What It Costs to Run an AI App on SkillSafe
Every number behind an app run: per-model rates, the 1.2× platform multiplier, credits at $1 = 10,000, creator margins, free grants, and the BYOK flat-rate lane — with worked examples.
The short answer: a run costs the model’s list price × 1.2, metered on the tokens it actually used, plus the app creator’s margin — all charged in credits at $1 = 10,000 credits, rounded up to whole credits with a 1-credit minimum. A chat turn on the default Workers AI model costs 4 credits ($0.0004); a hefty Claude Sonnet 5 run costs a few hundred. This post walks through every number, because opaque AI pricing is a choice and we made the other one.
Credits: $1 = 10,000
Credits are not a token or a points scheme — they’re dollars at a fixed denomination. One credit is $0.0001, chosen so that genuinely cheap runs can be billed exactly instead of rounding up to a whole cent. Your balance is shown in dollars, activity rows show exact costs, and cash amounts convert at the same rate in both directions.
What a Run Costs: Model Rate × 1.2
Every model an app can run has a published rate on the model catalog — billed dollars per million input and output tokens. The billed rate is the provider’s list price times 1.2; that margin covers Stripe fees, refunded runs, and infrastructure, and it’s the platform’s entire cut of usage (creators keep 100% of their markup).
The mechanics protect you on both sides:
- Before a run, the platform estimates the worst case and places a hold — you see the estimate before clicking run.
- The run settles at actual usage reported by the provider; the unused hold is refunded. Failed runs refund fully.
- Each run adds a small fixed overhead (half a credit) and rounds up to a whole credit, minimum 1.
- If your balance can’t cover the worst case, the run scales its output cap down to your budget instead of failing.
Worked Examples
Real arithmetic at current catalog rates, for a run of typical chat size:
| Scenario | Model | Tokens in / out | Cost | In credits |
|---|---|---|---|---|
| Chat turn, default model | Gemma 4 26B (Workers AI) | 1,500 / 400 | ~$0.0004 | 4 |
| Mid-size run, budget model | GPT-5 mini | 3,000 / 1,000 | ~$0.0034 | 34 |
| Premium run | Claude Sonnet 5 | 3,000 / 1,000 | ~$0.029 | 289 |
All rows include the per-job overhead and whole-credit rounding. The spread is the point: model choice changes cost by ~70× at identical token counts, which is why apps declare their model on their detail page and why per-run $model overrides exist for apps that let you choose.
The Creator Margin
App creators may add a markup of up to 500% on top of the billed cost. It’s shown transparently on each app’s detail page (“Usage-based + N% creator margin”, with the effective per-token rate), and it’s how a skill maker earns from their work — the platform takes a 10% fee from the creator’s proceeds, never a second cut from you. The creator-side view of this math is in How to Monetize a Claude Code Skill.
Running for Free: Signup Credit, Daily Grants, Free Apps
- $0.30 signup credit for every new verified account.
- $0.20 daily grant on each day you actively use the platform.
- Free grants expire after 7 days; purchased credits and earnings never expire.
- Guests can run guest-enabled apps without an account at all.
- Apps labeled “Completely free” in the directory are verified from source to never charge usage credits, and creators can sponsor usage from their own wallet with daily caps.
At default-model prices, the signup grant alone is roughly 750 chat turns — the free tier is real.
BYOK: Flat 1-Credit Runs on the Publisher’s Own Key
Apps whose publisher attached their own Anthropic or OpenAI API key bill differently: the publisher’s key pays for inference, markup is forced to zero, and you’re charged a flat 1 credit per run as pure platform overhead. It’s the cheapest possible lane and shows up like any other run in your activity.
Holds, Refunds, and Budget-Scaled Runs
Because settlement is capped at the pre-run hold, an app can never charge more than the estimate you saw. Since July 2026, hold/refund pairs display as a single activity row with the exact settled cost, and under-funded runs execute budget-scaled rather than throwing a 402 — both in the changelog.
Frequently Asked Questions
Why is the billed rate above the provider’s list price?
The 1.2× multiplier is the platform’s usage margin — it absorbs payment-processing fees, failed-run refunds, and hosting, so there are no seat fees, listing fees, or surprise charges anywhere else. Creator markup is separate and always displayed.
How do I see what a specific app will charge me?
The app’s detail page shows its pricing lane (free / usage-based / margin %), its model with the effective per-token rate, and any subscription plans. Before any run, the app shows the hold estimate.
What happens if a run fails?
The hold is refunded in full. Settlement only ever charges provider-reported usage on completed runs.
Can I buy credits without a subscription?
Yes — one-off top-ups from $5 to $1,000 on your billing page, always in whole cents. Subscriptions exist per app, not platform-wide; there’s no platform seat fee. Plans and team pricing are on the pricing page.
Conclusion
The whole cost model fits in one sentence: tokens used × billed model rate (+ creator margin), in credits at $1 = 10,000, rounded up, min 1, capped at the hold you saw. Every input to that sentence is public — the model catalog has the rates, app detail pages have the margins, and your activity ledger has the receipts. If you’d rather be on the earning side of it, start with turning your skill into an app.