reach a company's projects, and only one of them sees
billing. Company members open every project, manage the plan and see the
Billing page; project editors and viewers see only the projects shared with
them and never see billing (see Team). Billing
therefore lives with the company rather than inside any project, at
/companies/<id>/billing, reached from the plan meter at the foot of the
sidebar and from Billing in the account menu. Both lead there only for
the company's members. Project settings is grouped as Project,
Tracking, Connections and Data, and none of its tabs changes the plan
(frontend/src/routes/(app)/settings/+layout.svelte#groups).
Every project's settings have a Plan and usage tab that anyone who can
open the project can read. It names the company's plan, shows this
project's share of the pooled prompt slots and its own per-project usage,
and then either links a company member to Billing or tells anyone else who
can change the plan, by name
(api/routers/projects.py#get_project_usage,
frontend/src/lib/upgrade.js#planOwnersSentence). Every "See plans" link in
the app follows the same rule: a company member goes to the company's
Billing page, and anyone else gets an "Ask ... to upgrade" link naming a
company member, which opens Plan and usage
(frontend/src/lib/upgrade.js#upgradeTarget).
The checks below all resolve the plan from the project's company, never
from the person making the request. The competitor and article checks look
the company up from the project the request names
(api/services/limits.py#check_competitor_limit, #check_article_limit);
the project-count check that runs when a paused project is resumed is
handed that project's company (api/routers/projects.py#update_project),
and the same check at creation is handed the company the new project goes
into (api/services/company_projects.py#resolve_target_company); and data
exports resolve the plan the same way (api/routers/exports.py#exports_index,
#download_export). Exports make the effect concrete: a download is
allowed or refused on the company's plan, and nothing in that check
additionally looks at whether the person clicking download has write access
to the project, so at the API level a viewer on a project of a paid company
can download the same exports an editor or a company member could.
The prompt-slot check counts active prompt targets across the company's
active projects. On a plan with a slot limit, the reservation in front of
every new slot takes the company's row lock first, so two people adding
prompts to two projects of the same company at the same moment queue rather
than both passing the same count (api/services/limits.py#reserve_prompt_slots, #check_query_limit,
#get_active_prompt_slot_count). Every path that can add a slot reserves it
against the company of the project it lands in: creating, importing or
editing a tracked prompt (including turning a paused one back on), bulk
changes to a selection of prompts, accepting a suggested prompt, and
creating a project during onboarding
(api/routers/prompts.py#create_prompt, #import_prompts, #update_prompt,
api/services/prompt_bulk.py#organize_prompts,
api/services/prompt_variants.py#apply_variants,
api/routers/prompt_candidates.py#accept_candidate,
api/routers/projects.py#create_onboarding_project). So an editor adding a
prompt to a company's project spends that company's slots, on that
company's plan.
So if you are an editor or a viewer on a company's project, every limit and
gate you meet on that project is the company's, with no exception.
Reaching that project's screens in the app is a separate question, and the
answer is that you can: GET /projects returns the projects shared with you
alongside those of your own companies; see Team for
what each kind of person can then do once a screen is open.
What's metered
Four numeric limits are measured against the plan, each a plain integer
column on the plan itself rather than logic scattered through the code:
active prompt slots and active projects, both pooled across the company,
and active competitors per project and articles generated per week, both
per project. Each plan row, seeded at api/services/seed.py#DEFAULT_PLANS,
sets its own value for each of the four. A column holding negative one
turns that particular ceiling off entirely: the check that reads it returns
immediately, so nothing on that plan is ever compared against it, let alone
rejected (api/services/limits.py#check_project_limit, #check_query_limit,
#check_competitor_total_limit, #check_article_limit). The plan's
team-member column holds negative one on every plan and no check reads it,
because seats are unlimited
(alembic/versions/b5e1f7c3a9d2_companies.py#UNLIMITED_SEATS_SQL). The
actual figures for each plan, and which plan has which, live on
Pricing and nowhere else in this section, so there is exactly
one place to keep them current.
What each column governs, and where it is checked:
- Prompt slots: active prompt targets in the company's active projects,
pooled as described above. Checked before a slot is added, on every path
listed above. A country, audience
and language combination is
one slot each, exactly like a country was before languages existed:
languages, choosing which engines run a prompt, and saving a combination
as a template draw on this same pool, on every plan, with no separate
entitlement of their own
(
api/services/prompt_variants.py#sync_targets). - Projects: active projects in the company, whoever created them.
Checked before a new one is created, and checked again whenever a paused
project is resumed; see below. The check takes the company's row lock, so
two members creating projects at once cannot both pass the same count
(
api/services/limits.py#check_project_limit,#active_project_count). - Competitors per project: active competitors tracked on one project.
Checked per project, both when a project is first set up and whenever a
competitor is added afterward
(
api/services/limits.py#check_competitor_limit,#check_competitor_total_limit). - Paid articles per week, per project: articles started in the current calendar week,
Monday through Sunday, counting every article whose status is not
failed. A failed attempt does not count against the week, so retrying
one is free (
api/services/limits.py#check_article_limit). The Articles screen reads the same count before you start one, so a used-up week disables the write buttons and says why instead of failing after the click (api/services/limits.py#article_limit_reason).
What's gated
Separate from the four metered columns, capabilities and agent limits are persisted in each plan's entitlements, and every gate below reads them from the plan of the project's company. Renaming a plan or changing its price does not change those capabilities. Every gate below is one a customer can actually reach from a screen in the app:
- Explicit AI source-mention review uses the company's persisted
source_mention_reviewflag. Standard Starter, Growth and Pro enable generation; Free and Trial do not. Saved reads, corrections by company members and editors, combined brand filters and explicit snapshots remain available on every plan. No automatic review runs after scraping (api/services/source_mention_review.py#_access). - Reviewable AI prompt classification uses the company's persisted
prompt_classificationflag. Standard Starter, Growth and Pro enable it; Free and Trial do not. Manual labels and bulk edits remain available on every plan. Generation is limited to one batch per project per minute; saving an already generated, unexpired review does not make another model call (api/services/prompt_classification.py#require_generation_access). - Weekly automatic prompt-suggestion refresh, the toggle that keeps the
Suggestions queue topped up on its own. Turning it on is rejected unless
your plan's discovery tier allows it; turning it back off is always
allowed (
api/services/prompt_discovery.py#_tier_for_plan,api/routers/projects.py#update_project). - On-demand "Suggest more prompts", read from the same discovery tier
table as the toggle above, but as its own separate flag rather than tied
to whether weekly refresh is on
(
api/routers/prompt_candidates.py#generate_more_candidates). - Weekly citation-gap opportunity generation, which runs as a
background job rather than from a click. The entry plan's cap in this
table is zero, so the weekly job for a project on that plan returns
nothing and logs that it skipped, every week, indefinitely
(
api/services/citation_gap.py#_limit_for_plan,#find_gaps_for_project). - On-demand citation-gap refresh, the button that runs the same
underlying work immediately. This one reads a separate refresh permission
rather than the weekly volume limit, so the button's availability and the weekly job's
output are governed by separate entitlements that describe the
same feature (
api/routers/citation_gaps.py#_require_on_demand,#refresh_project_citation_gaps). - Weekly page-optimization opportunity generation, a background job
shaped like the citation-gap one above it: zero on the entry plan, a
per-week cap on the rest. One difference between the two is worth
knowing if you ever go looking in the logs: the citation-gap run records
a line saying it skipped, while this one returns an empty list and
records nothing at all
(
api/services/optimization/service.py#score_optimization_opportunities_for_project,#score_optimization_opportunities_for_project). - On-demand page-optimization refresh, the Refresh button on the
Optimizations screen, for a whole project or for one prompt. Unlike the
citation-gap button above, neither endpoint behind it reads a plan: both
call the same generator, which returns nothing at all on a cap of zero,
and both then report success with nothing produced. What keeps a person
off that path is the screen, which on the entry plan draws a link to the
plans page in place of the button; only when it cannot read the company's
plan does it draw the button anyway
(
api/routers/optimizations.py#refresh_project_optimizations,#refresh_prompt_optimizations,api/services/optimization/service.py#run_optimization_for_prompt,frontend/src/routes/(app)/optimizations/+page.svelte#refreshLocked). - Article generation, gated by the metered weekly column above, but a
zero on that column is not a silent skip here: starting an article,
whether from a citation-gap topic or one you typed yourself, is a
request a person clicked, so a zero refuses it outright with a message
instead of quietly producing nothing
(
api/services/limits.py#check_article_limit). Which drafting strategy the writer then uses for an article that is allowed to start, a research-grounded pass or a single one-shot draft, also varies by plan; see Articles for what that changes about the result. - Growth Advisor: both the manual "Refresh now" trigger and the weekly
auto-refresh toggle reject the entry plan, by the same rule written out
twice, in two separate checks whose messages differ only in their last
few words (
api/routers/growth_advisor.py#trigger_briefing,api/routers/projects.py#update_project). - llms.txt Advisor: the same shape as Growth Advisor, a manual trigger
and a toggle, both rejecting the entry plan
(
api/routers/llms_txt_advisor.py#trigger_audit,api/routers/projects.py#update_project). - Data exports: the company's persisted
csv_exportsentitlement covers both CSV and JSON. Standard Trial, Starter, Growth and Pro presets enable it; price and plan name do not determine access. Any active project member can download, including viewers (api/routers/exports.py#exports_index,#download_export). The same entitlement gates exporting an Explorer result (api/routers/explorer.py#export_explorer). - Customer read API: the company's persisted
customer_apientitlement enables key creation and authenticated reads. Standard Starter, Growth and Pro presets enable it; Free and Trial do not. Company members and editors manage project-scoped keys. Existing keys can still be listed and revoked after entitlement loss or project archive. Citation records use the separatecitations:readpermission under the same API entitlement. Daily metrics usemetrics:readand do not need weekly-report access. Explorer queries and saved views use the opt-inexplorer:readpermission under the same API entitlement, with no extra plan flag (api/schemas/customer_api.py#ReadScope). Saved weekly digest reads additionally require the company's weekly-report entitlement and a key withreports:read; existing keys keep their scopes. The read-only MCP connector uses the same entitlement, scopes and per-key rate budget; it has no separate plan flag. See Customer API and keys (api/services/customer_api.py#api_available). - Explorer share links: the company's persisted
weekly_reportsentitlement, the same one that gates client report links. Standard Starter, Growth and Pro presets enable it; Free and Trial do not. It is checked when a company member or editor previews or creates a link and again every time the link is opened, so a link stops opening while the company's plan lacks it. See Dashboards and sharing (api/services/explorer/shares.py#preview_share,#resolve_share). - Analyst: the company's persisted
analystentitlement. Standard Starter, Growth and Pro presets enable it; Free and Trial do not. It is checked when a member asks a question and again when the question starts running. Any project member can ask, viewers included; without it, existing conversations stay readable and new questions are refused. See Analyst (api/services/analyst/conversations.py#analyst_available,api/services/analyst/pipeline.py#_eligible). - Social sources: the company's persisted
social_sourcesentitlement. Standard Starter, Growth and Pro presets enable it; Free and Trial do not. Any current project member can read the screen once it is enabled; adding or removing an own social profile stays with company members and a competitor's with company members and editors, unrelated to this entitlement. See Social sources (api/services/entitlements.py#standard_entitlements,api/routers/social_sources.py#_project_with_access). - Brand reasons: the company's persisted
brand_reasonsentitlement. Standard Starter, Growth and Pro presets enable reading the Brand reasons screen; Free and Trial do not. Reasons are extracted for every plan's answers, so upgrading shows reasons for answers analysed since the feature shipped. See Brand reasons (api/routers/brand_reasons.py#_project_with_access). - Objections: the company's persisted
objectionsentitlement. Standard Starter, Growth and Pro presets enable it; Free and Trial do not. It gates reading the Objections screen, the weekly study, Run now, theobjectionsfile export (which also needs the data-export entitlement), the customer API'sGET /objectionsand thelist_objectionsMCP tool (both of which also need customer API access and a key withobjections:read). Any current project member can read the screen once it is enabled. A study runs automatically every Wednesday at 05:00 UTC for each eligible project, with no setting to turn on, and company members and editors can also run one on demand, which is refused within 24 hours of the project's latest study (one that never started or was interrupted does not count). Without the entitlement no new studies run and the screen is locked; studies already stored are kept. See Objections (api/routers/objections.py#read_objections,api/services/objections/studies.py#start_manual_study,#enqueue_scheduled_studies,api/routers/exports.py#download_export,api/services/customer_api.py#objections_page,api/services/customer_mcp.py#list_objections). - Attributes: the company's persisted
attributesentitlement. Standard Starter, Growth and Pro presets enable it; Free and Trial do not. It gates reading the Attributes screen, the weekly study, Run now, adding and removing your own attributes, theattributesfile export (which also needs the data-export entitlement), the customer API'sGET /attributesand thelist_attributesMCP tool (both of which also need customer API access and a key withattributes:read). Any current project member can read the screen once it is enabled. A study runs automatically every Thursday at 05:00 UTC for each eligible project, with no setting to turn on, and company members and editors can also run one on demand, which is refused within 24 hours of the project's latest study (one that never started or was interrupted does not count). Without the entitlement no new studies run and the screen is locked; studies already stored are kept. See Attributes (api/routers/attributes.py#read_attributes,#add_custom_attribute,api/services/attributes/studies.py#start_manual_study,#enqueue_scheduled_studies,api/routers/exports.py#download_export,api/services/customer_api.py#attributes_page,api/services/customer_mcp.py#list_attributes). - Fact check: the company's persisted
fact_checksentitlement. Standard Starter, Growth and Pro presets enable it; Free and Trial do not (api/services/entitlements.py#standard_entitlements). It gates reading the Fact check screen, the weekly fact study and Run now, the checks of your checked prompts' answers, Suggest from my site, fact contradiction alerts, thefact_checksfile export (which also needs the data-export entitlement), the customer API'sGET /fact-checksand thelist_fact_checksMCP tool (both of which also need customer API access and a key withfacts:read). Any current project member can read the screen once it is enabled; company members and editors make every change. A study runs automatically every Friday at 05:00 UTC for each eligible project, and company members and editors can also run one on demand, which is refused within 24 hours of the project's latest study (one that never started or was interrupted does not count). The feature has its own fixed caps, the same on every plan that includes it: 50 active facts, 20 drafts, a selection of checked prompts, and 200 checks of tracked answers per project per UTC day. Without the entitlement no answer is checked, no study runs, no fact alert is raised and the screen is locked; facts and findings already stored are kept. See Fact check (api/routers/facts.py#read_facts,api/services/fact_check/studies.py#start_manual_study,#enqueue_scheduled_studies,api/services/fact_check/tracked.py#check_execution,#DAILY_CAP,api/services/fact_check/facts.py#MAX_ACTIVE_FACTS,#MAX_DRAFTS,api/schemas/fact_check.py#MAX_CHECKED_PROMPTS,api/services/fact_check/alerts.py#detect_fact_contradictions,api/routers/exports.py#download_export,api/services/customer_api.py#fact_checks_page,api/services/customer_mcp.py#list_fact_checks). - WordPress drafts: the company's persisted
cms_draftsentitlement. Standard Starter, Growth and Pro presets enable it; Free and Trial do not. It gates connecting a WordPress account and sending an article as a draft; reading an existing connection and its send history stays open to any current project member regardless. See WordPress drafts (api/services/cms/wordpress.py#owner_can_use). - Personas: the company's persisted
max_personasentitlement caps how many active personas a project can hold at once, by plan; see Pricing for each plan's number. Creating or restoring a persona past that cap is refused with a message naming the limit; archiving one you can no longer create or restore remains available regardless, so a downgraded company can still tidy up (api/services/personas.py#persona_limit,api/services/personas.py#_enforce_limit). Existing personas and their run history are unaffected by a plan change on their own. - Alert narration: the company's persisted
alert_narrationentitlement. Standard Starter, Growth and Pro presets enable requesting an AI reading of one alert's saved evidence; Free and Trial do not. Every alert is still detected and shown on every plan regardless; the entitlement only gates the request to explain one (api/services/alert_narration.py#_access). See Alerts. - Sub-brands: the company's persisted
brand_hierarchyentitlement. Standard Starter, Growth and Pro presets enable creating a sub-brand, restoring an archived one, and adding a name to an active sub-brand; Free and Trial do not. A brand can hold up to 10 active sub-brands, and a project up to 50 active sub-brands in total. Archiving a sub-brand, and removing an alias other than a sub-brand's own name, which can never be removed, stay available on every plan, so a project that has moved off a qualifying plan can still tidy up; an archived sub-brand's own aliases are frozen in the app until it is restored. See Brands and sub-brands (api/services/brand_families.py#hierarchy_available,api/services/brand_families.py#MAX_SUB_BRANDS_PER_BRAND,api/services/brand_families.py#MAX_SUB_BRANDS_PER_PROJECT). - Which AI engines actually run your prompts is plan-dependent too,
through a different mechanism again: each plan is linked in the database
to a set of engines, and only an engine linked to the company's plan, and
still available at all, is ever queried for its projects. Nothing here checks a
plan name (
api/services/plan.py#get_company_provider_ids). The standard plans are linked as follows: Free to ChatGPT and Gemini; Trial and Starter to those two plus Perplexity, Google AI Overviews and Google AI Mode; Growth to those five plus Grok; Pro to all seven, adding Claude (api/services/seed.py#DEFAULT_PLANS). Google AI Overviews, Google AI Mode, ChatGPT and Gemini are collected through a licensed data provider rather than an API (see Engines and measurement, How ChatGPT is collected and How Gemini is collected). A prompt left on "All engines on your plan" runs on all four as soon as the company's plan includes them. The monthly estimates on Pricing multiply prompt slots by engines by 31 days (Trial 3,875, Starter 7,750, Growth 27,900, Pro 86,800), so they are upper bounds: persona variants, Chinese variants and prompts over 700 characters do not run on the Google engines, persona, city and Chinese variants and prompts over 2,000 characters do not run on ChatGPT, persona and Chinese variants and prompts over 2,000 characters do not run on Gemini (city variants do), and a Google run can show no AI answer (api/services/prompt_variants.py#DAYS_PER_MONTH_ESTIMATE).
What happens when you hit one
The four metered columns, and every gate checked from a toggle or from a button whose endpoint reads a plan, share one behavior: the request is refused outright, with a message, before anything happens. Nothing is created, nothing is half-applied.
Two things behave differently, and both can leave a screen empty with
nothing said. The first is the two weekly background jobs. When the company's
plan resolves to a cap of zero for citation gaps or for page optimizations,
the weekly run for that project returns nothing and moves on; no browser is
waiting on it, so there is no request to fail and no message to show. The
result looks identical to a week where the job ran and genuinely found
nothing worth surfacing: an empty list either way
(api/services/citation_gap.py#find_gaps_for_project,
api/services/optimization/service.py#score_optimization_opportunities_for_project).
The second is the page-optimization Refresh button, which is a click with a
browser waiting on it, and whose two endpoints read no plan at all: on a cap
of zero the same generator returns nothing, and the request reports success
with an empty result instead of a refusal. What keeps a person off that path
is the Optimizations screen, which on the entry plan draws a link to the
plans page in place of the button, so what you meet there is a missing
control rather than a message
(api/routers/optimizations.py#refresh_project_optimizations,
#refresh_prompt_optimizations,
frontend/src/routes/(app)/optimizations/+page.svelte#refreshLocked). The
citation-gap button is not shaped this way: it has its own plan check and
answers a click with a refusal
(api/routers/citation_gaps.py#_require_on_demand).
This is the most useful distinction on this page: whether a limit shows up as a message you can act on, or as a queue that quietly never fills.
The billing screen
A company's Billing page is /companies/<id>/billing, and only that
company's members can open it. For anyone else, an editor or viewer of one
of its projects included, the page and every billing request behind it
answer "not found" (api/dependencies.py#get_company_for_member,
api/routers/billing.py#billing_page). The old Settings → Billing address
still works: it sends a company member on to the Billing page of the
current project's company, and anyone else to Your profile
(frontend/src/lib/company.js#billingRedirectPath).
The page shows the company's plan name and its monthly price, a status
chip, and one of three renewal states: renewing on a coming date,
cancelling on a coming date and reverting to the entry plan then, or no
renewal date at all because nothing is currently being charged
(api/routers/billing.py#billing_page,
frontend/src/routes/(app)/companies/[id]/billing/+page.svelte). The chip
shows the subscription's status, or, when nothing is subscribed, "no card
on file" if the company has never started a checkout and "not subscribed"
if it has. A failed renewal payment shows as "past due", with a line asking
you to update your card in Manage billing: Stripe retries the payment for a
while, and the plan stays on until the retries run out, or for at most 30
days from the first failed renewal, whichever comes first
(api/services/billing.py#GRACE_SUBSCRIPTION_STATUSES, #PAST_DUE_GRACE,
#subscription_grants_paid_access). A subscription that still exists on
Stripe but no longer pays (its payments failed, it is paused, its first
payment never went through, or its renewal kept failing) is shown by its
plan's name and status, with a line saying why paid features are off; the
usage bars then show the Free plan's limits, which apply until it is
settled in Manage billing (api/routers/billing.py#_billing_page_subscription). When a cancellation is scheduled, the
renewal line gives the date it takes effect and says you can undo it in
Manage billing. When a downgrade is queued, a banner names the
plan you are moving to and when it starts, and says that choosing your
current plan under Change plan keeps it. If another plan's features are
already switched on ahead of the billing date, the banner also names which
plan is still being billed until then; if they are not, it says only that
billing stays where it is until that date
(api/routers/billing.py#_subscription_info,
frontend/src/routes/(app)/companies/[id]/billing/+page.svelte#sub).
Under the plan, Covers every project in the company names its active
projects, because a plan bought here applies to every one of them
(frontend/src/routes/(app)/companies/[id]/billing/+page.svelte#coveredProjects).
Manage billing, beside Change plan, opens Stripe's billing page for the
company: its card, past invoices, billing address and tax ID, switching
plan and cancelling. It appears once the company has started a checkout,
and stays there after a subscription ends or stops being paid, since the
card and the invoices are still on Stripe's side
(api/routers/billing.py#billing_page, #create_portal_session). Manage
billing, and every choice under Change plan except ending a trial, leave
the app for Stripe's own pages at checkout.stripe.com or
billing.stripe.com, and Stripe sends you back to the Billing page of the
same company, so a checkout always confirms against the company it started
in. The app follows a link only to those two Stripe addresses or back to
this company's own Billing page, so a link to anywhere else is refused with
a message to retry
(frontend/src/routes/(app)/companies/[id]/billing/redirects.js#isAllowedBillingRedirect).
Coming back, a line at the top says what happened: a finished payment is
first confirmed against Stripe, so the plan below is already the new one
(or, if Stripe has not caught up, the line says the plan will update in a
moment, and the screen checks again a few times); a checkout you left says
you have not been charged; and a change made on Stripe's billing page says
billing is updated
(frontend/src/routes/(app)/companies/[id]/billing/+page.server.js#readNotice,
api/routers/billing.py#confirm_checkout). A return that names a checkout
which is not this company's, or not a checkout at all, shows nothing.
Underneath, prompt slots and projects render as usage bars, used against
total, and both are pooled across the company: prompt slots count the
active prompt targets in its active projects, and projects count its active
projects, the same counts the limits use. When the company has more than
one active project, the prompt-slot bar also lists how many slots each one
uses. When the plan's column carries no ceiling, the total reads as
unlimited, no bar is drawn (a full bar would read as "at the limit"), and
the note under it says there is no limit on this plan
(api/routers/billing.py#_subscription_info,
frontend/src/routes/(app)/companies/[id]/billing/+page.svelte#meter,
#promptMeter, #projectMeter). There is no seat bar, because seats are
unlimited. Below that, a features list keyed to the plan's name, and a
payments list capped at a fixed number of recent rows, each with a link to
its invoice when there is one, and a note when it is showing only the
newest slice (api/routers/billing.py#PLAN_FEATURES, #billing_page).
Payments come from Stripe's paid invoices; one whose notification from
Stripe was lost is added by a daily check against Stripe
(api/services/billing_reconcile.py#_record_paid_invoices).
The company's first paid plan starts on Stripe's checkout page, opened from
the plan picker (Choose a plan, or Change plan during a trial). A checkout
is refused while the company already has a subscription, which is changed
on Stripe's billing page instead; the product trial does not count, since
paying for a plan ends it. A plan our team set up for the company, rather
than one bought through Stripe, cannot be changed from the plan picker at
all: it says so and gives hello@discoveredby.ai
(api/routers/billing.py#create_checkout_session,
api/services/billing.py#subscription_blocks_new_checkout). Once the
company is on a paid plan, choosing another plan under Change plan opens
Stripe's billing page on that one change, and choosing Free opens it on
cancelling; Manage billing opens the same page at its start. All three kinds
of change run there, on the same timing
(api/routers/billing.py#create_portal_session):
- Upgrades apply at once, and Stripe charges the prorated difference for the rest of the period already paid for.
- Downgrades take effect at the end of the paid period. Until then the billing screen shows the change as scheduled, and choosing the current plan again under Change plan drops it and keeps the company where it is. If a move to a cheaper plan is scheduled, choosing another plan or cancelling drops that scheduled move, even if you leave Stripe's page without confirming. If Stripe's page cannot be opened, the scheduled move stays.
- Cancelling ends paid access at the end of the paid period, not at once, and the company then drops to Free. Until that date the plan keeps working, and you can undo the cancellation on Stripe's billing page. Asking to cancel again while a cancellation is already scheduled is refused, and so is changing plan: undo the cancellation first.
Switching and cancelling need a Stripe subscription that has not ended;
without one there is nothing to change, and the request is refused. Manage
billing needs only that the company has started a checkout. Ending the
no-card product trial is the one change that happens in the app itself:
choosing Free during the trial ends it at once and moves the company to
Free. That same request refuses a paid plan, which is only cancelled on
Stripe's billing page (api/routers/billing.py#cancel_subscription).
One more re-check belongs here even though it happens on a different
screen: resuming a paused project runs through the exact same active-project
check that creating a brand new one does, not a lighter version of it. If
you paused a project specifically to get under the company's project limit,
resuming it later can be refused the same way starting a new project would
be, if the company is still at that limit when you try
(api/routers/projects.py#update_project,
api/services/limits.py#check_project_limit).
Importing prompts, checking robots.txt and site audits
CSV and Excel (.xlsx) prompt imports are available on every plan, subject to the company's prompt slots. Excel reads the first worksheet only; see Prompts for file limits and validation.
Robots diagnostics is included on standard Starter,
Growth and Pro plans, but not Free or Trial. Company members and editors can
run checks; viewers cannot. Custom plans use the saved robots diagnostics
feature setting. This checks declared policy, without measuring bot visits or
actual access. Saved page diagnostics reuses
this feature setting for explicit policy, HTTP and HTML checks with recheck
history. Site audit reuses the same feature
setting to start a crawl of the project's site; stopping a running audit
only needs company member or editor access and never checks this feature
setting, so an audit already in progress can always be stopped
(api/modules/website_crawler/projects.py#start_crawl, #stop).
Every current project member can read saved results, including after a
downgrade. There is no new plan flag or pricing change.
Languages, engine choice and variant templates
Every plan; each variant uses a prompt slot. Running a prompt in a
language, restricting which
engines it runs on, and saving a country/audience/language/engine
combination as a reusable template are all available on every plan, with
no entitlement of their own: a prompt tops out at 100 active variants
(countries times audiences times languages), enforced on every path that
can add one, creating or editing a prompt, bulk-applying a template,
CSV/Excel import, and accepting a suggested or discovered prompt (saving a
template is capped the same way, so its own grid can never be saved over
100 either). Editing a prompt or bulk-applying a template to one is the
one exception: either can keep a grid already larger than 100 from before
this release, just never grow it further. A project can hold at most 20
saved templates, the same ceilings regardless of plan
(api/services/prompt_variants.py#MAX_VARIANTS_PER_PROMPT,
#variant_cap_error, #_per_prompt_over_cap,
api/services/variant_templates.py#TEMPLATE_LIMIT). Choosing fewer
engines for a prompt never frees or costs a prompt slot; it only changes
how many answers that prompt produces a month.
Explorer, saved views and dashboards
The Explorer, saved views and
dashboards are on every plan,
with no entitlement of their own: they read the answers a project has
already collected and cost nothing extra to run. Their limits are the
same on every plan: a project keeps up to 100 saved views and 20
dashboards of up to 12 views each, and runs up to 120 Explorer queries a
minute, shared by the whole team, its exports, share previews and its API
keys (api/schemas/explorer.py#MAX_VIEWS, #MAX_DASHBOARDS, #MAX_TILES,
api/services/explorer/budget.py#QUERIES_PER_MINUTE). Only exporting a
result, sharing a snapshot by link and reading through the API use a plan
entitlement, each listed above.
Prompt coverage
Prompt coverage, the Coverage tab on
Prompts, is on every plan with no entitlement of its own: it reads the
answers a project has already collected, calls no AI model and stores
nothing of its own. Every project member can read it and preview a
selection; company members and editors can pause from it through the same bulk
pause as the Tracked tab. Pausing frees the paused prompts' slots, and
resuming one later needs free slots, the same as any other resume
(api/routers/prompt_coverage.py#read_coverage, #preview_coverage,
api/services/limits.py#get_active_prompt_slot_count,
#reserve_prompt_slots).
Related
- Team: company members, project editors and viewers, and why only company members see billing
- Create your account: what a project and a company are, how sign-in works, and the companies listed on Your profile
- Prompt suggestions: the on-demand and weekly-refresh entitlements for prompt discovery, and what counts against a prompt slot
- Citation gaps: the weekly opportunity generation this page describes as a background gate, from the screen where its results actually appear
- Articles: the weekly article quota in practice, and how the drafting strategy itself changes by plan
- Languages and templates: the 100-variant and 20-template ceilings in practice, and the preview that shows the slot cost before you save
- Dashboards and sharing: the saved-view, dashboard and share-link limits in practice
- Objections: when the weekly study runs and how the Run now cooldown counts
- Prompt coverage: which running prompts you could pause to free slots while what they see regularly is still covered
- Fact check: what the fact study and the checks of your checked prompts do, and the daily check limit
Last verified 2026-11-01