Compare changes
Choose two branches to see what one has that the other does not, then open a pull request for it.
1 commit
21 files+1157−600/21 viewed
| 87 | 87 | assigned the issue. That is why only members of a workspace can put g1t | |
| 88 | 88 | agents to work on its repositories. | |
| 89 | 89 | ||
| 90 | + | ## How prices are set | |
| 91 | + | ||
| 92 | + | g1t passes its own costs through. Everything a workspace uses costs g1t | |
| 93 | + | money first, at Cloudflare or a model provider, and is charged at that | |
| 94 | + | cost plus a set markup. There is no seat price, and nothing is bundled to | |
| 95 | + | hide what it costs. The live prices are on | |
| 96 | + | [g1t.sh/pricing](https://g1t.sh/pricing), straight from the price book | |
| 97 | + | billing charges from. | |
| 98 | + | ||
| 99 | + | Prices keep themselves current as those costs move: | |
| 100 | + | ||
| 101 | + | - **Models.** Each of g1t's hosted runs goes through its Cloudflare AI | |
| 102 | + | Gateway, which prices every request at the provider's current rates. A | |
| 103 | + | run is charged when it finishes at what the sandbox reported; within | |
| 104 | + | about 15 minutes it is **settled** to the gateway's figure, and any | |
| 105 | + | difference appears on the statement as a correction, such as | |
| 106 | + | *Correction to "Work on acme/api#12": AI Gateway priced its 41 model | |
| 107 | + | requests at $0.0312, not $0.0298*. When a provider changes its prices, | |
| 108 | + | runs are charged the new ones from that day. A run whose sandbox stopped | |
| 109 | + | without reporting is charged from the gateway's logs instead of not at | |
| 110 | + | all. | |
| 111 | + | - **Cloudflare.** Every day, g1t checks what Cloudflare billed its account | |
| 112 | + | against what was used: Containers against the seconds containers ran, | |
| 113 | + | Workers for Platforms per request and per CPU millisecond. When a cost | |
| 114 | + | moves by 2% or more, the price book moves with it, since each price is | |
| 115 | + | its cost times its markup, and the change is listed on the pricing page | |
| 116 | + | with the reason. A measurement far from the current cost (more than 4× | |
| 117 | + | either way) is not adopted, only logged, so one odd day cannot reprice | |
| 118 | + | anything. | |
| 119 | + | ||
| 120 | + | | | Markup | | |
| 121 | + | | --- | --- | | |
| 122 | + | | Models | 20% | | |
| 123 | + | | Deploy builds, app requests, CPU and apps | 20% | | |
| 124 | + | | Sandbox time | 138%, which also pays for the orchestration around each sandbox and everyone's free minutes | | |
| 125 | + | ||
| 90 | 126 | ## Sandbox time | |
| 91 | 127 | ||
| 92 | 128 | Every sandbox g1t starts for a workspace runs on Cloudflare Containers, and | |
| 98 | 134 | | | | | |
| 99 | 135 | | --- | --- | | |
| 100 | 136 | | Free each month | 500 minutes (calendar month, UTC) | | |
| 101 | − | | Past that | $0.003 a minute, by the second | | |
| 137 | + | | Past that | $0.003 a minute, by the second, at today's cost | | |
| 102 | 138 | | What it costs g1t | about $0.0013 a minute (Containers, standard-1) | | |
| 103 | 139 | ||
| 140 | + | Both follow what Cloudflare bills; see [How prices are set](#how-prices-are-set). | |
| 141 | + | ||
| 104 | 142 | Deploy builds are not counted here: [Deployments](/guides/deployments/) | |
| 105 | 143 | charges them by the second on its own plan. | |
| 106 | 144 |
| 165 | 165 | </Form> | |
| 166 | 166 | <nav className="flex items-center gap-0.5"> | |
| 167 | 167 | <HeaderLink to="/explore">Explore</HeaderLink> | |
| 168 | + | <HeaderLink to="/pricing">Pricing</HeaderLink> | |
| 168 | 169 | <HeaderLink to="https://docs.g1t.sh/">Docs</HeaderLink> | |
| 169 | 170 | </nav> | |
| 170 | 171 | <div className="ml-auto flex items-center gap-2"> | |
| 262 | 263 | title: "Product", | |
| 263 | 264 | links: [ | |
| 264 | 265 | ["Explore repositories", "/explore"], | |
| 266 | + | ["Pricing", "/pricing"], | |
| 265 | 267 | ["g1t agents", "https://docs.g1t.sh/guides/g1t-agents/"], | |
| 266 | 268 | ["Bring your own agent", "https://docs.g1t.sh/guides/bring-your-own-agent/"], | |
| 267 | 269 | ["Integrations", "https://docs.g1t.sh/guides/integrations/"], |
| 13 | 13 | route("new", "routes/new.tsx"), | |
| 14 | 14 | route("settings", "routes/settings.tsx"), | |
| 15 | 15 | route("explore", "routes/explore.tsx", { id: "explore" }), | |
| 16 | + | route("pricing", "routes/pricing.tsx"), | |
| 16 | 17 | route("search", "routes/explore.tsx", { id: "search" }), | |
| 17 | 18 | route("workspaces/new", "routes/workspace/new.tsx"), | |
| 18 | 19 | // A workspace's own pages sit under `-`, which no repository can be named. |
| 1 | + | import { ArrowUpRight } from "lucide-react"; | |
| 2 | + | ||
| 3 | + | import { DEPLOYMENTS_ALLOWANCE, MICROS_PER_DOLLAR, type Price } from "@g1t/contracts"; | |
| 4 | + | ||
| 5 | + | import type { Route } from "./+types/pricing"; | |
| 6 | + | import { TimeAgo } from "../components/ui"; | |
| 7 | + | import { billing } from "../lib/services.server"; | |
| 8 | + | ||
| 9 | + | export function meta() { | |
| 10 | + | return [ | |
| 11 | + | { title: "Pricing · g1t" }, | |
| 12 | + | { | |
| 13 | + | name: "description", | |
| 14 | + | content: "g1t passes its costs through: what Cloudflare and model providers charge g1t, plus a set markup. No seats.", | |
| 15 | + | }, | |
| 16 | + | ]; | |
| 17 | + | } | |
| 18 | + | ||
| 19 | + | export async function loader() { | |
| 20 | + | const book = await billing.prices().catch(() => null); | |
| 21 | + | return { book }; | |
| 22 | + | } | |
| 23 | + | ||
| 24 | + | /** A price in dollars, with as many digits as it needs to say anything. */ | |
| 25 | + | function money(micros: number): string { | |
| 26 | + | const dollars = micros / MICROS_PER_DOLLAR; | |
| 27 | + | if (dollars >= 1) return `$${dollars.toFixed(2)}`; | |
| 28 | + | if (dollars >= 0.01) return `$${dollars.toFixed(3)}`; | |
| 29 | + | return `$${dollars.toPrecision(2)}`; | |
| 30 | + | } | |
| 31 | + | ||
| 32 | + | /** Per second is easier to read per minute. */ | |
| 33 | + | function perUnit(price: Price, micros: number): string { | |
| 34 | + | return price.unit === "second" ? `${money(micros * 60)} a minute` : `${money(micros)} per ${price.unit}`; | |
| 35 | + | } | |
| 36 | + | ||
| 37 | + | const HOW = [ | |
| 38 | + | { | |
| 39 | + | title: "Our cost, passed through", | |
| 40 | + | body: "Every sandbox second, build, app request and model token costs g1t money at Cloudflare or a model provider. Each is metered and charged at that cost plus a set markup. Use a little, pay a little.", | |
| 41 | + | }, | |
| 42 | + | { | |
| 43 | + | title: "Prices follow costs, by themselves", | |
| 44 | + | body: "Model runs are charged at what Cloudflare's AI Gateway priced each request at, so a provider's price change reaches you the same day. Every day, each Cloudflare cost is checked against what Cloudflare billed g1t; when one moves, its price moves with it, and the change is listed below.", | |
| 45 | + | }, | |
| 46 | + | { | |
| 47 | + | title: "No seats, ever", | |
| 48 | + | body: "Add as many people and agents as you like. A workspace pays for what it uses, and for the features it turns on.", | |
| 49 | + | }, | |
| 50 | + | { | |
| 51 | + | title: "Limits that protect both of us", | |
| 52 | + | body: "Usage not yet paid for can only go so far: $3 for a new workspace, growing with what it pays. At the limit, work stops instead of running up a bill. Owners can set a lower one.", | |
| 53 | + | }, | |
| 54 | + | ]; | |
| 55 | + | ||
| 56 | + | export default function Pricing({ loaderData }: Route.ComponentProps) { | |
| 57 | + | const { book } = loaderData; | |
| 58 | + | const checked = book?.prices.map((p) => p.checkedAt).filter((at): at is string => !!at).sort().at(-1); | |
| 59 | + | return ( | |
| 60 | + | <main className="mx-auto max-w-4xl px-4 py-12"> | |
| 61 | + | <p className="text-sm font-medium text-accent">Pricing</p> | |
| 62 | + | <h1 className="mt-2 text-3xl font-semibold tracking-tight sm:text-4xl">What it costs us, plus a markup</h1> | |
| 63 | + | <p className="mt-3 max-w-2xl text-muted"> | |
| 64 | + | g1t runs on Cloudflare and model providers, and passes those costs through. The numbers on this page are the | |
| 65 | + | live price book g1t charges from. | |
| 66 | + | </p> | |
| 67 | + | <div className="mt-5 rounded-xl border border-accent/30 bg-accent/5 px-4 py-3 text-sm"> | |
| 68 | + | <span className="font-medium">Free while g1t is being built out.</span>{" "} | |
| 69 | + | <span className="text-muted"> | |
| 70 | + | Usage is recorded at these prices but not charged for now. Paid features, such as Deployments, are charged. | |
| 71 | + | </span> | |
| 72 | + | </div> | |
| 73 | + | ||
| 74 | + | <div className="mt-10 grid gap-4 sm:grid-cols-2"> | |
| 75 | + | {HOW.map((item) => ( | |
| 76 | + | <section key={item.title} className="rounded-xl border border-line bg-surface p-5"> | |
| 77 | + | <h2 className="font-medium">{item.title}</h2> | |
| 78 | + | <p className="mt-1.5 text-sm text-muted">{item.body}</p> | |
| 79 | + | </section> | |
| 80 | + | ))} | |
| 81 | + | </div> | |
| 82 | + | ||
| 83 | + | <h2 className="mt-14 text-xl font-semibold tracking-tight">Usage</h2> | |
| 84 | + | <p className="mt-1 text-sm text-muted"> | |
| 85 | + | {checked ? ( | |
| 86 | + | <> | |
| 87 | + | Last checked against Cloudflare's bill <TimeAgo at={checked} />. | |
| 88 | + | </> | |
| 89 | + | ) : ( | |
| 90 | + | "Starting from Cloudflare's published prices; checked against its bill daily." | |
| 91 | + | )} | |
| 92 | + | </p> | |
| 93 | + | <div className="mt-4 overflow-x-auto rounded-xl border border-line"> | |
| 94 | + | <table className="w-full min-w-[36rem] text-left text-sm"> | |
| 95 | + | <thead className="border-b border-line text-xs text-muted"> | |
| 96 | + | <tr> | |
| 97 | + | <th className="px-4 py-2.5 font-medium">What</th> | |
| 98 | + | <th className="px-4 py-2.5 font-medium">Costs g1t</th> | |
| 99 | + | <th className="px-4 py-2.5 font-medium">Markup</th> | |
| 100 | + | <th className="px-4 py-2.5 font-medium">You pay</th> | |
| 101 | + | </tr> | |
| 102 | + | </thead> | |
| 103 | + | <tbody className="divide-y divide-line"> | |
| 104 | + | <tr> | |
| 105 | + | <td className="px-4 py-3"> | |
| 106 | + | <p className="font-medium">Models</p> | |
| 107 | + | <p className="text-xs text-faint">g1t's hosted models, through AI Gateway</p> | |
| 108 | + | </td> | |
| 109 | + | <td className="px-4 py-3 text-muted">What the provider charges, per request</td> | |
| 110 | + | <td className="px-4 py-3 tabular-nums">{book?.modelMarginPercent ?? 20}%</td> | |
| 111 | + | <td className="px-4 py-3 text-muted">Cost + {book?.modelMarginPercent ?? 20}%</td> | |
| 112 | + | </tr> | |
| 113 | + | {(book?.prices ?? []).map((price) => ( | |
| 114 | + | <tr key={price.meter}> | |
| 115 | + | <td className="px-4 py-3"> | |
| 116 | + | <p className="font-medium">{price.title}</p> | |
| 117 | + | <p className="text-xs text-faint"> | |
| 118 | + | {price.source === "cloudflare" ? "Measured from Cloudflare's bill" : "Cloudflare's published price"} | |
| 119 | + | {price.meter === "sandbox_second" && " · 500 minutes free each month"} | |
| 120 | + | </p> | |
| 121 | + | </td> | |
| 122 | + | <td className="px-4 py-3 font-mono text-xs tabular-nums text-muted">{perUnit(price, price.costMicros)}</td> | |
| 123 | + | <td className="px-4 py-3 tabular-nums">{price.markupPercent}%</td> | |
| 124 | + | <td className="px-4 py-3 font-mono text-xs tabular-nums">{perUnit(price, price.priceMicros)}</td> | |
| 125 | + | </tr> | |
| 126 | + | ))} | |
| 127 | + | </tbody> | |
| 128 | + | </table> | |
| 129 | + | </div> | |
| 130 | + | <p className="mt-3 text-xs text-faint"> | |
| 131 | + | Sandbox time carries more markup than the rest: it pays for the orchestration around each sandbox, and the | |
| 132 | + | free minutes everyone gets. | |
| 133 | + | </p> | |
| 134 | + | ||
| 135 | + | <h2 className="mt-14 text-xl font-semibold tracking-tight">Features</h2> | |
| 136 | + | <p className="mt-1 text-sm text-muted">Turned on per workspace with a monthly plan. Never free.</p> | |
| 137 | + | <section className="mt-4 rounded-xl border border-line bg-surface p-5"> | |
| 138 | + | <div className="flex flex-wrap items-baseline justify-between gap-2"> | |
| 139 | + | <h3 className="font-medium">Deployments</h3> | |
| 140 | + | <p> | |
| 141 | + | <span className="text-2xl font-semibold">$5</span> <span className="text-sm text-muted">/ month</span> | |
| 142 | + | </p> | |
| 143 | + | </div> | |
| 144 | + | <p className="mt-1 text-sm text-muted"> | |
| 145 | + | Includes {DEPLOYMENTS_ALLOWANCE.apps} apps up at once, {(DEPLOYMENTS_ALLOWANCE.requests / 1e6).toLocaleString()}{" "} | |
| 146 | + | million requests and {(DEPLOYMENTS_ALLOWANCE.cpuMs / 1e6).toLocaleString()} million CPU milliseconds a month; | |
| 147 | + | builds, and usage past that, at the prices above. | |
| 148 | + | </p> | |
| 149 | + | </section> | |
| 150 | + | ||
| 151 | + | <h2 className="mt-14 text-xl font-semibold tracking-tight">Price changes</h2> | |
| 152 | + | {book && book.changes.length > 0 ? ( | |
| 153 | + | <ul className="mt-4 divide-y divide-line rounded-xl border border-line"> | |
| 154 | + | {book.changes.map((change) => { | |
| 155 | + | const title = book.prices.find((p) => p.meter === change.meter)?.title ?? change.meter; | |
| 156 | + | const up = change.newCostMicros > change.oldCostMicros; | |
| 157 | + | return ( | |
| 158 | + | <li key={`${change.meter}-${change.createdAt}`} className="px-4 py-3 text-sm"> | |
| 159 | + | <p> | |
| 160 | + | <span className="font-medium">{title}</span>{" "} | |
| 161 | + | <span className={up ? "text-warn" : "text-accent"}> | |
| 162 | + | {up ? "up" : "down"} {Math.abs((change.newCostMicros / change.oldCostMicros - 1) * 100).toFixed(1)}% | |
| 163 | + | </span> | |
| 164 | + | </p> | |
| 165 | + | <p className="mt-0.5 text-xs text-faint"> | |
| 166 | + | {change.reason} · <TimeAgo at={change.createdAt} /> | |
| 167 | + | </p> | |
| 168 | + | </li> | |
| 169 | + | ); | |
| 170 | + | })} | |
| 171 | + | </ul> | |
| 172 | + | ) : ( | |
| 173 | + | <p className="mt-2 text-sm text-muted">None yet. When a cost moves, it is listed here with why.</p> | |
| 174 | + | )} | |
| 175 | + | ||
| 176 | + | <a | |
| 177 | + | href="https://docs.g1t.sh/guides/usage-and-billing/" | |
| 178 | + | className="mt-12 inline-flex items-center gap-1.5 text-sm text-accent hover:underline" | |
| 179 | + | > | |
| 180 | + | How usage and billing work | |
| 181 | + | <ArrowUpRight size={14} /> | |
| 182 | + | </a> | |
| 183 | + | </main> | |
| 184 | + | ); | |
| 185 | + | } |
| 181 | 181 | /// The runner, which is TypeScript, sends it as `billedTo`. | |
| 182 | 182 | #[serde(default = "g1t", alias = "billedTo")] | |
| 183 | 183 | pub billed_to: String, | |
| 184 | + | /// The model session's id, when its requests go through g1t's AI | |
| 185 | + | /// Gateway: settling charges the run what the gateway priced them at. | |
| 186 | + | #[serde(default)] | |
| 187 | + | pub session: Option<String>, | |
| 184 | 188 | } | |
| 185 | 189 | ||
| 186 | 190 | #[derive(Clone, Debug, Serialize, Deserialize)] | |
| 401 | 405 | pub workspace: String, | |
| 402 | 406 | } | |
| 403 | 407 | ||
| 408 | + | /// `note_pending`: usage this month that will be charged later, such as | |
| 409 | + | /// app traffic past a plan, so the workspace's limit counts it now. Each | |
| 410 | + | /// report replaces the last for that workspace, source and month. Called | |
| 411 | + | /// by the service that meters it. Returns `bool`. | |
| 412 | + | #[derive(Debug, Serialize, Deserialize)] | |
| 413 | + | #[serde(rename_all = "camelCase")] | |
| 414 | + | pub struct NotePendingArgs { | |
| 415 | + | pub workspace: String, | |
| 416 | + | /// `deployments`. | |
| 417 | + | pub source: String, | |
| 418 | + | /// What it cost g1t so far this month, before the margin. | |
| 419 | + | pub cost_micros: i64, | |
| 420 | + | } | |
| 421 | + | ||
| 404 | 422 | /// `set_spend_limit`: the owner's own monthly ceiling, under g1t's; None | |
| 405 | 423 | /// removes it. Owners only. Returns `Outcome<Limit>`. | |
| 406 | 424 | #[derive(Debug, Serialize, Deserialize)] | |
| 411 | 429 | pub spend_limit_micros: Option<i64>, | |
| 412 | 430 | } | |
| 413 | 431 | ||
| 432 | + | /// One metered unit: what it costs g1t, and what it is sold at. The price | |
| 433 | + | /// is always `cost × (100 + markup) / 100`, so it follows the cost. | |
| 434 | + | #[derive(Clone, Debug, Serialize, Deserialize)] | |
| 435 | + | #[serde(rename_all = "camelCase")] | |
| 436 | + | pub struct Price { | |
| 437 | + | /// `sandbox_second`, `build_second`, `app_requests`, `app_cpu`, `app_month`. | |
| 438 | + | pub meter: String, | |
| 439 | + | pub title: String, | |
| 440 | + | pub unit: String, | |
| 441 | + | /// Millionths of a dollar per unit; may have a fraction. | |
| 442 | + | pub cost_micros: f64, | |
| 443 | + | pub markup_percent: u32, | |
| 444 | + | pub price_micros: f64, | |
| 445 | + | /// `list`: Cloudflare's published price. `cloudflare`: what Cloudflare | |
| 446 | + | /// actually billed g1t, measured. | |
| 447 | + | pub source: String, | |
| 448 | + | /// When it was last checked against Cloudflare's bill. | |
| 449 | + | pub checked_at: Option<String>, | |
| 450 | + | pub updated_at: String, | |
| 451 | + | } | |
| 452 | + | ||
| 453 | + | impl Price { | |
| 454 | + | pub fn price_for(cost_micros: f64, markup_percent: u32) -> f64 { | |
| 455 | + | cost_micros * f64::from(100 + markup_percent) / 100.0 | |
| 456 | + | } | |
| 457 | + | } | |
| 458 | + | ||
| 459 | + | /// A cost that moved. | |
| 460 | + | #[derive(Clone, Debug, Serialize, Deserialize)] | |
| 461 | + | #[serde(rename_all = "camelCase")] | |
| 462 | + | pub struct PriceChange { | |
| 463 | + | pub meter: String, | |
| 464 | + | pub old_cost_micros: f64, | |
| 465 | + | pub new_cost_micros: f64, | |
| 466 | + | pub markup_percent: u32, | |
| 467 | + | pub reason: String, | |
| 468 | + | pub created_at: String, | |
| 469 | + | } | |
| 470 | + | ||
| 471 | + | /// `prices`: every metered price and the recent changes. Public. Returns | |
| 472 | + | /// `PriceBook`. | |
| 473 | + | #[derive(Clone, Debug, Serialize, Deserialize)] | |
| 474 | + | #[serde(rename_all = "camelCase")] | |
| 475 | + | pub struct PriceBook { | |
| 476 | + | pub prices: Vec<Price>, | |
| 477 | + | pub changes: Vec<PriceChange>, | |
| 478 | + | /// The margin on model usage, which is charged at what AI Gateway | |
| 479 | + | /// priced each request at. | |
| 480 | + | pub model_margin_percent: u32, | |
| 481 | + | } | |
| 482 | + | ||
| 414 | 483 | /// What a feature's plan costs and includes. | |
| 415 | 484 | #[derive(Clone, Debug, Serialize, Deserialize)] | |
| 416 | 485 | #[serde(rename_all = "camelCase")] |
| 353 | 353 | pub provider_name: Option<String>, | |
| 354 | 354 | /// The model to use instead of g1t's choice, if the connection names one. | |
| 355 | 355 | pub model: Option<String>, | |
| 356 | + | /// Names the run in AI Gateway's logs (`metadata.session`), so billing | |
| 357 | + | /// can charge each run what the gateway priced its requests at. Not a | |
| 358 | + | /// secret: it cannot be turned back into the token. | |
| 359 | + | #[serde(default)] | |
| 360 | + | pub id: String, | |
| 356 | 361 | } | |
| 357 | 362 | ||
| 358 | 363 | /// What the model proxy needs to forward one run's requests. | |
| 376 | 381 | pub repo: String, | |
| 377 | 382 | pub number: u32, | |
| 378 | 383 | pub task: String, | |
| 384 | + | /// The session's id; see `ModelSession::id`. | |
| 385 | + | #[serde(default)] | |
| 386 | + | pub session: String, | |
| 379 | 387 | /// For `endpoint`: where to send requests. | |
| 380 | 388 | pub base_url: Option<String>, | |
| 381 | 389 | /// For `anthropic` and `endpoint`: the workspace's key. |
| 93 | 93 | message: string | null; | |
| 94 | 94 | }; | |
| 95 | 95 | ||
| 96 | + | /** One metered unit: what it costs g1t and what it is sold at; the price follows the cost. */ | |
| 97 | + | export type Price = { | |
| 98 | + | meter: "sandbox_second" | "build_second" | "app_requests" | "app_cpu" | "app_month" | string; | |
| 99 | + | title: string; | |
| 100 | + | unit: string; | |
| 101 | + | costMicros: number; | |
| 102 | + | markupPercent: number; | |
| 103 | + | priceMicros: number; | |
| 104 | + | /** `list`: Cloudflare's published price. `cloudflare`: measured from Cloudflare's bill. */ | |
| 105 | + | source: "list" | "cloudflare" | string; | |
| 106 | + | checkedAt: string | null; | |
| 107 | + | updatedAt: string; | |
| 108 | + | }; | |
| 109 | + | ||
| 110 | + | export type PriceChange = { | |
| 111 | + | meter: string; | |
| 112 | + | oldCostMicros: number; | |
| 113 | + | newCostMicros: number; | |
| 114 | + | markupPercent: number; | |
| 115 | + | reason: string; | |
| 116 | + | createdAt: string; | |
| 117 | + | }; | |
| 118 | + | ||
| 119 | + | export type PriceBook = { prices: Price[]; changes: PriceChange[]; modelMarginPercent: number }; | |
| 120 | + | ||
| 96 | 121 | export type Trial = { | |
| 97 | 122 | open: boolean; | |
| 98 | 123 | usedMicros: number; | |
| 205 | 230 | repo?: string | null; | |
| 206 | 231 | reference: string; | |
| 207 | 232 | }): Promise<Result<boolean>>; | |
| 233 | + | /** | |
| 234 | + | * Usage this month to be charged later (app traffic past a plan), so the | |
| 235 | + | * workspace's limit counts it now. Replaces the last report. | |
| 236 | + | */ | |
| 237 | + | notePending(workspace: string, source: "deployments", costMicros: number): Promise<boolean>; | |
| 238 | + | /** Every metered price and the recent changes. Public. */ | |
| 239 | + | prices(): Promise<PriceBook>; | |
| 208 | 240 | /** A workspace's limit, for its members. */ | |
| 209 | 241 | limit(workspace: string, viewer: Viewer): Promise<Result<Limit>>; | |
| 210 | 242 | /** The same, for the services that enforce it. */ | |
| 231 | 263 | model: string; | |
| 232 | 264 | /** `workspace` when the run uses the workspace's own model provider. */ | |
| 233 | 265 | billedTo?: "g1t" | "workspace"; | |
| 266 | + | /** The model session's id, so the run can be settled at AI Gateway's price. */ | |
| 267 | + | session?: string | null; | |
| 234 | 268 | }): Promise<Result<RunTicket | null>>; | |
| 235 | 269 | } | |
| 236 | 270 |
| 202 | 202 | recordSandbox: (usage) => call("record_sandbox", usage), | |
| 203 | 203 | limit: (workspace, viewer) => call("limit", { workspace, viewer }), | |
| 204 | 204 | checkLimit: (workspace) => call("check_limit", { workspace }), | |
| 205 | + | prices: () => call("prices", {}), | |
| 206 | + | notePending: (workspace, source, costMicros) => call("note_pending", { workspace, source, costMicros }), | |
| 205 | 207 | setSpendLimit: (actor, workspace, spendLimitMicros) => | |
| 206 | 208 | call("set_spend_limit", { actor, workspace, spendLimitMicros }), | |
| 207 | 209 | }; |
| 122 | 122 | billedTo: "g1t" | "workspace"; | |
| 123 | 123 | providerName: string | null; | |
| 124 | 124 | model: string | null; | |
| 125 | + | /** Names the run in AI Gateway's logs (`metadata.session`), for billing. */ | |
| 126 | + | id: string; | |
| 125 | 127 | }; | |
| 126 | 128 | ||
| 127 | 129 | export type ModelUpstream = { | |
| 138 | 140 | repo: string; | |
| 139 | 141 | number: number; | |
| 140 | 142 | task: string; | |
| 143 | + | /** The session's id; see `ModelSession.id`. */ | |
| 144 | + | session: string; | |
| 141 | 145 | baseUrl: string | null; | |
| 142 | 146 | apiKey: string | null; | |
| 143 | 147 | authHeader: string | null; |
| 6 | 6 | /** Routes and reserved words that may not be registered as usernames. */ | |
| 7 | 7 | const RESERVED = new Set([ | |
| 8 | 8 | "api", "mcp", "login", "logout", "register", "new", "settings", "search", | |
| 9 | − | "admin", "auth", "pulls", "issues", "verify", "forgot", "reset", "device", "workspaces", "u", "oauth", "assets", "docs", "explore", "g1t", "about", | |
| 9 | + | "admin", "auth", "pulls", "issues", "verify", "forgot", "reset", "device", "workspaces", "u", "oauth", "assets", "docs", "explore", "g1t", "about", "pricing", | |
| 10 | 10 | ]); | |
| 11 | 11 | ||
| 12 | 12 | export function isValidNamespace(value: string): boolean { |
| 1 | + | -- Prices that keep themselves current. See src/keeper.rs. | |
| 2 | + | ||
| 3 | + | -- Which AI Gateway session a run's model requests went through, and what | |
| 4 | + | -- the gateway priced them at once settled. A run is first charged what | |
| 5 | + | -- the sandbox reported; settling corrects it to the gateway's figure. | |
| 6 | + | ALTER TABLE runs ADD COLUMN session_id TEXT; | |
| 7 | + | ALTER TABLE runs ADD COLUMN settled_at TEXT; | |
| 8 | + | ALTER TABLE runs ADD COLUMN gateway_cost_micros INTEGER; | |
| 9 | + | ||
| 10 | + | -- What each metered unit costs g1t, and the markup it is sold at. Price | |
| 11 | + | -- is always cost × (100 + markup) / 100, so when a cost moves, the price | |
| 12 | + | -- moves with it. | |
| 13 | + | CREATE TABLE prices ( | |
| 14 | + | meter TEXT PRIMARY KEY, | |
| 15 | + | title TEXT NOT NULL, | |
| 16 | + | -- second, million requests, million CPU ms, app-month. | |
| 17 | + | unit TEXT NOT NULL, | |
| 18 | + | -- Millionths of a dollar per unit; fractions allowed. | |
| 19 | + | cost_micros REAL NOT NULL, | |
| 20 | + | markup_percent INTEGER NOT NULL, | |
| 21 | + | -- list (Cloudflare's published price) or cloudflare (what Cloudflare | |
| 22 | + | -- actually billed g1t, measured). | |
| 23 | + | source TEXT NOT NULL, | |
| 24 | + | checked_at TEXT, | |
| 25 | + | updated_at TEXT NOT NULL | |
| 26 | + | ); | |
| 27 | + | ||
| 28 | + | INSERT INTO prices (meter, title, unit, cost_micros, markup_percent, source, updated_at) VALUES | |
| 29 | + | ('sandbox_second', 'Sandbox time', 'second', 21, 138, 'list', '2026-10-04T00:00:00Z'), | |
| 30 | + | ('build_second', 'Deploy builds', 'second', 21, 20, 'list', '2026-10-04T00:00:00Z'), | |
| 31 | + | ('app_requests', 'App requests', 'million requests', 300000, 20, 'list', '2026-10-04T00:00:00Z'), | |
| 32 | + | ('app_cpu', 'App CPU time', 'million CPU ms', 20000, 20, 'list', '2026-10-04T00:00:00Z'), | |
| 33 | + | ('app_month', 'Apps up past the plan', 'app-month', 20000, 20, 'list', '2026-10-04T00:00:00Z'); | |
| 34 | + | ||
| 35 | + | -- Every time a cost moved, and why: the public record of price changes. | |
| 36 | + | CREATE TABLE price_changes ( | |
| 37 | + | id TEXT PRIMARY KEY, | |
| 38 | + | meter TEXT NOT NULL, | |
| 39 | + | old_cost_micros REAL NOT NULL, | |
| 40 | + | new_cost_micros REAL NOT NULL, | |
| 41 | + | markup_percent INTEGER NOT NULL, | |
| 42 | + | reason TEXT NOT NULL, | |
| 43 | + | created_at TEXT NOT NULL | |
| 44 | + | ); | |
| 45 | + | CREATE INDEX price_changes_by_time ON price_changes (created_at); | |
| 46 | + | ||
| 47 | + | -- What Cloudflare billed g1t's account, as its usage API reports it, kept | |
| 48 | + | -- as given so the measured costs can be checked. | |
| 49 | + | CREATE TABLE cloudflare_usage ( | |
| 50 | + | period_start TEXT NOT NULL, | |
| 51 | + | period_end TEXT NOT NULL, | |
| 52 | + | service TEXT NOT NULL, | |
| 53 | + | unit TEXT NOT NULL, | |
| 54 | + | quantity REAL NOT NULL, | |
| 55 | + | cost_usd REAL NOT NULL, | |
| 56 | + | fetched_at TEXT NOT NULL, | |
| 57 | + | PRIMARY KEY (period_start, service, unit) | |
| 58 | + | ); |
| 1 | + | -- Usage this month that is not on the ledger yet, such as app traffic | |
| 2 | + | -- past the Deployments plan, which is charged when the month closes. It | |
| 3 | + | -- counts toward the workspace's limit as it happens. Replaced on each | |
| 4 | + | -- report; see `note_pending` in src/limits.rs. | |
| 5 | + | CREATE TABLE pending_usage ( | |
| 6 | + | workspace TEXT NOT NULL, | |
| 7 | + | -- deployments. | |
| 8 | + | source TEXT NOT NULL, | |
| 9 | + | -- YYYY-MM. | |
| 10 | + | month TEXT NOT NULL, | |
| 11 | + | -- What it will be charged, in millionths of a dollar. | |
| 12 | + | charge_micros INTEGER NOT NULL, | |
| 13 | + | updated_at TEXT NOT NULL, | |
| 14 | + | PRIMARY KEY (workspace, source, month) | |
| 15 | + | ); |
| 1 | + | //! Keeps every price current with what g1t actually pays. | |
| 2 | + | //! | |
| 3 | + | //! g1t passes its own costs through, so a price is only right while the | |
| 4 | + | //! cost under it is. Two jobs keep them right, on the billing service's | |
| 5 | + | //! cron: | |
| 6 | + | //! | |
| 7 | + | //! - **Settling runs** (every 15 minutes). A model run is charged when it | |
| 8 | + | //! finishes at what the sandbox reported. Each of g1t's hosted runs goes | |
| 9 | + | //! through its AI Gateway, which prices every request at the provider's | |
| 10 | + | //! current rates and logs it with the run's session. Settling sums those | |
| 11 | + | //! logs and corrects the charge to the gateway's figure, with a | |
| 12 | + | //! correction on the statement. A run whose sandbox died before | |
| 13 | + | //! reporting is charged here instead of never. | |
| 14 | + | //! - **Checking costs** (daily). What Cloudflare billed g1t's account, from | |
| 15 | + | //! its usage API, is measured against how much was used: Containers | |
| 16 | + | //! against the seconds containers ran, Workers for Platforms per request | |
| 17 | + | //! and per CPU millisecond. When a measured cost moves, the price book | |
| 18 | + | //! moves with it, since each price is its cost plus a set markup, and | |
| 19 | + | //! the change is recorded where anyone can see it. A measurement far off | |
| 20 | + | //! the current cost is not adopted, only logged, so one odd day of data | |
| 21 | + | //! cannot reprice everything. | |
| 22 | + | ||
| 23 | + | use g1t_contracts::billing::{EntryKind, MICROS_PER_DOLLAR, Price, PriceBook, PriceChange}; | |
| 24 | + | use g1t_contracts::new_id; | |
| 25 | + | use g1t_contracts::time::rfc3339; | |
| 26 | + | use g1t_kit::now_ms; | |
| 27 | + | use serde::Deserialize; | |
| 28 | + | use serde_json::{Value, json}; | |
| 29 | + | use worker::{Env, Fetch, Headers, Method, Request, RequestInit, Result}; | |
| 30 | + | ||
| 31 | + | use crate::{Billing, RunRow, charge_micros}; | |
| 32 | + | ||
| 33 | + | /// The cron that also checks costs against Cloudflare's bill. | |
| 34 | + | pub(crate) const DAILY: &str = "17 4 * * *"; | |
| 35 | + | ||
| 36 | + | /// A run is settled once its logs have had time to land. | |
| 37 | + | const SETTLE_AFTER_MS: u64 = 5 * 60 * 1000; | |
| 38 | + | /// A run with no gateway logs after this is left as reported. | |
| 39 | + | const GIVE_UP_AFTER_MS: u64 = 3 * 60 * 60 * 1000; | |
| 40 | + | /// A run never finished after this died without reporting. | |
| 41 | + | const ABANDONED_AFTER_MS: u64 = 3 * 60 * 60 * 1000; | |
| 42 | + | /// Too little spend to measure a cost from. | |
| 43 | + | const MIN_MEASURED_USD: f64 = 5.0; | |
| 44 | + | /// Smaller moves are noise. | |
| 45 | + | const MIN_CHANGE: f64 = 0.02; | |
| 46 | + | /// A measurement outside this factor of the current cost is suspect. | |
| 47 | + | const MAX_FACTOR: f64 = 4.0; | |
| 48 | + | ||
| 49 | + | /// Where the keeper reads what g1t pays. | |
| 50 | + | pub(crate) struct Keeper { | |
| 51 | + | /// `CLOUDFLARE_USAGE_TOKEN`: Billing, Account Analytics and AI Gateway, | |
| 52 | + | /// read only. | |
| 53 | + | token: Option<String>, | |
| 54 | + | account: String, | |
| 55 | + | gateway: String, | |
| 56 | + | } | |
| 57 | + | ||
| 58 | + | impl Keeper { | |
| 59 | + | pub(crate) fn from_env(env: &Env) -> Self { | |
| 60 | + | let var = |name: &str| env.var(name).map(|v| v.to_string()).unwrap_or_default(); | |
| 61 | + | Keeper { | |
| 62 | + | token: env.secret("CLOUDFLARE_USAGE_TOKEN").ok().map(|v| v.to_string()).filter(|v| !v.is_empty()), | |
| 63 | + | account: var("CLOUDFLARE_ACCOUNT_ID"), | |
| 64 | + | gateway: var("AI_GATEWAY_ID"), | |
| 65 | + | } | |
| 66 | + | } | |
| 67 | + | ||
| 68 | + | async fn send(&self, method: Method, url: &str, body: Option<Value>) -> Result<Value> { | |
| 69 | + | let Some(token) = &self.token else { | |
| 70 | + | return Err(worker::Error::RustError("no CLOUDFLARE_USAGE_TOKEN".into())); | |
| 71 | + | }; | |
| 72 | + | let headers = Headers::new(); | |
| 73 | + | headers.set("authorization", &format!("Bearer {token}"))?; | |
| 74 | + | headers.set("content-type", "application/json")?; | |
| 75 | + | let mut init = RequestInit::new(); | |
| 76 | + | init.with_method(method).with_headers(headers); | |
| 77 | + | if let Some(body) = body { | |
| 78 | + | init.with_body(Some(body.to_string().into())); | |
| 79 | + | } | |
| 80 | + | let mut response = Fetch::Request(Request::new_with_init(url, &init)?).send().await?; | |
| 81 | + | let status = response.status_code(); | |
| 82 | + | let value: Value = response.json().await.unwrap_or(Value::Null); | |
| 83 | + | if status != 200 { | |
| 84 | + | return Err(worker::Error::RustError(format!("Cloudflare answered {status}: {value}"))); | |
| 85 | + | } | |
| 86 | + | Ok(value) | |
| 87 | + | } | |
| 88 | + | ||
| 89 | + | fn api(&self, path: &str) -> String { | |
| 90 | + | format!("https://api.cloudflare.com/client/v4/accounts/{}{path}", self.account) | |
| 91 | + | } | |
| 92 | + | ||
| 93 | + | /// What AI Gateway priced a session's requests at, in dollars, and how | |
| 94 | + | /// many there were. | |
| 95 | + | async fn session_cost(&self, session: &str) -> Result<(f64, u32)> { | |
| 96 | + | let mut cost = 0.0; | |
| 97 | + | let mut count = 0; | |
| 98 | + | for page in 1..=40 { | |
| 99 | + | let url = self.api(&format!( | |
| 100 | + | "/ai-gateway/gateways/{}/logs?per_page=50&page={page}\ | |
| 101 | + | &filters[0][key]=metadata.value&filters[0][operator]=eq&filters[0][value][0]={session}", | |
| 102 | + | self.gateway | |
| 103 | + | )); | |
| 104 | + | let body = self.send(Method::Get, &url, None).await?; | |
| 105 | + | let logs = body["result"].as_array().cloned().unwrap_or_default(); | |
| 106 | + | for log in &logs { | |
| 107 | + | cost += log["cost"].as_f64().unwrap_or(0.0); | |
| 108 | + | count += 1; | |
| 109 | + | } | |
| 110 | + | if logs.len() < 50 { | |
| 111 | + | break; | |
| 112 | + | } | |
| 113 | + | } | |
| 114 | + | Ok((cost, count)) | |
| 115 | + | } | |
| 116 | + | ||
| 117 | + | /// The account's billable usage this month, as Cloudflare reports it. | |
| 118 | + | async fn billable_usage(&self, from: &str, to: &str) -> Result<Vec<UsageRow>> { | |
| 119 | + | let body = self | |
| 120 | + | .send(Method::Get, &self.api(&format!("/billing/usage/paygo?from={from}&to={to}")), None) | |
| 121 | + | .await?; | |
| 122 | + | let rows = body["result"].as_array().cloned().unwrap_or_default(); | |
| 123 | + | Ok(rows.iter().filter_map(UsageRow::from_value).collect()) | |
| 124 | + | } | |
| 125 | + | ||
| 126 | + | /// Seconds g1t's containers ran since `since` (RFC 3339), across the | |
| 127 | + | /// account. | |
| 128 | + | async fn container_seconds(&self, since: &str, until: &str) -> Result<f64> { | |
| 129 | + | let query = "query ($account: String!, $since: Time!, $until: Time!) { | |
| 130 | + | viewer { accounts(filter: { accountTag: $account }) { | |
| 131 | + | containersMetricsAdaptiveGroups(limit: 10000, filter: { datetime_geq: $since, datetime_leq: $until }) { | |
| 132 | + | sum { containerUptime } | |
| 133 | + | } | |
| 134 | + | } } | |
| 135 | + | }"; | |
| 136 | + | let body = self | |
| 137 | + | .send( | |
| 138 | + | Method::Post, | |
| 139 | + | "https://api.cloudflare.com/client/v4/graphql", | |
| 140 | + | Some(json!({ "query": query, "variables": { "account": self.account, "since": since, "until": until } })), | |
| 141 | + | ) | |
| 142 | + | .await?; | |
| 143 | + | let groups = body["data"]["viewer"]["accounts"][0]["containersMetricsAdaptiveGroups"] | |
| 144 | + | .as_array() | |
| 145 | + | .cloned() | |
| 146 | + | .unwrap_or_default(); | |
| 147 | + | Ok(groups.iter().map(|g| g["sum"]["containerUptime"].as_f64().unwrap_or(0.0)).sum()) | |
| 148 | + | } | |
| 149 | + | } | |
| 150 | + | ||
| 151 | + | /// One line of Cloudflare's billable usage. | |
| 152 | + | #[derive(Debug, Clone)] | |
| 153 | + | pub(crate) struct UsageRow { | |
| 154 | + | period_start: String, | |
| 155 | + | period_end: String, | |
| 156 | + | service: String, | |
| 157 | + | unit: String, | |
| 158 | + | quantity: f64, | |
| 159 | + | cost: f64, | |
| 160 | + | } | |
| 161 | + | ||
| 162 | + | impl UsageRow { | |
| 163 | + | /// Read leniently: the API is new, and its field names are FOCUS's. | |
| 164 | + | fn from_value(row: &Value) -> Option<Self> { | |
| 165 | + | let text = |keys: &[&str]| keys.iter().find_map(|k| row[*k].as_str()).unwrap_or_default().to_owned(); | |
| 166 | + | let number = |keys: &[&str]| { | |
| 167 | + | keys.iter() | |
| 168 | + | .find_map(|k| row[*k].as_f64().or_else(|| row[*k].as_str().and_then(|s| s.parse().ok()))) | |
| 169 | + | .unwrap_or(0.0) | |
| 170 | + | }; | |
| 171 | + | let service = text(&["ServiceName", "service_name", "service"]); | |
| 172 | + | if service.is_empty() { | |
| 173 | + | return None; | |
| 174 | + | } | |
| 175 | + | let family = text(&["ServiceFamilyName", "service_family_name"]); | |
| 176 | + | Some(UsageRow { | |
| 177 | + | period_start: text(&["ChargePeriodStart", "charge_period_start"]), | |
| 178 | + | period_end: text(&["ChargePeriodEnd", "charge_period_end"]), | |
| 179 | + | service: if family.is_empty() { service } else { format!("{family} / {service}") }, | |
| 180 | + | unit: text(&["ConsumedUnit", "PricingUnit", "consumed_unit"]), | |
| 181 | + | quantity: number(&["PricingQuantity", "ConsumedQuantity", "pricing_quantity"]), | |
| 182 | + | cost: number(&["ContractedCost", "BilledCost", "contracted_cost"]), | |
| 183 | + | }) | |
| 184 | + | } | |
| 185 | + | } | |
| 186 | + | ||
| 187 | + | /// What a cost should become from a measurement, or why not. | |
| 188 | + | pub(crate) fn adopt(current: f64, measured: f64) -> std::result::Result<Option<f64>, String> { | |
| 189 | + | if !measured.is_finite() || measured <= 0.0 { | |
| 190 | + | return Err("nothing to measure".into()); | |
| 191 | + | } | |
| 192 | + | let ratio = measured / current; | |
| 193 | + | if !(1.0 / MAX_FACTOR..=MAX_FACTOR).contains(&ratio) { | |
| 194 | + | return Err(format!("measured {measured:.4} against {current:.4}, too far off to adopt")); | |
| 195 | + | } | |
| 196 | + | Ok(((ratio - 1.0).abs() >= MIN_CHANGE).then_some(measured)) | |
| 197 | + | } | |
| 198 | + | ||
| 199 | + | #[derive(Deserialize)] | |
| 200 | + | struct PriceRow { | |
| 201 | + | meter: String, | |
| 202 | + | title: String, | |
| 203 | + | unit: String, | |
| 204 | + | cost_micros: f64, | |
| 205 | + | markup_percent: u32, | |
| 206 | + | source: String, | |
| 207 | + | checked_at: Option<String>, | |
| 208 | + | updated_at: String, | |
| 209 | + | } | |
| 210 | + | ||
| 211 | + | #[derive(Deserialize)] | |
| 212 | + | struct ChangeRow { | |
| 213 | + | meter: String, | |
| 214 | + | old_cost_micros: f64, | |
| 215 | + | new_cost_micros: f64, | |
| 216 | + | markup_percent: u32, | |
| 217 | + | reason: String, | |
| 218 | + | created_at: String, | |
| 219 | + | } | |
| 220 | + | ||
| 221 | + | #[derive(Deserialize)] | |
| 222 | + | struct Unsettled { | |
| 223 | + | id: String, | |
| 224 | + | workspace: String, | |
| 225 | + | repo: String, | |
| 226 | + | number: u32, | |
| 227 | + | task: String, | |
| 228 | + | model: String, | |
| 229 | + | token_hash: String, | |
| 230 | + | billed_to: Option<String>, | |
| 231 | + | session_id: String, | |
| 232 | + | created_at: String, | |
| 233 | + | finished_at: Option<String>, | |
| 234 | + | } | |
| 235 | + | ||
| 236 | + | #[derive(Deserialize)] | |
| 237 | + | struct Charged { | |
| 238 | + | cost_micros: Option<i64>, | |
| 239 | + | description: String, | |
| 240 | + | } | |
| 241 | + | ||
| 242 | + | fn ms(timestamp: &str) -> u64 { | |
| 243 | + | // RFC 3339 in UTC, as g1t writes them. | |
| 244 | + | worker::js_sys::Date::parse(timestamp) as u64 | |
| 245 | + | } | |
| 246 | + | ||
| 247 | + | impl Billing { | |
| 248 | + | pub(crate) async fn prices(&self) -> Result<PriceBook> { | |
| 249 | + | let prices = self | |
| 250 | + | .db | |
| 251 | + | .prepare("SELECT * FROM prices ORDER BY rowid") | |
| 252 | + | .all() | |
| 253 | + | .await? | |
| 254 | + | .results::<PriceRow>()?; | |
| 255 | + | let changes = self | |
| 256 | + | .db | |
| 257 | + | .prepare("SELECT * FROM price_changes ORDER BY created_at DESC LIMIT 20") | |
| 258 | + | .all() | |
| 259 | + | .await? | |
| 260 | + | .results::<ChangeRow>()?; | |
| 261 | + | Ok(PriceBook { | |
| 262 | + | prices: prices | |
| 263 | + | .into_iter() | |
| 264 | + | .map(|row| Price { | |
| 265 | + | price_micros: Price::price_for(row.cost_micros, row.markup_percent), | |
| 266 | + | meter: row.meter, | |
| 267 | + | title: row.title, | |
| 268 | + | unit: row.unit, | |
| 269 | + | cost_micros: row.cost_micros, | |
| 270 | + | markup_percent: row.markup_percent, | |
| 271 | + | source: row.source, | |
| 272 | + | checked_at: row.checked_at, | |
| 273 | + | updated_at: row.updated_at, | |
| 274 | + | }) | |
| 275 | + | .collect(), | |
| 276 | + | changes: changes | |
| 277 | + | .into_iter() | |
| 278 | + | .map(|row| PriceChange { | |
| 279 | + | meter: row.meter, | |
| 280 | + | old_cost_micros: row.old_cost_micros, | |
| 281 | + | new_cost_micros: row.new_cost_micros, | |
| 282 | + | markup_percent: row.markup_percent, | |
| 283 | + | reason: row.reason, | |
| 284 | + | created_at: row.created_at, | |
| 285 | + | }) | |
| 286 | + | .collect(), | |
| 287 | + | model_margin_percent: self.margin_percent, | |
| 288 | + | }) | |
| 289 | + | } | |
| 290 | + | ||
| 291 | + | /// A meter's cost and price per unit, from the book. | |
| 292 | + | pub(crate) async fn price(&self, meter: &str) -> Result<Option<(f64, f64)>> { | |
| 293 | + | #[derive(Deserialize)] | |
| 294 | + | struct Row { | |
| 295 | + | cost_micros: f64, | |
| 296 | + | markup_percent: u32, | |
| 297 | + | } | |
| 298 | + | Ok(self | |
| 299 | + | .db | |
| 300 | + | .prepare("SELECT cost_micros, markup_percent FROM prices WHERE meter = ?") | |
| 301 | + | .bind(&[meter.into()])? | |
| 302 | + | .first::<Row>(None) | |
| 303 | + | .await? | |
| 304 | + | .map(|row| (row.cost_micros, Price::price_for(row.cost_micros, row.markup_percent)))) | |
| 305 | + | } | |
| 306 | + | ||
| 307 | + | /// Corrects finished runs to what AI Gateway priced them at, and | |
| 308 | + | /// charges runs whose sandbox died before reporting. | |
| 309 | + | pub(crate) async fn settle_runs(&self, keeper: &Keeper) -> Result<()> { | |
| 310 | + | if keeper.token.is_none() || keeper.gateway.is_empty() { | |
| 311 | + | return Ok(()); | |
| 312 | + | } | |
| 313 | + | let now = now_ms(); | |
| 314 | + | let runs = self | |
| 315 | + | .db | |
| 316 | + | .prepare( | |
| 317 | + | "SELECT id, workspace, repo, number, task, model, token_hash, billed_to, session_id, created_at, finished_at | |
| 318 | + | FROM runs | |
| 319 | + | WHERE session_id IS NOT NULL AND settled_at IS NULL | |
| 320 | + | AND ((finished_at IS NOT NULL AND finished_at < ?1) OR created_at < ?2) | |
| 321 | + | ORDER BY created_at LIMIT 10", | |
| 322 | + | ) | |
| 323 | + | .bind(&[rfc3339(now - SETTLE_AFTER_MS).into(), rfc3339(now - ABANDONED_AFTER_MS).into()])? | |
| 324 | + | .all() | |
| 325 | + | .await? | |
| 326 | + | .results::<Unsettled>()?; | |
| 327 | + | for run in runs { | |
| 328 | + | let (cost_usd, requests) = match keeper.session_cost(&run.session_id).await { | |
| 329 | + | Ok(found) => found, | |
| 330 | + | Err(error) => { | |
| 331 | + | worker::console_error!("could not read gateway logs for {}: {error}", run.id); | |
| 332 | + | continue; | |
| 333 | + | } | |
| 334 | + | }; | |
| 335 | + | let since = ms(run.finished_at.as_deref().unwrap_or(&run.created_at)); | |
| 336 | + | if requests == 0 && now.saturating_sub(since) < GIVE_UP_AFTER_MS { | |
| 337 | + | continue; | |
| 338 | + | } | |
| 339 | + | self.settle(&run, cost_usd, requests).await?; | |
| 340 | + | } | |
| 341 | + | Ok(()) | |
| 342 | + | } | |
| 343 | + | ||
| 344 | + | async fn settle(&self, run: &Unsettled, cost_usd: f64, requests: u32) -> Result<()> { | |
| 345 | + | let row = RunRow { | |
| 346 | + | workspace: run.workspace.clone(), | |
| 347 | + | repo: run.repo.clone(), | |
| 348 | + | number: run.number, | |
| 349 | + | task: run.task.clone(), | |
| 350 | + | model: run.model.clone(), | |
| 351 | + | token_hash: run.token_hash.clone(), | |
| 352 | + | billed_to: run.billed_to.clone(), | |
| 353 | + | }; | |
| 354 | + | let gateway_micros = charge_micros(cost_usd, 0); | |
| 355 | + | let charged = self | |
| 356 | + | .db | |
| 357 | + | .prepare("SELECT cost_micros, description FROM ledger WHERE reference = ?") | |
| 358 | + | .bind(&[run.id.as_str().into()])? | |
| 359 | + | .first::<Charged>(None) | |
| 360 | + | .await?; | |
| 361 | + | let charge_for = |micros: i64| { | |
| 362 | + | if self.free { | |
| 363 | + | 0 | |
| 364 | + | } else { | |
| 365 | + | charge_micros(micros as f64 / MICROS_PER_DOLLAR as f64, self.margin_percent) | |
| 366 | + | } | |
| 367 | + | }; | |
| 368 | + | let settled_at = rfc3339(now_ms()); | |
| 369 | + | // Claim it, so two crons never settle it twice. | |
| 370 | + | let claimed = self | |
| 371 | + | .db | |
| 372 | + | .prepare("UPDATE runs SET settled_at = ?, gateway_cost_micros = ?, finished_at = COALESCE(finished_at, ?) WHERE id = ? AND settled_at IS NULL RETURNING id") | |
| 373 | + | .bind(&[ | |
| 374 | + | settled_at.as_str().into(), | |
| 375 | + | (gateway_micros as f64).into(), | |
| 376 | + | settled_at.as_str().into(), | |
| 377 | + | run.id.as_str().into(), | |
| 378 | + | ])? | |
| 379 | + | .first::<Value>(None) | |
| 380 | + | .await?; | |
| 381 | + | if claimed.is_none() || requests == 0 { | |
| 382 | + | return Ok(()); | |
| 383 | + | } | |
| 384 | + | let free_note = if self.free { " (free while g1t is being built out)" } else { "" }; | |
| 385 | + | match charged { | |
| 386 | + | // Never reported: charged now, from the gateway's figure. | |
| 387 | + | None => { | |
| 388 | + | let description = format!( | |
| 389 | + | "Work on {}#{}, settled from AI Gateway after the sandbox stopped without reporting{free_note}", | |
| 390 | + | run.repo, run.number | |
| 391 | + | ); | |
| 392 | + | self.enter(&run.workspace, EntryKind::Usage, -charge_for(gateway_micros), &description, &run.id, Some(&row), Some(gateway_micros), None, None) | |
| 393 | + | .await?; | |
| 394 | + | } | |
| 395 | + | Some(charged) => { | |
| 396 | + | let reported = charged.cost_micros.unwrap_or(0); | |
| 397 | + | let delta = gateway_micros - reported; | |
| 398 | + | if delta == 0 { | |
| 399 | + | return Ok(()); | |
| 400 | + | } | |
| 401 | + | let amount = -(charge_for(gateway_micros) - charge_for(reported)); | |
| 402 | + | let description = format!( | |
| 403 | + | "Correction to “{}”: AI Gateway priced its {requests} model requests at {}, not {}", | |
| 404 | + | charged.description, | |
| 405 | + | crate::features::dollars(gateway_micros), | |
| 406 | + | crate::features::dollars(reported), | |
| 407 | + | ); | |
| 408 | + | self.enter( | |
| 409 | + | &run.workspace, | |
| 410 | + | EntryKind::Usage, | |
| 411 | + | amount, | |
| 412 | + | &description, | |
| 413 | + | &format!("{}/settled", run.id), | |
| 414 | + | Some(&row), | |
| 415 | + | Some(delta), | |
| 416 | + | None, | |
| 417 | + | None, | |
| 418 | + | ) | |
| 419 | + | .await?; | |
| 420 | + | } | |
| 421 | + | } | |
| 422 | + | Ok(()) | |
| 423 | + | } | |
| 424 | + | ||
| 425 | + | /// Checks each cost against what Cloudflare billed this month, and | |
| 426 | + | /// moves the ones that changed. | |
| 427 | + | pub(crate) async fn reconcile(&self, keeper: &Keeper) -> Result<()> { | |
| 428 | + | if keeper.token.is_none() { | |
| 429 | + | return Ok(()); | |
| 430 | + | } | |
| 431 | + | let now = rfc3339(now_ms()); | |
| 432 | + | let month_start = format!("{}-01", &now[..7]); | |
| 433 | + | let today = &now[..10]; | |
| 434 | + | let rows = keeper.billable_usage(&month_start, today).await?; | |
| 435 | + | for row in &rows { | |
| 436 | + | self.db | |
| 437 | + | .prepare( | |
| 438 | + | "INSERT INTO cloudflare_usage (period_start, period_end, service, unit, quantity, cost_usd, fetched_at) | |
| 439 | + | VALUES (?1, ?2, ?3, ?4, ?5, ?6, ?7) | |
| 440 | + | ON CONFLICT (period_start, service, unit) DO UPDATE SET | |
| 441 | + | period_end = ?2, quantity = ?5, cost_usd = ?6, fetched_at = ?7", | |
| 442 | + | ) | |
| 443 | + | .bind(&[ | |
| 444 | + | row.period_start.as_str().into(), | |
| 445 | + | row.period_end.as_str().into(), | |
| 446 | + | row.service.as_str().into(), | |
| 447 | + | row.unit.as_str().into(), | |
| 448 | + | row.quantity.into(), | |
| 449 | + | row.cost.into(), | |
| 450 | + | now.as_str().into(), | |
| 451 | + | ])? | |
| 452 | + | .run() | |
| 453 | + | .await?; | |
| 454 | + | } | |
| 455 | + | ||
| 456 | + | let matching = |service: &str, unit: Option<&str>| -> (f64, f64) { | |
| 457 | + | rows.iter() | |
| 458 | + | .filter(|r| r.service.to_lowercase().contains(service)) | |
| 459 | + | .filter(|r| unit.is_none_or(|u| r.unit.to_lowercase().contains(u))) | |
| 460 | + | .fold((0.0, 0.0), |(q, c), r| (q + r.quantity, c + r.cost)) | |
| 461 | + | }; | |
| 462 | + | ||
| 463 | + | // Containers: what they cost, over the seconds they ran. | |
| 464 | + | let (_, container_cost) = matching("container", None); | |
| 465 | + | if container_cost >= MIN_MEASURED_USD { | |
| 466 | + | let seconds = keeper.container_seconds(&format!("{month_start}T00:00:00Z"), &now).await?; | |
| 467 | + | if seconds > 0.0 { | |
| 468 | + | let per_second = container_cost * MICROS_PER_DOLLAR as f64 / seconds; | |
| 469 | + | for meter in ["sandbox_second", "build_second"] { | |
| 470 | + | self.measure(meter, per_second, &format!("Cloudflare billed ${container_cost:.2} for {seconds:.0} container-seconds this month")).await?; | |
| 471 | + | } | |
| 472 | + | } | |
| 473 | + | } | |
| 474 | + | // Workers for Platforms: per million requests and CPU milliseconds. | |
| 475 | + | for (meter, unit, scale) in [("app_requests", "request", 1e6), ("app_cpu", "ms", 1e6)] { | |
| 476 | + | let (quantity, cost) = matching("workers for platforms", Some(unit)); | |
| 477 | + | if cost >= MIN_MEASURED_USD && quantity > 0.0 { | |
| 478 | + | let per = cost * MICROS_PER_DOLLAR as f64 / quantity * scale; | |
| 479 | + | self.measure(meter, per, &format!("Cloudflare billed ${cost:.2} for {quantity:.0} {unit}s this month")).await?; | |
| 480 | + | } | |
| 481 | + | } | |
| 482 | + | self.db | |
| 483 | + | .prepare("UPDATE prices SET checked_at = ?") | |
| 484 | + | .bind(&[now.as_str().into()])? | |
| 485 | + | .run() | |
| 486 | + | .await?; | |
| 487 | + | Ok(()) | |
| 488 | + | } | |
| 489 | + | ||
| 490 | + | /// Moves a meter's cost to a measurement, if it is sound and different. | |
| 491 | + | async fn measure(&self, meter: &str, measured: f64, reason: &str) -> Result<()> { | |
| 492 | + | let Some((current, _)) = self.price(meter).await? else { | |
| 493 | + | return Ok(()); | |
| 494 | + | }; | |
| 495 | + | match adopt(current, measured) { | |
| 496 | + | Err(why) => worker::console_log!("{meter}: {why}"), | |
| 497 | + | Ok(None) => {} | |
| 498 | + | Ok(Some(cost)) => { | |
| 499 | + | let now = now_ms(); | |
| 500 | + | self.db | |
| 501 | + | .batch(vec![ | |
| 502 | + | self.db | |
| 503 | + | .prepare("UPDATE prices SET cost_micros = ?, source = 'cloudflare', updated_at = ? WHERE meter = ?") | |
| 504 | + | .bind(&[cost.into(), rfc3339(now).into(), meter.into()])?, | |
| 505 | + | self.db | |
| 506 | + | .prepare( | |
| 507 | + | "INSERT INTO price_changes (id, meter, old_cost_micros, new_cost_micros, markup_percent, reason, created_at) | |
| 508 | + | SELECT ?, meter, ?, ?, markup_percent, ?, ? FROM prices WHERE meter = ?", | |
| 509 | + | ) | |
| 510 | + | .bind(&[ | |
| 511 | + | new_id("prc", now).into(), | |
| 512 | + | current.into(), | |
| 513 | + | cost.into(), | |
| 514 | + | reason.into(), | |
| 515 | + | rfc3339(now).into(), | |
| 516 | + | meter.into(), | |
| 517 | + | ])?, | |
| 518 | + | ]) | |
| 519 | + | .await?; | |
| 520 | + | } | |
| 521 | + | } | |
| 522 | + | Ok(()) | |
| 523 | + | } | |
| 524 | + | } | |
| 525 | + | ||
| 526 | + | #[cfg(test)] | |
| 527 | + | mod tests { | |
| 528 | + | use super::*; | |
| 529 | + | ||
| 530 | + | #[test] | |
| 531 | + | fn small_moves_are_noise_and_wild_ones_are_not_believed() { | |
| 532 | + | assert_eq!(adopt(21.0, 21.2), Ok(None)); | |
| 533 | + | assert_eq!(adopt(21.0, 25.0), Ok(Some(25.0))); | |
| 534 | + | assert_eq!(adopt(21.0, 15.0), Ok(Some(15.0))); | |
| 535 | + | assert!(adopt(21.0, 200.0).is_err()); | |
| 536 | + | assert!(adopt(21.0, 0.0).is_err()); | |
| 537 | + | } | |
| 538 | + | ||
| 539 | + | #[test] | |
| 540 | + | fn usage_rows_are_read_by_their_focus_names() { | |
| 541 | + | let row = UsageRow::from_value(&json!({ | |
| 542 | + | "ServiceFamilyName": "Containers", | |
| 543 | + | "ServiceName": "Memory", | |
| 544 | + | "ConsumedUnit": "GiB-seconds", | |
| 545 | + | "PricingQuantity": "1200.5", | |
| 546 | + | "ContractedCost": 0.003, | |
| 547 | + | "ChargePeriodStart": "2026-10-01", | |
| 548 | + | })) | |
| 549 | + | .unwrap(); | |
| 550 | + | assert_eq!(row.service, "Containers / Memory"); | |
| 551 | + | assert_eq!(row.quantity, 1200.5); | |
| 552 | + | assert_eq!(row.cost, 0.003); | |
| 553 | + | assert!(UsageRow::from_value(&json!({ "nothing": 1 })).is_none()); | |
| 554 | + | } | |
| 555 | + | } |
| 17 | 17 | //! the methods and their arguments. | |
| 18 | 18 | ||
| 19 | 19 | mod features; | |
| 20 | + | mod keeper; | |
| 20 | 21 | mod limits; | |
| 21 | 22 | mod stripe; | |
| 22 | 23 | ||
| 27 | 28 | use serde::Deserialize; | |
| 28 | 29 | use sha2::{Digest, Sha256}; | |
| 29 | 30 | use worker::wasm_bindgen::JsValue; | |
| 30 | − | use worker::{Context, D1Database, Env, Request, Response, Result, event}; | |
| 31 | + | use worker::{Context, D1Database, Env, Request, Response, Result, ScheduleContext, ScheduledEvent, event}; | |
| 31 | 32 | ||
| 32 | 33 | use stripe::Stripe; | |
| 33 | 34 | ||
| 597 | 598 | let token = hex::encode(bytes); | |
| 598 | 599 | self.db | |
| 599 | 600 | .prepare( | |
| 600 | − | "INSERT INTO runs (id, workspace, repo, number, task, model, token_hash, created_at, billed_to) | |
| 601 | − | VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)", | |
| 601 | + | "INSERT INTO runs (id, workspace, repo, number, task, model, token_hash, created_at, billed_to, session_id) | |
| 602 | + | VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)", | |
| 602 | 603 | ) | |
| 603 | 604 | .bind(&[ | |
| 604 | 605 | run_id.as_str().into(), | |
| 610 | 611 | hash(&token).into(), | |
| 611 | 612 | rfc3339(now).into(), | |
| 612 | 613 | if a.billed_to == "workspace" { "workspace" } else { "g1t" }.into(), | |
| 614 | + | optional(a.session.as_deref().filter(|_| a.billed_to != "workspace")), | |
| 613 | 615 | ])? | |
| 614 | 616 | .run() | |
| 615 | 617 | .await?; | |
| 719 | 721 | .await? | |
| 720 | 722 | .map_or(seconds, |used| used.seconds); | |
| 721 | 723 | let billable = sandbox_billable(after - seconds, seconds); | |
| 722 | − | let charge = if self.free { 0 } else { billable * sandbox_allowance::MICROS_PER_SECOND }; | |
| 724 | + | // From the price book, which follows what Cloudflare bills g1t. | |
| 725 | + | let (cost_per_second, price_per_second) = self.price("sandbox_second").await?.unwrap_or(( | |
| 726 | + | sandbox_allowance::COST_MICROS_PER_SECOND as f64, | |
| 727 | + | sandbox_allowance::MICROS_PER_SECOND as f64, | |
| 728 | + | )); | |
| 729 | + | let charge = if self.free { 0 } else { (billable as f64 * price_per_second).ceil() as i64 }; | |
| 723 | 730 | let mut description = format!("{}: {} of sandbox time", a.description, duration(seconds)); | |
| 724 | 731 | if billable < seconds { | |
| 725 | 732 | description.push_str(if billable == 0 { | |
| 746 | 753 | (-(charge as f64)).into(), | |
| 747 | 754 | description.as_str().into(), | |
| 748 | 755 | optional(a.repo.as_deref()), | |
| 749 | − | ((seconds * sandbox_allowance::COST_MICROS_PER_SECOND) as f64).into(), | |
| 756 | + | (seconds as f64 * cost_per_second).ceil().into(), | |
| 750 | 757 | a.reference.as_str().into(), | |
| 751 | 758 | timestamp.as_str().into(), | |
| 752 | 759 | ])?, | |
| 793 | 800 | ) | |
| 794 | 801 | } | |
| 795 | 802 | ||
| 803 | + | impl Billing { | |
| 804 | + | fn from_env(env: &Env) -> Result<Self> { | |
| 805 | + | Ok(Billing { | |
| 806 | + | db: env.d1("DB")?, | |
| 807 | + | stripe: env | |
| 808 | + | .secret("STRIPE_SECRET_KEY") | |
| 809 | + | .ok() | |
| 810 | + | .map(|key| key.to_string()) | |
| 811 | + | .filter(|key| !key.is_empty()) | |
| 812 | + | .map(Stripe::new), | |
| 813 | + | margin_percent: env | |
| 814 | + | .var("MARGIN_PERCENT") | |
| 815 | + | .ok() | |
| 816 | + | .and_then(|percent| percent.to_string().parse().ok()) | |
| 817 | + | .unwrap_or(20), | |
| 818 | + | orchestration_fee_micros: env | |
| 819 | + | .var("ORCHESTRATION_FEE_MICROS") | |
| 820 | + | .ok() | |
| 821 | + | .and_then(|fee| fee.to_string().parse().ok()) | |
| 822 | + | .unwrap_or(100_000), | |
| 823 | + | free: env.var("FREE_WHILE_BUILDING").is_ok_and(|v| v.to_string() == "true"), | |
| 824 | + | ceilings: limits::Ceilings::from_env(&env), | |
| 825 | + | deployments_monthly_cents: env | |
| 826 | + | .var("DEPLOYMENTS_MONTHLY_CENTS") | |
| 827 | + | .ok() | |
| 828 | + | .and_then(|cents| cents.to_string().parse().ok()) | |
| 829 | + | .unwrap_or(500), | |
| 830 | + | trial: { | |
| 831 | + | let number = |name: &str| env.var(name).ok().and_then(|v| v.to_string().parse::<i64>().ok()); | |
| 832 | + | match ( | |
| 833 | + | number("TRIAL_WORKSPACE_MICROS"), | |
| 834 | + | number("TRIAL_TOTAL_MICROS"), | |
| 835 | + | env.var("TRIAL_UNTIL").ok().map(|v| v.to_string()), | |
| 836 | + | ) { | |
| 837 | + | (Some(per_workspace_micros), Some(total_micros), Some(until)) | |
| 838 | + | if per_workspace_micros > 0 && !until.is_empty() => | |
| 839 | + | { | |
| 840 | + | Some(TrialConfig { | |
| 841 | + | per_workspace_micros, | |
| 842 | + | total_micros, | |
| 843 | + | until, | |
| 844 | + | }) | |
| 845 | + | } | |
| 846 | + | _ => None, | |
| 847 | + | } | |
| 848 | + | }, | |
| 849 | + | }) | |
| 850 | + | } | |
| 851 | + | } | |
| 852 | + | ||
| 853 | + | #[event(scheduled)] | |
| 854 | + | async fn scheduled(event: ScheduledEvent, env: Env, _ctx: ScheduleContext) { | |
| 855 | + | let Ok(billing) = Billing::from_env(&env) else { | |
| 856 | + | return; | |
| 857 | + | }; | |
| 858 | + | let keeper = keeper::Keeper::from_env(&env); | |
| 859 | + | if let Err(error) = billing.settle_runs(&keeper).await { | |
| 860 | + | worker::console_error!("settling runs failed: {error}"); | |
| 861 | + | } | |
| 862 | + | // Once a day: check every cost against what Cloudflare billed. | |
| 863 | + | if event.cron() == keeper::DAILY { | |
| 864 | + | if let Err(error) = billing.reconcile(&keeper).await { | |
| 865 | + | worker::console_error!("checking costs against Cloudflare failed: {error}"); | |
| 866 | + | } | |
| 867 | + | } | |
| 868 | + | } | |
| 869 | + | ||
| 796 | 870 | #[event(fetch)] | |
| 797 | 871 | async fn fetch(mut request: Request, env: Env, _ctx: Context) -> Result<Response> { | |
| 798 | 872 | let Some(method) = rpc_method(&request) else { | |
| 799 | 873 | return Response::error("Not found", 404); | |
| 800 | 874 | }; | |
| 801 | 875 | let body: serde_json::Value = request.json().await?; | |
| 802 | − | let billing = Billing { | |
| 803 | − | db: env.d1("DB")?, | |
| 804 | − | stripe: env | |
| 805 | − | .secret("STRIPE_SECRET_KEY") | |
| 806 | − | .ok() | |
| 807 | − | .map(|key| key.to_string()) | |
| 808 | − | .filter(|key| !key.is_empty()) | |
| 809 | − | .map(Stripe::new), | |
| 810 | − | margin_percent: env | |
| 811 | − | .var("MARGIN_PERCENT") | |
| 812 | − | .ok() | |
| 813 | − | .and_then(|percent| percent.to_string().parse().ok()) | |
| 814 | − | .unwrap_or(20), | |
| 815 | − | orchestration_fee_micros: env | |
| 816 | − | .var("ORCHESTRATION_FEE_MICROS") | |
| 817 | − | .ok() | |
| 818 | − | .and_then(|fee| fee.to_string().parse().ok()) | |
| 819 | − | .unwrap_or(100_000), | |
| 820 | − | free: env.var("FREE_WHILE_BUILDING").is_ok_and(|v| v.to_string() == "true"), | |
| 821 | − | ceilings: limits::Ceilings::from_env(&env), | |
| 822 | − | deployments_monthly_cents: env | |
| 823 | − | .var("DEPLOYMENTS_MONTHLY_CENTS") | |
| 824 | − | .ok() | |
| 825 | − | .and_then(|cents| cents.to_string().parse().ok()) | |
| 826 | − | .unwrap_or(500), | |
| 827 | − | trial: { | |
| 828 | − | let number = |name: &str| env.var(name).ok().and_then(|v| v.to_string().parse::<i64>().ok()); | |
| 829 | − | match ( | |
| 830 | − | number("TRIAL_WORKSPACE_MICROS"), | |
| 831 | − | number("TRIAL_TOTAL_MICROS"), | |
| 832 | − | env.var("TRIAL_UNTIL").ok().map(|v| v.to_string()), | |
| 833 | − | ) { | |
| 834 | − | (Some(per_workspace_micros), Some(total_micros), Some(until)) | |
| 835 | − | if per_workspace_micros > 0 && !until.is_empty() => | |
| 836 | − | { | |
| 837 | − | Some(TrialConfig { | |
| 838 | − | per_workspace_micros, | |
| 839 | − | total_micros, | |
| 840 | − | until, | |
| 841 | − | }) | |
| 842 | − | } | |
| 843 | − | _ => None, | |
| 844 | − | } | |
| 845 | − | }, | |
| 846 | − | }; | |
| 876 | + | let billing = Billing::from_env(&env)?; | |
| 847 | 877 | match method.as_str() { | |
| 848 | 878 | "status" => reply(&billing.status()), | |
| 849 | 879 | "account" => reply(&billing.account(args(body)?).await?), | |
| 865 | 895 | "limit" => reply(&billing.limit(args(body)?).await?), | |
| 866 | 896 | "check_limit" => reply(&billing.check_limit(args(body)?).await?), | |
| 867 | 897 | "set_spend_limit" => reply(&billing.set_spend_limit(args(body)?).await?), | |
| 898 | + | "prices" => reply(&billing.prices().await?), | |
| 899 | + | "note_pending" => reply(&billing.note_pending(args(body)?).await?), | |
| 868 | 900 | _ => Response::error("Unknown method", 404), | |
| 869 | 901 | } | |
| 870 | 902 | } |
| 21 | 21 | //! exemption from the ceiling. Test-mode payments are not money, so they | |
| 22 | 22 | //! do not raise trust. | |
| 23 | 23 | ||
| 24 | − | use g1t_contracts::billing::{CheckLimitArgs, Limit, LimitArgs, LimitState, SetSpendLimitArgs, Trust}; | |
| 24 | + | use g1t_contracts::billing::{CheckLimitArgs, Limit, LimitArgs, NotePendingArgs, LimitState, SetSpendLimitArgs, Trust}; | |
| 25 | 25 | use g1t_contracts::time::rfc3339; | |
| 26 | 26 | use g1t_contracts::{FailureCode, Outcome, Role}; | |
| 27 | 27 | use g1t_kit::now_ms; | |
| 124 | 124 | .first::<Month>(None) | |
| 125 | 125 | .await?; | |
| 126 | 126 | let (used, paid_month) = month.map_or((0, 0), |m| (m.used.unwrap_or(0), m.paid.unwrap_or(0))); | |
| 127 | + | // And what is metered but not charged until the month closes. | |
| 128 | + | let pending = self | |
| 129 | + | .db | |
| 130 | + | .prepare("SELECT SUM(charge_micros) AS paid FROM pending_usage WHERE workspace = ? AND month = ?") | |
| 131 | + | .bind(&[workspace.as_str().into(), month_start[..7].into()])? | |
| 132 | + | .first::<Paid>(None) | |
| 133 | + | .await? | |
| 134 | + | .and_then(|row| row.paid) | |
| 135 | + | .unwrap_or(0); | |
| 136 | + | let used = used + pending; | |
| 127 | 137 | // Test-mode payments are not money: they pay nothing off. | |
| 128 | 138 | let live = self.stripe.as_ref().is_some_and(crate::stripe::Stripe::live); | |
| 129 | 139 | let exposure = (used - if live { paid_month } else { 0 }).max(0); | |
| 216 | 226 | Ok(Outcome::Ok(self.limit_of(&workspace).await?)) | |
| 217 | 227 | } | |
| 218 | 228 | ||
| 229 | + | pub(crate) async fn note_pending(&self, a: NotePendingArgs) -> Result<bool> { | |
| 230 | + | let now = rfc3339(now_ms()); | |
| 231 | + | let charge = crate::charge_micros(a.cost_micros.max(0) as f64 / g1t_contracts::billing::MICROS_PER_DOLLAR as f64, self.margin_percent); | |
| 232 | + | self.db | |
| 233 | + | .prepare( | |
| 234 | + | "INSERT INTO pending_usage (workspace, source, month, charge_micros, updated_at) VALUES (?1, ?2, ?3, ?4, ?5) | |
| 235 | + | ON CONFLICT (workspace, source, month) DO UPDATE SET charge_micros = ?4, updated_at = ?5", | |
| 236 | + | ) | |
| 237 | + | .bind(&[ | |
| 238 | + | a.workspace.to_lowercase().into(), | |
| 239 | + | a.source.as_str().into(), | |
| 240 | + | now[..7].into(), | |
| 241 | + | (charge as f64).into(), | |
| 242 | + | now.as_str().into(), | |
| 243 | + | ])? | |
| 244 | + | .run() | |
| 245 | + | .await?; | |
| 246 | + | Ok(true) | |
| 247 | + | } | |
| 248 | + | ||
| 219 | 249 | pub(crate) async fn check_limit(&self, a: CheckLimitArgs) -> Result<Outcome<Limit>> { | |
| 220 | 250 | Ok(Outcome::Ok(self.limit_of(&a.workspace).await?)) | |
| 221 | 251 | } |
| 47 | 47 | "TRIAL_UNTIL": "2026-10-23T06:59:59Z", | |
| 48 | 48 | // The Deployments plan's monthly price, in cents. Turning the | |
| 49 | 49 | // feature on starts it; FREE_WHILE_BUILDING does not cover it. | |
| 50 | − | "DEPLOYMENTS_MONTHLY_CENTS": "500" | |
| 50 | + | "DEPLOYMENTS_MONTHLY_CENTS": "500", | |
| 51 | + | // Where the keeper reads what g1t pays (src/keeper.rs). Its token, | |
| 52 | + | // CLOUDFLARE_USAGE_TOKEN, is a secret: Billing, Account Analytics | |
| 53 | + | // and AI Gateway, read only. | |
| 54 | + | "CLOUDFLARE_ACCOUNT_ID": "1e6f2cffa3f445920836e8ebe446bb58", | |
| 55 | + | "AI_GATEWAY_ID": "g1t" | |
| 51 | 56 | }, | |
| 57 | + | // Settling runs every 15 minutes; checking costs daily (keeper::DAILY). | |
| 58 | + | "triggers": { "crons": ["*/15 * * * *", "17 4 * * *"] }, | |
| 52 | 59 | // Secret: STRIPE_SECRET_KEY. Without it nothing is charged and the | |
| 53 | 60 | // runner decides who may start agents some other way. | |
| 54 | 61 | "observability": { "enabled": true } |
| 823 | 823 | ||
| 824 | 824 | /** Each build is charged by the second at the container price plus the margin. */ | |
| 825 | 825 | private async chargeBuild(row: DeploymentRow, seconds: number): Promise<void> { | |
| 826 | − | const cost = Math.ceil(seconds) * DEPLOYMENTS_ALLOWANCE.microsPerBuildSecond; | |
| 826 | + | const costs = await this.costs(); | |
| 827 | + | const cost = Math.ceil(Math.ceil(seconds) * costs.buildSecond); | |
| 827 | 828 | if (cost <= 0) return; | |
| 828 | 829 | const what = | |
| 829 | 830 | row.kind === "preview" | |
| 846 | 847 | .run(); | |
| 847 | 848 | } | |
| 848 | 849 | ||
| 850 | + | /** | |
| 851 | + | * What each unit costs g1t now, from billing's price book, which follows | |
| 852 | + | * what Cloudflare bills. The plan's figures if billing cannot say. | |
| 853 | + | */ | |
| 854 | + | private async costs(): Promise<{ buildSecond: number; millionRequests: number; millionCpuMs: number; appMonth: number }> { | |
| 855 | + | const a = DEPLOYMENTS_ALLOWANCE; | |
| 856 | + | const book = await billingClient(this.env.BILLING) | |
| 857 | + | .prices() | |
| 858 | + | .catch(() => null); | |
| 859 | + | const cost = (meter: string, fallback: number) => book?.prices.find((p) => p.meter === meter)?.costMicros ?? fallback; | |
| 860 | + | return { | |
| 861 | + | buildSecond: cost("build_second", a.microsPerBuildSecond), | |
| 862 | + | millionRequests: cost("app_requests", a.microsPerMillionRequests), | |
| 863 | + | millionCpuMs: cost("app_cpu", a.microsPerMillionCpuMs), | |
| 864 | + | appMonth: cost("app_month", a.microsPerAppMonth), | |
| 865 | + | }; | |
| 866 | + | } | |
| 867 | + | ||
| 849 | 868 | /** Remembers the most apps the workspace had up at once this month. */ | |
| 850 | 869 | private async notePeak(workspace: string): Promise<void> { | |
| 851 | 870 | await this.db | |
| 1061 | 1080 | } | |
| 1062 | 1081 | } | |
| 1063 | 1082 | for (const workspace of new Set(apps.map((app) => app.workspace))) await this.notePeak(workspace); | |
| 1083 | + | // What this month's traffic past the plan will cost, so the workspace's | |
| 1084 | + | // limit counts it now rather than when the month closes. | |
| 1085 | + | const costs = await this.costs(); | |
| 1086 | + | const a = DEPLOYMENTS_ALLOWANCE; | |
| 1087 | + | for (const workspace of perWorkspace.keys()) { | |
| 1088 | + | const meter = await this.db | |
| 1089 | + | .prepare("SELECT requests, cpu_ms, peak_apps FROM meters WHERE namespace = ? AND month = ?") | |
| 1090 | + | .bind(workspace, month()) | |
| 1091 | + | .first<{ requests: number; cpu_ms: number; peak_apps: number }>(); | |
| 1092 | + | if (!meter) continue; | |
| 1093 | + | const cost = Math.ceil( | |
| 1094 | + | (Math.max(0, meter.requests - a.requests) / 1_000_000) * costs.millionRequests + | |
| 1095 | + | (Math.max(0, meter.cpu_ms - a.cpuMs) / 1_000_000) * costs.millionCpuMs + | |
| 1096 | + | Math.max(0, meter.peak_apps - a.apps) * costs.appMonth, | |
| 1097 | + | ); | |
| 1098 | + | await billingClient(this.env.BILLING) | |
| 1099 | + | .notePending(workspace, "deployments", cost) | |
| 1100 | + | .catch((error) => console.error("could not note pending usage", error)); | |
| 1101 | + | } | |
| 1064 | 1102 | } | |
| 1065 | 1103 | ||
| 1066 | 1104 | /** Previews no one has visited in their project's idle days. */ | |
| 1082 | 1120 | .bind(month()) | |
| 1083 | 1121 | .all<{ namespace: string; month: string; requests: number; cpu_ms: number; peak_apps: number }>(); | |
| 1084 | 1122 | const a = DEPLOYMENTS_ALLOWANCE; | |
| 1123 | + | const costs = await this.costs(); | |
| 1085 | 1124 | for (const meter of due.results) { | |
| 1086 | 1125 | const extraRequests = Math.max(0, meter.requests - a.requests); | |
| 1087 | 1126 | const extraCpu = Math.max(0, meter.cpu_ms - a.cpuMs); | |
| 1088 | 1127 | const extraApps = Math.max(0, meter.peak_apps - a.apps); | |
| 1089 | 1128 | const cost = Math.ceil( | |
| 1090 | − | (extraRequests / 1_000_000) * a.microsPerMillionRequests + | |
| 1091 | − | (extraCpu / 1_000_000) * a.microsPerMillionCpuMs + | |
| 1092 | − | extraApps * a.microsPerAppMonth, | |
| 1129 | + | (extraRequests / 1_000_000) * costs.millionRequests + | |
| 1130 | + | (extraCpu / 1_000_000) * costs.millionCpuMs + | |
| 1131 | + | extraApps * costs.appMonth, | |
| 1093 | 1132 | ); | |
| 1094 | 1133 | if (cost > 0) { | |
| 1095 | 1134 | const parts = [ |
| 104 | 104 | issue: Option<String>, | |
| 105 | 105 | } | |
| 106 | 106 | ||
| 107 | + | /// A model session's public id: the start of its token's hash. | |
| 108 | + | fn session_id(token_hash: &str) -> String { | |
| 109 | + | format!("ms_{}", &token_hash[..token_hash.len().min(24)]) | |
| 110 | + | } | |
| 111 | + | ||
| 107 | 112 | #[derive(Deserialize)] | |
| 108 | 113 | struct SessionRow { | |
| 114 | + | token_hash: String, | |
| 109 | 115 | workspace: String, | |
| 110 | 116 | connection_id: Option<String>, | |
| 111 | 117 | repo: String, | |
| 1219 | 1225 | ])?, | |
| 1220 | 1226 | ]) | |
| 1221 | 1227 | .await?; | |
| 1228 | + | let id = session_id(&crypto::sha256_hex(&token)); | |
| 1222 | 1229 | Ok(Outcome::Ok(ModelSession { | |
| 1223 | 1230 | token, | |
| 1224 | 1231 | billed_to: if connection.is_some() { "workspace" } else { "g1t" }.to_owned(), | |
| 1225 | 1232 | provider_name: connection.map(|row| row.name.clone()), | |
| 1226 | 1233 | model, | |
| 1234 | + | id, | |
| 1227 | 1235 | })) | |
| 1228 | 1236 | } | |
| 1229 | 1237 | ||
| 1247 | 1255 | repo: session.repo, | |
| 1248 | 1256 | number: session.number, | |
| 1249 | 1257 | task: session.task, | |
| 1258 | + | session: session_id(&session.token_hash), | |
| 1250 | 1259 | base_url: None, | |
| 1251 | 1260 | api_key: None, | |
| 1252 | 1261 | auth_header: None, |
| 5 | 5 | ||
| 6 | 6 | import { presentedToken, upstreamRequest } from "./route.ts"; | |
| 7 | 7 | ||
| 8 | − | const run = { workspace: "acme", repo: "acme/web", number: 7, task: "implement", baseUrl: null, apiKey: null, authHeader: null, api: "anthropic" as const, model: null, official: false, provider: "g1t" }; | |
| 8 | + | const run = { workspace: "acme", repo: "acme/web", number: 7, task: "implement", session: "ms_abc", baseUrl: null, apiKey: null, authHeader: null, api: "anthropic" as const, model: null, official: false, provider: "g1t" }; | |
| 9 | 9 | const hosted = { AI_GATEWAY_ID: "g1t", CLOUDFLARE_ACCOUNT_ID: "acct", AI_GATEWAY_TOKEN: "gw-token" }; | |
| 10 | 10 | ||
| 11 | 11 | function incoming(): Headers { | |
| 35 | 35 | workspace: "acme", | |
| 36 | 36 | repo: "acme/web", | |
| 37 | 37 | pull: 7, | |
| 38 | + | session: "ms_abc", | |
| 38 | 39 | }); | |
| 39 | 40 | }); | |
| 40 | 41 |
| 55 | 55 | // be read per kind of work, workspace, repository and pull request. | |
| 56 | 56 | headers.set( | |
| 57 | 57 | "cf-aig-metadata", | |
| 58 | − | JSON.stringify({ task: upstream.task, workspace: upstream.workspace, repo: upstream.repo, pull: upstream.number }), | |
| 58 | + | JSON.stringify({ | |
| 59 | + | task: upstream.task, | |
| 60 | + | workspace: upstream.workspace, | |
| 61 | + | repo: upstream.repo, | |
| 62 | + | pull: upstream.number, | |
| 63 | + | // What billing finds the run's requests by, to charge what they cost. | |
| 64 | + | session: upstream.session, | |
| 65 | + | }), | |
| 59 | 66 | ); | |
| 60 | 67 | if (hosted.AI_GATEWAY_TOKEN) headers.set("cf-aig-authorization", `Bearer ${hosted.AI_GATEWAY_TOKEN}`); | |
| 61 | 68 | if (hosted.ANTHROPIC_API_KEY) headers.set("x-api-key", hosted.ANTHROPIC_API_KEY); |
| 557 | 557 | task, | |
| 558 | 558 | model: own ? `${modelName} (${session?.providerName ?? "own provider"})` : modelName, | |
| 559 | 559 | billedTo: own ? "workspace" : "g1t", | |
| 560 | + | session: own ? null : (session?.id ?? null), | |
| 560 | 561 | }); | |
| 561 | 562 | if (!ticket.ok) return ticket; | |
| 562 | 563 | const vars: Record<string, string> = session |