Pricing and billing
You pay for two things: building and improving a Model, and calling it. Every build is quoted before it starts, and the quote is the most it can cost.
Plans
| Plan | Price | What you get |
|---|---|---|
| Free | $0 | A $15 free credit, once, with no expiry: it pays for drafting, training and calls. 10 drafts a month. No card |
| Pay as you go | Usage, billed monthly, no plan fee | Everything in Free; past the free credit, usage is charged to your card |
| Team | $20 a month | All of it usable on usage, then Pay as you go rates. Shared workspaces, unlimited members, Tier 2 limits from the start |
Every account gets a $15 free credit, once, in its Personal workspace, with no expiry and no card. It pays for drafting, training, comparisons and calls. When it is used, calls, new drafts and new changes stop until an Owner adds a card in Settings, Billing, which moves the workspace to Pay as you go, with no plan fee. Owners get an email at 50, 80 and 100% of the credit. A shared workspace is on Team: until an Owner chooses it, invites, drafts and changes there are refused with team_required. A workspace changes plan in Settings, Billing.
Building and improving
- v1: the draft’s review shows the typical cost and the cap before you start, in your coding agent and in the web app. Most first versions cost a few dollars.
- Your free credit pays for v1. On Free, v1 starts when its cap fits in the free credit left. Drafting is charged as a change’s planning is, from the same credit.
- A run that fails on Facet’s side charges nothing. A change that fails with an error on our side gives back everything it was charged.
- Each later change: quoted when Facet plans the Change. A change to the Instructions alone costs cents; one that needs a new build costs about what v1 did. The quote says exactly.
- The quote is a cap. A change never spends past it. If it would, it stops and asks you to raise the quote.
- Stopping a change charges only what ran.
Calling a Model
Calls are priced per million tokens, input and output, by base model:
| Base model | Input, per 1M tokens | Output, per 1M tokens |
|---|---|---|
| Qwen3.5 0.8B | $0.04 | $0.12 |
| Qwen3.5 4B | $0.08 | $0.25 |
The free credit pays for calls until it is used; then calls are billed on Pay as you go or Team.
Billing
- Usage is billed monthly to your card, in arrears. A month under $0.50 rolls into the next.
- The Usage page shows spend by day, Model and key, and exports to CSV.
- If a payment fails, an Owner pays the invoice from Settings, Billing.
- One monthly spend limit per workspace stops new changes and calls when it’s reached; see Limits.
Next steps
- Limits: rate limits and the spend limit
- Base models: which base to pick