fix(cost): per-model pricing so pi/Paperclip report real spend

The omni provider's models.json entries carried no 'cost' field, so pi's
calculateCost() returned 0 for every run and Paperclip cost events/budgets
all read $0.00 despite real spend.

- scripts/omni-pricing.mjs: pulls authoritative prices (OmniRoute /api/pricing
  for deepseek/*, OpenRouter /api/v1/models for openrouter/*) and injects
  { cost: { input, output, cacheRead, cacheWrite } } USD per 1M tokens.
- Priced: deepseek-v4-flash, deepseek-v4-pro, gemini-3.1-flash-lite, gemini-2.5-flash.
- Must be re-run after every /omni sync, which rewrites models.json wholesale.
This commit is contained in:
2026-09-27 18:37:24 +10:00
parent 3f36f599ce
commit 3a8a6e98b1
2 changed files with 5478 additions and 5290 deletions

10604
models.json

File diff suppressed because it is too large Load Diff

164
scripts/omni-pricing.mjs Normal file
View File

@@ -0,0 +1,164 @@
#!/usr/bin/env node
/**
* Inject per-model pricing into ~/.agents/models.json for the `omni` provider.
*
* WHY THIS EXISTS
* ---------------
* `pi --list-models` / the omni extension's /omni sync regenerates models.json
* from OmniRoute and writes entries WITHOUT a `cost` field. pi's calculateCost()
* then reports $0.00 for every run, so Paperclip's cost events and budgets all
* read zero even though real money is being spent.
*
* The fix is to add { cost: { input, output, cacheRead, cacheWrite } } (USD per
* million tokens) to the model entries we actually use.
*
* Because /omni sync rewrites the whole file, this script must be re-run after
* every sync. That is the whole reason it is a script and not a one-off edit.
*
* PRICE SOURCES (both authoritative, no guessing)
* - deepseek/* -> OmniRoute /api/pricing, group "deepseek"
* - openrouter/* -> OpenRouter /api/v1/models (strip the "openrouter/" prefix)
*
* Model ids that use routing prefixes (aug/, ds/, oc/, tllm/, opencode-go/) do
* NOT map cleanly to pricing groups and are deliberately skipped — add them to
* MANUAL below if you need them.
*
* USAGE
* node omni-pricing.mjs --dry-run # show what would change
* node omni-pricing.mjs # write models.json
*/
import fs from "node:fs";
import path from "node:path";
const MODELS_JSON = path.join(process.env.HOME, ".agents", "models.json");
const OMNIROUTE_PRICING = "http://192.168.20.13:20128/api/pricing";
const OPENROUTER_MODELS = "https://openrouter.ai/api/v1/models";
// Models we actually assign to workers. Keep this list short and deliberate.
const TARGETS = [
"deepseek/deepseek-v4-flash",
"deepseek/deepseek-v4-pro",
"openrouter/google/gemini-3.1-flash-lite",
"openrouter/google/gemini-2.5-flash",
];
// Hand-priced entries: id -> {input, output, cacheRead, cacheWrite}
const MANUAL = {};
const dryRun = process.argv.includes("--dry-run");
function omniKey() {
const cfg = JSON.parse(fs.readFileSync(MODELS_JSON, "utf8"));
return cfg.providers?.omni?.apiKey ?? "";
}
/** Fetch OmniRoute's own price table: { group: { model: {input,output,cached,cache_creation} } } */
async function fetchOmniRoutePricing() {
const res = await fetch(OMNIROUTE_PRICING, {
headers: { Authorization: `Bearer ${omniKey()}` },
});
if (!res.ok) throw new Error(`OmniRoute pricing HTTP ${res.status}`);
return res.json();
}
/** Fetch OpenRouter prices keyed by bare model id (no "openrouter/" prefix). */
async function fetchOpenRouterPricing() {
const res = await fetch(OPENROUTER_MODELS);
if (!res.ok) throw new Error(`OpenRouter models HTTP ${res.status}`);
const { data } = await res.json();
const out = {};
for (const m of data) {
const p = m.pricing ?? {};
out[m.id] = {
input: Number(p.prompt ?? 0) * 1e6,
output: Number(p.completion ?? 0) * 1e6,
cacheRead: Number(p.input_cache_read ?? 0) * 1e6,
cacheWrite: Number(p.input_cache_write ?? 0) * 1e6,
};
}
return out;
}
const r6 = (n) => Math.round(Number(n) * 1e6) / 1e6;
/** Resolve a pi model id to a {input,output,cacheRead,cacheWrite} price, or null. */
function resolvePrice(id, omniPricing, orPricing) {
if (MANUAL[id]) return MANUAL[id];
// deepseek/<name> -> OmniRoute group "deepseek"
if (id.startsWith("deepseek/")) {
const name = id.slice("deepseek/".length);
const row = omniPricing?.deepseek?.[name];
if (row) {
return {
input: r6(row.input),
output: r6(row.output),
cacheRead: r6(row.cached ?? 0),
cacheWrite: r6(row.cache_creation ?? 0),
};
}
}
// openrouter/<bare-id> -> OpenRouter catalogue
if (id.startsWith("openrouter/")) {
const bare = id.slice("openrouter/".length);
if (orPricing[bare]) {
const p = orPricing[bare];
return { input: r6(p.input), output: r6(p.output), cacheRead: r6(p.cacheRead), cacheWrite: r6(p.cacheWrite) };
}
}
return null;
}
const cfg = JSON.parse(fs.readFileSync(MODELS_JSON, "utf8"));
const models = cfg.providers?.omni?.models;
if (!Array.isArray(models)) {
console.error("models.json: providers.omni.models is not an array — aborting");
process.exit(1);
}
const [omniPricing, orPricing] = await Promise.all([
fetchOmniRoutePricing(),
fetchOpenRouterPricing(),
]);
const byId = new Map(models.filter((m) => m && m.id).map((m) => [m.id, m]));
let changed = 0;
const missing = [];
for (const id of TARGETS) {
const entry = byId.get(id);
if (!entry) {
missing.push(id);
continue;
}
const price = resolvePrice(id, omniPricing, orPricing);
if (!price) {
missing.push(id);
continue;
}
const current = JSON.stringify(entry.cost ?? null);
const next = JSON.stringify(price);
if (current !== next) {
entry.cost = price;
changed++;
console.log(
`${dryRun ? "[dry-run] " : ""}${id} -> in $${price.input} out $${price.output} cacheR $${price.cacheRead} cacheW $${price.cacheWrite}`,
);
} else {
console.log(`${id} -> already priced, unchanged`);
}
}
if (missing.length) console.log(`\nnot found / no price (skipped): ${missing.join(", ")}`);
if (dryRun) {
console.log(`\ndry-run: ${changed} entr(y/ies) would change`);
} else if (changed) {
fs.writeFileSync(MODELS_JSON, JSON.stringify(cfg, null, 2) + "\n");
console.log(`\nwrote ${MODELS_JSON} (${changed} changed)`);
} else {
console.log("\nnothing to do");
}