Guide

How LLM gateway pricing works

Written by Published Updated

Short answer

Total LLM gateway cost is model usage plus applicable gateway and platform fees plus operational cost. Compare token markup, credit-purchase fees, subscriptions and optional features separately. BYOK changes the billing route; self-hosting changes who operates the gateway. Neither makes the entire service free.

The four mechanisms

These get discussed as if they were variations on one thing. They are not. A percentage fee grows with usage and is invisible at small scale; a seat fee is fixed and is nearly all of your cost at small scale. Two products with identical headline claims can differ by an order of magnitude at your volume depending on which of these they use.

Markup on tokensMarkup: A percentage the gateway adds on top of what the model actually costs. Some charge none at all and make money elsewhere.
A percentage added to what the model actually cost. Charged on consumption, so it scales exactly with usage and disappears when you are idle. The most predictable of the four, and the easiest to model.
A cut when you add fundsCredit or top-up fee: A cut taken when you add money to a prepaid balance, typically around 5%. Easy to miss because it is not a markup on tokens — but you pay it on every dollar you load.
Taken when you top up a prepaid balance rather than when you spend it, typically around five per cent. Easy to miss because it never appears on a per-token price list, and you pay it on money you have not spent yet.
Per developer, per month
A flat seat charge. Independent of how many tokens you push through, which makes it punishing on a small workload with a large team and excellent on a large workload with a small one. Grows with hiring, not with traffic.
Self-hosted softwareSelf-hosted: You operate the software on your infrastructure and own its uptime, patching and upgrades. Model hosting, telemetry and control planes may still involve third parties; commercial editions can have licence fees.
A permissively licensed open-source edition can have no software licence fee; verify paid editions and services separately. You pay for infrastructure, and — the line that appears on no pricing page — for the engineer time to operate a service that is now in your request path.

A fifth thing is not a mechanism but changes the arithmetic: BYOKBYOK — bring your own key: You keep your own accounts and contracts with OpenAI, Anthropic and the rest, and the gateway routes through your keys. You keep your negotiated rates and any committed-spend discounts; the gateway charges you for the plumbing, not the tokens.. You keep your own provider contracts and the gateway routes through your keys, so you keep any negotiated rate and the gateway charges only for the plumbing. It does not lower the token price; it stops the gateway from being the one who sets it.

What each one actually costs

These four illustrative workloads hold blended model prices constant to compare gateway overhead. Real model prices, discounts and routes can differ. The numbers use the same catalogue and computation as the cost estimator; they exclude model spend from the overhead columns and do not price engineering labor. Vercel represents credits with optional add-ons, not a mandatory seat subscription.

Recorded base fees used in the estimates; optional charges and edition costs are separate.
ProductToken markupCredit feeSeat fee
Requesty 5% Checked 2026-08-29 Not published Check date not recorded None Checked 2026-08-29
OpenRouter None Checked 2026-08-29 5.5% Checked 2026-08-29 Not published Check date not recorded
Vercel AI Gateway None Checked 2026-08-29 None Checked 2026-08-29 None Checked 2026-09-16
LiteLLM None Checked 2026-08-29 None Checked 2026-08-29 None Checked 2026-08-29
Monthly gateway overhead for four workloads across four charging mechanisms.
Workload Assumed model spend Requesty Markup on tokens OpenRouter Cut when you add funds Vercel AI Gateway Gateway credits; optional add-ons LiteLLM Self-hosted; assumed infrastructure
Prototype 10k requests · 1 seat $6.752M input × $1.5/M + 0.5M output × $7.5/M; assumed rates. Infrastructure allowance: $10/month. $0.34
Partial estimate: scope
  • Credit-purchase fees are not published; this estimate is incomplete.
 $0.80
Partial estimate: scope
  • Seat fees are not published; this estimate is incomplete.
  • Assumes one credit purchase equal to model spend, with the percentage added to usable credits. More top-ups can incur additional minimum fees.
  • Not included, because these are optional or priced per unit rather than per request: Crypto (Coinbase) credit purchase fee (5%); Card credit purchase fee minimum ($0.80 per purchase). Add them yourself if they apply.
 $0.00
Partial estimate: scope
  • Not included, because these are optional or priced per unit rather than per request: Team-wide zero data retention ($0.10 per 1,000 requests (Pro and Enterprise)); Team-wide provider allowlist ($0.10 per 1,000 successful requests (Pro and Enterprise)); Custom Reporting writes ($0.075 per 1,000 tag / user ID / quota entity writes); Custom Reporting queries ($5 per 1,000 queries to the reporting endpoint); Optional Vercel Pro developer seat ($20 per month); Optional Trace Drains delivery ($0.05 per 1,000 traces (Pro and Enterprise)); Optional Trace Drains egress ($0.50 per GB (Pro and Enterprise)). Add them yourself if they apply.
 $10
Partial estimate: scope
  • Self-hosting also costs engineering time to deploy, monitor, and upgrade, which this tool does not price.
assumed
Early product 250k requests · 3 seats $15050M input × $1.5/M + 10M output × $7.5/M; assumed rates. Infrastructure allowance: $40/month. $7.50
Partial estimate: scope
  • Credit-purchase fees are not published; this estimate is incomplete.
 $8.25
Partial estimate: scope
  • Seat fees are not published; this estimate is incomplete.
  • Assumes one credit purchase equal to model spend, with the percentage added to usable credits. More top-ups can incur additional minimum fees.
  • Not included, because these are optional or priced per unit rather than per request: Crypto (Coinbase) credit purchase fee (5%); Card credit purchase fee minimum ($0.80 per purchase). Add them yourself if they apply.
 $0.00
Partial estimate: scope
  • Not included, because these are optional or priced per unit rather than per request: Team-wide zero data retention ($0.10 per 1,000 requests (Pro and Enterprise)); Team-wide provider allowlist ($0.10 per 1,000 successful requests (Pro and Enterprise)); Custom Reporting writes ($0.075 per 1,000 tag / user ID / quota entity writes); Custom Reporting queries ($5 per 1,000 queries to the reporting endpoint); Optional Vercel Pro developer seat ($20 per month); Optional Trace Drains delivery ($0.05 per 1,000 traces (Pro and Enterprise)); Optional Trace Drains egress ($0.50 per GB (Pro and Enterprise)). Add them yourself if they apply.
 $40
Partial estimate: scope
  • Self-hosting also costs engineering time to deploy, monitor, and upgrade, which this tool does not price.
assumed
Scaling product 3M requests · 8 seats $1,800600M input × $1.5/M + 120M output × $7.5/M; assumed rates. Infrastructure allowance: $250/month. $90
Partial estimate: scope
  • Credit-purchase fees are not published; this estimate is incomplete.
 $99
Partial estimate: scope
  • Seat fees are not published; this estimate is incomplete.
  • Assumes one credit purchase equal to model spend, with the percentage added to usable credits. More top-ups can incur additional minimum fees.
  • Not included, because these are optional or priced per unit rather than per request: Crypto (Coinbase) credit purchase fee (5%); Card credit purchase fee minimum ($0.80 per purchase). Add them yourself if they apply.
 $0.00
Partial estimate: scope
  • Not included, because these are optional or priced per unit rather than per request: Team-wide zero data retention ($0.10 per 1,000 requests (Pro and Enterprise)); Team-wide provider allowlist ($0.10 per 1,000 successful requests (Pro and Enterprise)); Custom Reporting writes ($0.075 per 1,000 tag / user ID / quota entity writes); Custom Reporting queries ($5 per 1,000 queries to the reporting endpoint); Optional Vercel Pro developer seat ($20 per month); Optional Trace Drains delivery ($0.05 per 1,000 traces (Pro and Enterprise)); Optional Trace Drains egress ($0.50 per GB (Pro and Enterprise)). Add them yourself if they apply.
 $250
Partial estimate: scope
  • Self-hosting also costs engineering time to deploy, monitor, and upgrade, which this tool does not price.
assumed
Heavy production 25M requests · 25 seats $14,2505000M input × $1.5/M + 900M output × $7.5/M; assumed rates. Infrastructure allowance: $1200/month. $713
Partial estimate: scope
  • Credit-purchase fees are not published; this estimate is incomplete.
 $784
Partial estimate: scope
  • Seat fees are not published; this estimate is incomplete.
  • Assumes one credit purchase equal to model spend, with the percentage added to usable credits. More top-ups can incur additional minimum fees.
  • Not included, because these are optional or priced per unit rather than per request: Crypto (Coinbase) credit purchase fee (5%); Card credit purchase fee minimum ($0.80 per purchase). Add them yourself if they apply.
 $0.00
Partial estimate: scope
  • Not included, because these are optional or priced per unit rather than per request: Team-wide zero data retention ($0.10 per 1,000 requests (Pro and Enterprise)); Team-wide provider allowlist ($0.10 per 1,000 successful requests (Pro and Enterprise)); Custom Reporting writes ($0.075 per 1,000 tag / user ID / quota entity writes); Custom Reporting queries ($5 per 1,000 queries to the reporting endpoint); Optional Vercel Pro developer seat ($20 per month); Optional Trace Drains delivery ($0.05 per 1,000 traces (Pro and Enterprise)); Optional Trace Drains egress ($0.50 per GB (Pro and Enterprise)). Add them yourself if they apply.
 $1,200
Partial estimate: scope
  • Self-hosting also costs engineering time to deploy, monitor, and upgrade, which this tool does not price.
assumed

All columns are estimates, not vendor quotes. Input and output token rates are assumptions; see the workload inputs in the table. The self-hosting allowance excludes labor and commercial licensing. Optional charges and unknown fees are disclosed beneath each result. A lower partial estimate is not proof of a cheaper complete service.

Calculate the fee on the right base

For a hypothetical $100 of usable credits, a 5% fee added to the purchase costs $105. If a different service deducts 5% from the payment, you must pay $100 ÷ 0.95 = $105.26 to receive the same credit. Neither percentage describes token markup unless the contract says so. A minimum fee can dominate small purchases, and repeated top-ups can trigger it repeatedly.

For a purely hypothetical $20 monthly fixed fee versus a 5.5% fee added to purchased credits, the fee-only crossover is $20 ÷ 0.055 ≈ $364 of credits, assuming one seat, no minimum, no other fees and full consumption. This is not a Vercel-versus-OpenRouter recommendation. Change the seat count, fee basis or consumption and the answer changes.

Vercel documents gateway credits without a mandatory token platform fee (reviewed September 16, 2026). Charge a platform subscription to the gateway decision only when the required feature creates that incremental expense; also show the full allocated cost if finance needs it. Add-ons remain separate.

Which mechanism suits you

Prefer a percentage if

  • Your traffic is spiky, seasonal, or still unpredictable.
  • You have more developers than you have token volume.
  • You want cost that falls to nearly nothing in a quiet month.
  • You are still prototyping and want no fixed commitment at all.

Prefer a flat seat fee if

  • Your applicable fixed fee is cheaper under the same usage, feature and contract assumptions.
  • Finance wants a predictable line item rather than a variable one.
  • The team is small and the workload is large.

Prefer self-hosting if

  • You are choosing it for control, licence or data residency — not for the fee.
  • You already run a platform team who can own another service.
  • A third party in the request path is unacceptable regardless of cost.

Insist on BYOK if

  • You have negotiated rates or committed spend worth protecting.
  • You want the option to leave without renegotiating with model providers.
  • Your security model requires the provider contract to be in your name.

What the headline number leaves out

Five charges that sit outside the four mechanisms and are routinely missed. A per-request surcharge for zero data retention, which turns a compliance requirement into a usage fee. A log-retention tier, where the useful retention window is on a higher plan than the one you priced. A minimum commitment or annual floor. Overage pricing that differs from the rate you were quoted. And guardrail or moderation features billed separately from the requests they inspect.

The catalogue currently records explicit zero values for token markup, credit fee and seat fee for 5 of 31 products. That narrow three-field count does not establish that all features, editions or operations are free. Missing values are excluded, not treated as zero. Use the estimator for an itemized scenario and spending limits for enforcement.

Common questions

Is a 5% credit top-up fee worse than a 5% markup on tokens?

They are close to equivalent in effect and differ in what they apply to. A markup is charged on the tokens you actually consume. A top-up fee is charged on every dollar you load onto a prepaid balance, whether or not you spend it, so unused balance has already been taxed. A fee added to credits and a fee deducted from payment have different arithmetic. Compare the same usable balance, minimum charge and number of top-ups.

Is a zero-markup gateway actually free?

Zero markup means no percentage on tokens. It does not mean no cost. Look for a per-seat charge, a cut when you add funds, a per-request surcharge for zero data retention, a log-retention tier, and a minimum commitment. The estimator shows each of those as a separate line rather than one total, because which line you are paying determines how the cost grows.

Does BYOK save money?

It changes who bills you for tokens rather than reducing the token price. With BYOK you keep your own provider contracts, so you keep any negotiated rate or committed-spend discount, and the gateway charges you for the plumbing only. That is worth real money if you have a discount to protect. If you are paying list price anyway, BYOK mainly buys you the ability to leave without re-signing anything.

At what point should I self-host to save on fees?

Later than the fee percentage suggests, because the fee is not what you are comparing against. A self-hosted gateway costs infrastructure plus the engineer time to deploy it, monitor it, upgrade it and be paged for it, and that last part is the expensive one and appears in no pricing page. The honest answer is that self-hosting is usually chosen for control, data residency or licence reasons, and the fee saving is a bonus rather than the trigger.

Why do the fees in this guide differ from the vendor pricing page?

They should not. Every figure here is read from this site’s catalogue, and each catalogue value carries the vendor page it came from and the date it was checked. If you find a difference, the vendor page wins and we want to know: the corrections form goes straight to the person who maintains the row.

Do these examples include the cost of the tokens themselves?

No, deliberately. The table shows gateway overhead only, because the example deliberately holds blended model rates constant, and mixing the two makes a large identical number hide a small differing one. The estimator can show either view.

Next