Platform

Pricing & plans

A plan buys access, an allowance in dollars of model spend, and a ceiling. Tokens are priced per request against the catalog. This page explains how those three interact.

The commercial page is at lobstack.ai/pricing, and both pages read the same plan catalogue, so the numbers cannot drift apart. This page is about the mechanics behind them: what the allowance counts, what the ceiling does to routing, and what the metered dollar figure on each response is and is not.

The plans

FreeTeam
Per month$0$79
Per year—$758
Included$5 to start, once$20 of model usage at provider prices
Metered onModel spendModel spend
Ceilingstandardflagship
Seats110
Top-upsNoYes
Savings creditNoNo
Own provider keysNoYes
Clients with budgetsNoneUnlimited clients
Spend capsNonePer client, person and key
Permission settingsNoneWho creates keys and changes caps
Calls at once (paid plans warned, not yet refused)5, refused over30
Request history7 days1 year
Audit recordNoneScreen and CSV

A plan used to include a count of messages. A message is not a unit of cost — the same word covered a forty-token ping and a two-hundred-thousand-token context — so an allowance denominated in messages bounded nothing. A plan now sells Lobstack itself, and includes dollars of model usage, spent at the provider's own prices. Past that, calls are charged at provider price + 50%, and the receipt on every response says which of the two applied. Annual billing takes 20% off; the included usage stays monthly and resets monthly.

Paid plans can also add their own provider keys in Settings › Provider keys. A call that runs on one of your keys is metered and receipted, but it is not marked up and does not spend included usage or credit. The BYOK plan, metered on requests, is no longer sold.

A top-up buys credit: any whole amount from $25 to $1,000, with $25, $50, $100, $250 one click away. Credit is spent at provider price + 50% after the month's included usage, it does not expire, and it does not change the plan. Buy it in Console › Settings › Billing or on Usage, on a plan that sells it: Free cannot top up, because the wall is what makes the case for paying.

Subscriptions run through Stripe Checkout against the Price carrying each plan's lookup key (lobstack_<plan>_<monthly|annual>); a top-up is priced inline for the amount chosen, and the webhook never credits more than was paid. Both paths require STRIPE_SECRET_KEY in the environment, and without it the checkout routes throw rather than degrade. While a previous Stripe account still bills subscriptions, STRIPE_LEGACY_SECRET_KEY lets its customers open the billing portal and STRIPE_LEGACY_WEBHOOK_SECRET verifies its webhooks.

Free trial credit

Free is $5 to start, once. A verified account that starts with the API or the Lobstack app gets $5 of Gateway model usage for 30 days. On Free it is spent at the provider's price. On a paid plan it is drawn only after the month’s included usage is used up, at provider price + 50% like any other usage past it. It is counted in x-lobstack-quota-allowance-usd (what is left of it is in x-lobstack-quota-credit-usd), and whatever is unused when it expires lapses. One per organization, and one per person.

When it is unavailable or used, the Gateway refuses Free calls with a 402 carrying a machine-readable credit error code and no retry-after, because nothing resets. API callers can choose a paid plan for managed usage or add an organization provider key on a paid plan in Settings › Provider keys. The app keeps working free on your own provider key or GitHub Copilot, neither of which goes through the Gateway. There is no weekly credit any more; a weekly grant issued before 13 October 2026 is still spent and expires on its Monday.

How much history each plan keeps

Logs, Usage, /api/v1/usage and /api/v1/requests show request-by-request history for 7 days on Free, 1 year on Team. A period that reaches further back starts where your plan's history does, and the response says so in history.limited; the Console greys out the periods your plan does not include.

Rows older than your plan's history plus 30 days may be deleted, and nothing in the current billing month ever is — so upgrading within a month brings the older history back. Monthly totals per client and model are kept either way, and a client statement for any past month still adds up.

What the ceiling does

The plan ceiling is the highest tier that "auto" may reach. Free is capped at standard; every paid plan reaches flagship. Paid plans differ in allowance, seats and the organisational features, not in which models they can call.

The cap on Free is a cost control that works in the account holder's favour. A few long flagship requests can spend the whole $5 credit; capped at standard it runs to hundreds of calls.

A hard prompt against the cap does not fail and does not silently cost more. It is served by the best model under the ceiling and x-lobstack-tier comes back naming that tier, so you can see the cap acting rather than infer it from a worse answer.

Naming a model lowers the ceiling too. Asking for a standard model on a plan that reaches flagship caps that request at standard; the effective ceiling is always the lower of the two.

You can watch the router decide without spending a token on the routing preview. Its plan_tier parameter still takes the legacy tier names rather than the plan ids above: starter reproduces a standard ceiling, and pro, performance and enterprise reproduce flagship. Anything else falls back to pro, so a preview sent "free" today answers as though it were a flagship-ceiling plan.

What the allowance counts

Three meters, because three different things have been sold. Every response names the one that applied in x-lobstack-quota-meter.

MeterApplies toThe wallHeaders
spendA plan that includes dollars of model spendIncluded allowance, plus purchased top-ups, plus credited savings, plus any trial credit, minus what has been spent this periodquota-allowance-usd, quota-spent-usd, quota-remaining-usd, quota-credit-usd
requestsThe BYOK plan, no longer soldIncluded requests for the calendar monthquota-limit, quota-used, quota-remaining
legacyA subscription bought on the older messages-per-month tiersThat subscription's own message allowance, counted exactly as it always wasquota-limit, quota-used, quota-remaining, quota-credits

The allowance is enforced for every credential. Legacy agent credentials were exempt until 2026-09-28, while the machines they belonged to still ran; none do now.

A spend meter emits dollar headers and no request counters. A zero in x-lobstack-quota-limit would be read as "no allowance" by a client that cannot tell which meter it is on, so the counters are absent rather than zero.

Only requests that returned below 400 count against an org key's request allowance. A provider outage on our side does not consume your quota. The same rule holds on a spend meter: an error row accrues no spend.

What a refusal looks like

An exhausted allowance is a 402 of class quota, and the message is written in the unit the customer actually bought. retry-after carries the seconds until the period resets, which on a monthly allowance is usually days rather than seconds. Free's refusal has no retry-after: its credit does not come back.

Calls to providers you hold your own key for are the exception: they spend no allowance, so they still go through, and auto routes only among those providers.

Spend meter, on a paid planjson
{
  "error": {
    "message": "monthly allowance exhausted: this month's included usage and your credit are used up. Top up any amount in Console › Settings › Billing (credit does not expire), upgrade the plan, or wait for the month to reset.",
    "type": "quota",
    "code": 402,
    "request_id": "8f2b1e0c-4d5a-4b91-9c3e-6a7f0d2b5c41"
  }
}
Free, once the trial credit is usedjson
{
  "error": {
    "message": "Your free credit is used. Keep going free with your own provider key or GitHub Copilot in the Lobstack app; for Gateway API calls, pick a paid plan for managed usage or add an organization provider key in Console › Settings › Provider keys: https://www.lobstack.ai/pricing",
    "type": "quota",
    "code": 402,
    "error_code": "FREE_CREDIT_USED",
    "request_id": "8f2b1e0c-4d5a-4b91-9c3e-6a7f0d2b5c41"
  }
}
Request and legacy metersjson
{
  "error": {
    "message": "monthly allowance exhausted (100,000 of 100,000 requests). Upgrade the plan or wait for the period to reset.",
    "type": "quota",
    "code": 402,
    "request_id": "8f2b1e0c-4d5a-4b91-9c3e-6a7f0d2b5c41"
  }
}

Quoting requests to somebody who bought dollars is a support ticket, and quoting dollars to a legacy subscriber who bought messages is a broken promise, so the message names the meter it is refusing on. Errors & retries has the rest of the taxonomy.

Token metering

Independently of the allowance, every request is priced. The catalog holds a per-million input price and a per-million output price for each model key, verified against each provider's own pricing page on 2026-10-16, and the ledger row freezes the prices that were in force when the request ran.

A request has two costs and they are not the same number. The catalog holds the provider's list price, which is what the tokens cost us. The Lobstack rate is that figure times 1.5. A call inside the plan's included usage, and every Free call, is debited at the list price; a call past it, or spending purchased credit, at the Lobstack rate, and a call that crosses the line is split. The receipt reports the result. Each tier's lead model:

ModelTierList $/1M inList $/1M outLobstack $/1M inLobstack $/1M out
gemini-3.1-flash-litenano$0.25$1.50$0.375$2.25
claude-haiku-5-5small$0.10$0.50$0.15$0.75
claude-sonnet-5-5standard$2.00$10.00$3.00$15.00
gemini-3.1-propremium$2.00$12.00$3.00$18.00
claude-opus-5-5flagship$4.00$20.00$6.00$30.00
What a request costs past the included usage
1,000 input + 500 output tokens on claude-sonnet-5

  provider list           0.007000
  x 1.5 Lobstack rate
                          ─────────
  x-lobstack-cost-usd     0.010500

The multiplier applies to managed traffic only. On a call that ran on your own provider key (byok) and in direct mode you have already paid your provider, so the row carries the provider figure in both columns and is marked not billable. What we paid is recorded on the ledger row as provider_cost_usd and never leaves the server: it is in no header, no stream frame and no API response.

A model missing from the catalog entirely is priced as null and the response says x-lobstack-priced: false. It is never recorded as free.

The full catalog, with every price and provider, is on Models & providers, and GET /api/gateway/v1/models returns the same figures as JSON.

The ledger is not the invoice

A spend allowance is consumed by the dollar figure on each ledger row, and running out of allowance is what a 402 means. It is not a separate line billed on top of the subscription: the subscription and any top-ups you bought are the charges, and the metering is the record of what they were spent on. Legacy agent billing works differently again, with per-message overage rates that run from $0.01 to $0.05 depending on the model, and a message-credit top-up consumed once the monthly allowance is gone.

If you need an authoritative figure for what you owe, read your Stripe invoices, not this metering. If you need to know where your spend went and which key or model caused it, read the metering, because the invoice will never tell you that.

The two can disagree where the metering pre-dates its own columns. A row written before 20260910_spend_metering.sql carries a customer cost and no margin columns, and a row older than the priced ledger carries no cost at all. Nothing backfills either, because the prices and the plan in force at the time are not recoverable, so those gaps stay visible as gaps rather than filled in with a number nobody can reconstruct.

Savings, and when there are none

A dollar saving is the difference between what a baseline model would have charged for these exact token counts and what you were charged. When you named a model, that model is the baseline, baseline_reason reads named, and the comparison needs no explanation.

On "auto" there is no model you asked for. The baseline is then the most expensive managed model your plan may reach and baseline_reason reads plan_ceiling. That is a real comparison — it is what you would have paid had you asked for the best one — and it is not the same claim as a saving against a model you actually named. It is also the most favourable comparison available to us, which is why it is labelled rather than merged into one number. A client that renders the figure without the reason is reporting a saving against a model its user never chose.

The credit share is currently 0%: a verified saving is reported on the receipt and extends no allowance. Verified means all of: the plan meters spend, the request ran on our provider key, the row is not an error row, both models priced, and the baseline is strictly above what was actually charged. Fail any one and the saving is zero.

Routing does not always find something cheaper. On the calls where it does not there is no saving, and nothing here promises a saving of any particular size — the figure is whatever is measured, which is sometimes nothing.

The percentage in x-lobstack-savings-pct is something else: a heuristic from tier cost multipliers, present on every response. Do not add the two up or treat one as a rounded version of the other. The full rule set is on Metering & cost.