ai-lcr 0.4.0 → 0.5.1

package/CHANGELOG.md

@@ -4,6 +4,28 @@ All notable changes to `ai-lcr` are documented here. The format follows
 [Keep a Changelog](https://keepachangelog.com/), and the project adheres to
 [Semantic Versioning](https://semver.org/).
 
+## [0.5.0] — 2026-06-02
+
+All additions are optional and backward compatible.
+
+### Added
+
+- **Official-price savings baseline for media.** A media model's savings baseline
+  is now the model-maker's first-party list price — what a user pays going
+  *direct*, bypassing the cheaper providers we route to — instead of the priciest
+  provider we happen to route between. For the common case of a model served by a
+  single aggregator (Runware, fal, …), the old baseline equalled the actual cost,
+  so savings showed as `$0`; the official price surfaces the real saving.
+  - `MediaModelDef.official?: MediaPricing` — an inline first-party price on a
+    model def. When set, it wins.
+  - `MediaLCRConfig.officialPrices?: Record<string, MediaPricing>` — a modelId →
+    price map so a downstream registry gets correct baselines without inlining
+    prices. Defaults to the bundled **`OFFICIAL_PRICES`** (now exported), lifted
+    from the cross-provider price table by `scripts/gen-media-official.mjs`.
+  - When no official price is known (e.g. open-weight models served only by
+    aggregators), the baseline falls back to the priciest configured route — or
+    none if there's a single route — exactly as before.
+
 ## [0.4.0] — 2026-06-02
 
 All additions are optional and backward compatible.

package/dist/index.cjs

@@ -22,6 +22,7 @@ var index_exports = {};
 __export(index_exports, {
   DEFAULT_REFERENCE: () => DEFAULT_REFERENCE,
   MEDIA_PRICING: () => MEDIA_PRICING,
+  OFFICIAL_PRICES: () => OFFICIAL_PRICES,
   cheapestRoute: () => cheapestRoute,
   classifyError: () => classifyError,
   classifyErrorKind: () => classifyErrorKind,
@@ -193,6 +194,11 @@ function costForUsage(cost, inputTokens, outputTokens, cacheReadTokens) {
   const cachedRate = cost.cacheRead ?? cost.input;
   return fullInput / 1e6 * cost.input + cached / 1e6 * cachedRate + outputTokens / 1e6 * cost.output;
 }
+function cacheSavingForUsage(cost, inputTokens, cacheReadTokens) {
+  if (cost.cacheRead === void 0) return 0;
+  const cached = Math.min(Math.max(cacheReadTokens, 0), inputTokens);
+  return cached / 1e6 * (cost.input - cost.cacheRead);
+}
 function requestIdFrom(options) {
   const raw = options.providerOptions?.lcr?.requestId;
   return typeof raw === "string" && raw.length > 0 ? raw : void 0;
@@ -297,19 +303,22 @@ var LcrFallbackModel = class {
     });
   }
   /**
-   * Baseline = what this same usage would have cost on the most expensive
-   * *priced* provider in the chain (typically the OpenRouter fallback leg). The
-   * winner's savings is `baselineUsd - costUsd`. Undefined when no provider in
-   * the chain carries a price (nothing to compare against).
+   * Baseline = what this same usage would have cost on the always-on fallback:
+   * the LAST priced leg of the chain (by convention the list-price provider you'd
+   * use without routing — e.g. OpenRouter, always last). The winner's saving is
+   * `baselineUsd - costUsd`. We take the last priced leg, NOT the most expensive
+   * one: prompt caching can make a sticker-cheaper provider (no `cacheRead`) cost
+   * MORE on a cache-heavy call, and a max-of-chain baseline would then fabricate a
+   * "saving" even on calls the fallback itself served. Undefined when no provider
+   * in the chain carries a price (nothing to compare against).
    */
   baselineUsd(inputTokens, outputTokens, cacheReadTokens) {
-    let max;
+    let baseline;
     for (const p of this.opts.providers) {
       if (!p.cost) continue;
-      const c = costForUsage(p.cost, inputTokens, outputTokens, cacheReadTokens);
-      if (max === void 0 || c > max) max = c;
+      baseline = costForUsage(p.cost, inputTokens, outputTokens, cacheReadTokens);
     }
-    return max;
+    return baseline;
   }
   /** Winner settled: record the attempt, fire `onCost` (compat) + `onCall`. */
   finalizeOk(ctx, provider, attemptStart, usage, ttftMs) {
@@ -318,6 +327,7 @@ var LcrFallbackModel = class {
     const outputTokens = usage?.outputTokens?.total ?? 0;
     const cacheReadTokens = usage?.inputTokens?.cacheRead ?? 0;
     const costUsd = provider.cost ? costForUsage(provider.cost, inputTokens, outputTokens, cacheReadTokens) : 0;
+    const cachedSavingUsd = provider.cost ? cacheSavingForUsage(provider.cost, inputTokens, cacheReadTokens) : 0;
     const usageMissing = inputTokens === 0 && outputTokens === 0;
     this.emitCost({
       model: this.opts.modelName,
@@ -340,6 +350,7 @@ var LcrFallbackModel = class {
       ...cacheReadTokens > 0 ? { cachedInputTokens: cacheReadTokens } : {},
       costUsd,
       baselineUsd: this.baselineUsd(inputTokens, outputTokens, cacheReadTokens),
+      ...cachedSavingUsd > 0 ? { cachedSavingUsd } : {},
       ...ctx.requestId ? { requestId: ctx.requestId } : {},
       ...usageMissing ? { usageMissing: true } : {}
     });
@@ -569,6 +580,68 @@ function createHttpSink(options) {
   };
 }
 
+// src/media-official.ts
+var OFFICIAL_PRICES = {
+  "alibaba/qwen-image": { unit: "image", cents: 3.5 },
+  "alibaba/qwen-image-edit": { unit: "image", cents: 4.5 },
+  "alibaba/wan-2-2-i2v": { unit: "call", cents: 50 },
+  "alibaba/wan-2-2-t2v": { unit: "call", cents: 50 },
+  "alibaba/wan-2-5-i2v": { unit: "call", cents: 75 },
+  "alibaba/wan-2-5-t2v": { unit: "call", cents: 75 },
+  "alibaba/wan-2-7-image-pro": { unit: "image", cents: 7.5 },
+  "alibaba/wan-2-7-t2v": { unit: "call", cents: 75 },
+  "alibaba/z-image-turbo": { unit: "image", cents: 1.5 },
+  "bfl/flux-1.1-pro": { unit: "image", cents: 4 },
+  "bfl/flux-2-flex": { unit: "image", cents: 6 },
+  "bfl/flux-2-klein-4b": { unit: "image", cents: 1.4 },
+  "bfl/flux-2-klein-9b": { unit: "image", cents: 1.5 },
+  "bfl/flux-2-pro": { unit: "image", cents: 3 },
+  "bfl/flux-kontext-max": { unit: "image", cents: 8 },
+  "bfl/flux-kontext-pro": { unit: "image", cents: 4 },
+  "bria/rmbg-2": { unit: "image", cents: 1.8 },
+  "bytedance/seedance-2-0": { unit: "call", cents: 187 },
+  "bytedance/seedance-2-0-fast": { unit: "call", cents: 60 },
+  "bytedance/seedance-2-0-fast-i2v": { unit: "call", cents: 60 },
+  "bytedance/seedance-v1-pro": { unit: "call", cents: 61 },
+  "bytedance/seedance-v1-pro-i2v": { unit: "call", cents: 61 },
+  "bytedance/seedream-4-5": { unit: "image", cents: 3 },
+  "bytedance/seedream-5-lite": { unit: "image", cents: 3.5 },
+  "google/imagen-4-ultra": { unit: "image", cents: 6 },
+  "google/nano-banana": { unit: "image", cents: 3.9 },
+  "google/nano-banana-2": { unit: "image", cents: 6.7 },
+  "google/nano-banana-pro": { unit: "image", cents: 13.4 },
+  "google/veo-3-1": { unit: "call", cents: 200 },
+  "google/veo-3-1-lite": { unit: "call", cents: 40 },
+  "google/veo-3-quality": { unit: "call", cents: 200 },
+  "ideogram/v3-balanced": { unit: "image", cents: 6 },
+  "kuaishou/kling-image-3": { unit: "image", cents: 2.8 },
+  "kuaishou/kling-image-o3": { unit: "image", cents: 2.8 },
+  "kuaishou/kling-motion-control": { unit: "call", cents: 56 },
+  "kuaishou/kling-v21-master": { unit: "call", cents: 56 },
+  "kuaishou/kling-v21-master-i2v": { unit: "call", cents: 56 },
+  "kuaishou/kling-v26-pro-i2v": { unit: "call", cents: 56 },
+  "kuaishou/kling-v3-pro": { unit: "call", cents: 56 },
+  "kuaishou/kling-v3-pro-i2v": { unit: "call", cents: 56 },
+  "lightricks/ltx-2": { unit: "call", cents: 30 },
+  "lightricks/ltx-2-i2v": { unit: "call", cents: 30 },
+  "minimax/hailuo-02-pro": { unit: "call", cents: 53 },
+  "minimax/hailuo-02-standard": { unit: "call", cents: 27 },
+  "minimax/hailuo-2-3-pro": { unit: "call", cents: 53 },
+  "openai/gpt-image-1-5": { unit: "image", cents: 3.4 },
+  "openai/gpt-image-2": { unit: "image", cents: 5.3 },
+  "openai/gpt-image-2-high": { unit: "image", cents: 21.1 },
+  "openai/sora-2": { unit: "call", cents: 50 },
+  "openai/sora-2-i2v": { unit: "call", cents: 50 },
+  "pixverse/v5-5-i2v": { unit: "call", cents: 60 },
+  "pixverse/v6": { unit: "call", cents: 45 },
+  "recraft/v3": { unit: "image", cents: 4 },
+  "recraft/v4-1": { unit: "image", cents: 25 },
+  "runway/gen-4-image": { unit: "image", cents: 8 },
+  "stability/fast-sdxl": { unit: "image", cents: 0.9 },
+  "stability/stable-diffusion-3": { unit: "image", cents: 6.5 },
+  "xai/grok-image-quality": { unit: "image", cents: 7 }
+};
+
 // src/media.ts
 var DEFAULT_REFERENCE = {
   image: { width: 1920, height: 1080 },
@@ -620,7 +693,15 @@ function newMediaCallId() {
   return c?.randomUUID ? c.randomUUID() : `lcr_${Date.now().toString(36)}`;
 }
 function createMediaLCR(config) {
-  const { registry, adapters, reference = DEFAULT_REFERENCE, onError, onCost, onCall } = config;
+  const {
+    registry,
+    adapters,
+    reference = DEFAULT_REFERENCE,
+    officialPrices = OFFICIAL_PRICES,
+    onError,
+    onCost,
+    onCall
+  } = config;
   const safeError = (error, provider) => {
     try {
       onError?.(error, provider);
@@ -645,7 +726,8 @@ function createMediaLCR(config) {
       throw new Error(`ai-lcr: unknown media model "${modelId}" \u2014 add it to the registry`);
     }
     const ranked = rankRoutes(def, reference);
-    const baselineUsd = ranked.length > 0 ? Math.max(...ranked.map((r) => r.refCents)) / 100 : 0;
+    const official = def.official ?? officialPrices[modelId];
+    const baselineUsd = official !== void 0 ? normalizedCents(official, reference) / 100 : ranked.length > 0 ? Math.max(...ranked.map((r) => r.refCents)) / 100 : 0;
     const startedAt = Date.now();
     const attempts = [];
     let lastErr;
@@ -1130,6 +1212,7 @@ function createLCR(config) {
 0 && (module.exports = {
   DEFAULT_REFERENCE,
   MEDIA_PRICING,
+  OFFICIAL_PRICES,
   cheapestRoute,
   classifyError,
   classifyErrorKind,

package/dist/index.d.cts

@@ -109,12 +109,25 @@ interface CallRecord {
     /** Computed from the winner's `cost`; 0 if no price was given or the call failed. */
     costUsd: number;
     /**
-     * What the same request would have cost on the most expensive *priced*
-     * provider in the chain, on identical token usage — the savings baseline
-     * (`baselineUsd - costUsd`). Set by both routers whenever at least one
-     * provider carries a `cost`; undefined only when no provider was priced.
+     * What this same usage would have cost on the savings baseline, so
+     * `baselineUsd - costUsd` is what routing actually saved. Text router: the
+     * always-on fallback leg — the LAST priced provider in the chain, i.e. the
+     * list-price provider you'd fall back to without routing (e.g. OpenRouter).
+     * Media router: the model-maker's official direct price. NOT the most
+     * expensive leg of the chain: prompt caching can make a sticker-cheaper
+     * provider cost more on a cache-heavy call, and a max-of-chain baseline would
+     * fabricate a "saving" on calls the fallback itself served. Undefined only
+     * when no provider was priced.
      */
     baselineUsd?: number;
+    /**
+     * The slice of `costUsd` that prompt-cache reads saved versus paying the full
+     * input rate for those same tokens (`cachedTokens × (input − cacheRead)`).
+     * Present only when > 0. This is the serving provider's own caching benefit —
+     * it happens with or without routing — so it is NOT a routing saving and must
+     * be surfaced separately, never folded into `baselineUsd - costUsd`.
+     */
+    cachedSavingUsd?: number;
     /**
      * Caller-supplied correlation id, read from `providerOptions.lcr.requestId`
      * on the call. Multi-step tool loops emit one record per `doStream`/
@@ -264,6 +277,15 @@ interface MediaModelDef {
     modality: MediaModality;
     /** Providers that serve this model. Order is irrelevant — routing sorts by cost. */
     routes: MediaRoute[];
+    /**
+     * The model-maker's first-party list price — what a user pays going DIRECT,
+     * bypassing the cheaper providers we route to. When set, it's the savings
+     * baseline (savings = official − actual cost). Omit for open-weight models
+     * with no first-party API price; those fall back to the priciest configured
+     * route, or no baseline if there's only one. Can also be supplied out-of-band
+     * via {@link MediaLCRConfig.officialPrices} so a registry needn't carry it inline.
+     */
+    official?: MediaPricing;
 }
 type MediaRegistry = Record<string, MediaModelDef>;
 /**
@@ -347,6 +369,14 @@ interface MediaLCRConfig {
     /** Adapters keyed by provider. A route with no adapter is skipped. */
     adapters: Record<string, MediaAdapter>;
     reference?: ReferenceSpec;
+    /**
+     * Model-maker first-party list prices keyed by modelId — the savings baseline
+     * for a model whose registry def carries no inline `official` price. Lets a
+     * downstream registry (e.g. ai-art's) get correct baselines without inlining
+     * prices. Defaults to the bundled {@link OFFICIAL_PRICES} (lifted from the
+     * cross-provider price table). A def's inline `official` wins over this.
+     */
+    officialPrices?: Record<string, MediaPricing>;
     onError?: (error: Error, provider: string) => void;
     onCost?: (event: MediaCostEvent) => void;
     /**
@@ -387,6 +417,8 @@ declare function createMediaLCR(config: MediaLCRConfig): (modelId: string, input
 
 declare const MEDIA_PRICING: MediaRegistry;
 
+declare const OFFICIAL_PRICES: Record<string, MediaPricing>;
+
 /**
  * Kunavo media adapter — image (sync) + video (async poll).
  *
@@ -545,4 +577,4 @@ type LCRRouter = (modelName: string) => LanguageModelV3;
  */
 declare function createLCR(config: LCRConfig): LCRRouter;
 
-export { type CallRecord, type CostEvent, DEFAULT_REFERENCE, type ErrorKind, type FormatOptions, type HttpSinkOptions, type LCRConfig, type LCRRouter, MEDIA_PRICING, type MediaAdapter, type MediaCostEvent, type MediaGenerateRequest, type MediaGenerateResult, type MediaLCRConfig, type MediaModality, type MediaModelDef, type MediaOutput, type MediaPricing, type MediaRegistry, type MediaRoute, type MediaRunResult, type MediaUnit, type PriceComparisonRow, type ProviderCost, type ProviderEntry, type RankedRoute, type ReferenceSpec, type RouteAttempt, cheapestRoute, classifyError, classifyErrorKind, comparePrices, createFalMediaAdapter, createHttpSink, createKunavoMediaAdapter, createLCR, createMediaLCR, createRunwareMediaAdapter, formatCallRecord, normalizedCents, rankRoutes, referenceMegapixels };
+export { type CallRecord, type CostEvent, DEFAULT_REFERENCE, type ErrorKind, type FormatOptions, type HttpSinkOptions, type LCRConfig, type LCRRouter, MEDIA_PRICING, type MediaAdapter, type MediaCostEvent, type MediaGenerateRequest, type MediaGenerateResult, type MediaLCRConfig, type MediaModality, type MediaModelDef, type MediaOutput, type MediaPricing, type MediaRegistry, type MediaRoute, type MediaRunResult, type MediaUnit, OFFICIAL_PRICES, type PriceComparisonRow, type ProviderCost, type ProviderEntry, type RankedRoute, type ReferenceSpec, type RouteAttempt, cheapestRoute, classifyError, classifyErrorKind, comparePrices, createFalMediaAdapter, createHttpSink, createKunavoMediaAdapter, createLCR, createMediaLCR, createRunwareMediaAdapter, formatCallRecord, normalizedCents, rankRoutes, referenceMegapixels };

package/dist/index.d.ts

@@ -109,12 +109,25 @@ interface CallRecord {
     /** Computed from the winner's `cost`; 0 if no price was given or the call failed. */
     costUsd: number;
     /**
-     * What the same request would have cost on the most expensive *priced*
-     * provider in the chain, on identical token usage — the savings baseline
-     * (`baselineUsd - costUsd`). Set by both routers whenever at least one
-     * provider carries a `cost`; undefined only when no provider was priced.
+     * What this same usage would have cost on the savings baseline, so
+     * `baselineUsd - costUsd` is what routing actually saved. Text router: the
+     * always-on fallback leg — the LAST priced provider in the chain, i.e. the
+     * list-price provider you'd fall back to without routing (e.g. OpenRouter).
+     * Media router: the model-maker's official direct price. NOT the most
+     * expensive leg of the chain: prompt caching can make a sticker-cheaper
+     * provider cost more on a cache-heavy call, and a max-of-chain baseline would
+     * fabricate a "saving" on calls the fallback itself served. Undefined only
+     * when no provider was priced.
      */
     baselineUsd?: number;
+    /**
+     * The slice of `costUsd` that prompt-cache reads saved versus paying the full
+     * input rate for those same tokens (`cachedTokens × (input − cacheRead)`).
+     * Present only when > 0. This is the serving provider's own caching benefit —
+     * it happens with or without routing — so it is NOT a routing saving and must
+     * be surfaced separately, never folded into `baselineUsd - costUsd`.
+     */
+    cachedSavingUsd?: number;
     /**
      * Caller-supplied correlation id, read from `providerOptions.lcr.requestId`
      * on the call. Multi-step tool loops emit one record per `doStream`/
@@ -264,6 +277,15 @@ interface MediaModelDef {
     modality: MediaModality;
     /** Providers that serve this model. Order is irrelevant — routing sorts by cost. */
     routes: MediaRoute[];
+    /**
+     * The model-maker's first-party list price — what a user pays going DIRECT,
+     * bypassing the cheaper providers we route to. When set, it's the savings
+     * baseline (savings = official − actual cost). Omit for open-weight models
+     * with no first-party API price; those fall back to the priciest configured
+     * route, or no baseline if there's only one. Can also be supplied out-of-band
+     * via {@link MediaLCRConfig.officialPrices} so a registry needn't carry it inline.
+     */
+    official?: MediaPricing;
 }
 type MediaRegistry = Record<string, MediaModelDef>;
 /**
@@ -347,6 +369,14 @@ interface MediaLCRConfig {
     /** Adapters keyed by provider. A route with no adapter is skipped. */
     adapters: Record<string, MediaAdapter>;
     reference?: ReferenceSpec;
+    /**
+     * Model-maker first-party list prices keyed by modelId — the savings baseline
+     * for a model whose registry def carries no inline `official` price. Lets a
+     * downstream registry (e.g. ai-art's) get correct baselines without inlining
+     * prices. Defaults to the bundled {@link OFFICIAL_PRICES} (lifted from the
+     * cross-provider price table). A def's inline `official` wins over this.
+     */
+    officialPrices?: Record<string, MediaPricing>;
     onError?: (error: Error, provider: string) => void;
     onCost?: (event: MediaCostEvent) => void;
     /**
@@ -387,6 +417,8 @@ declare function createMediaLCR(config: MediaLCRConfig): (modelId: string, input
 
 declare const MEDIA_PRICING: MediaRegistry;
 
+declare const OFFICIAL_PRICES: Record<string, MediaPricing>;
+
 /**
  * Kunavo media adapter — image (sync) + video (async poll).
  *
@@ -545,4 +577,4 @@ type LCRRouter = (modelName: string) => LanguageModelV3;
  */
 declare function createLCR(config: LCRConfig): LCRRouter;
 
-export { type CallRecord, type CostEvent, DEFAULT_REFERENCE, type ErrorKind, type FormatOptions, type HttpSinkOptions, type LCRConfig, type LCRRouter, MEDIA_PRICING, type MediaAdapter, type MediaCostEvent, type MediaGenerateRequest, type MediaGenerateResult, type MediaLCRConfig, type MediaModality, type MediaModelDef, type MediaOutput, type MediaPricing, type MediaRegistry, type MediaRoute, type MediaRunResult, type MediaUnit, type PriceComparisonRow, type ProviderCost, type ProviderEntry, type RankedRoute, type ReferenceSpec, type RouteAttempt, cheapestRoute, classifyError, classifyErrorKind, comparePrices, createFalMediaAdapter, createHttpSink, createKunavoMediaAdapter, createLCR, createMediaLCR, createRunwareMediaAdapter, formatCallRecord, normalizedCents, rankRoutes, referenceMegapixels };
+export { type CallRecord, type CostEvent, DEFAULT_REFERENCE, type ErrorKind, type FormatOptions, type HttpSinkOptions, type LCRConfig, type LCRRouter, MEDIA_PRICING, type MediaAdapter, type MediaCostEvent, type MediaGenerateRequest, type MediaGenerateResult, type MediaLCRConfig, type MediaModality, type MediaModelDef, type MediaOutput, type MediaPricing, type MediaRegistry, type MediaRoute, type MediaRunResult, type MediaUnit, OFFICIAL_PRICES, type PriceComparisonRow, type ProviderCost, type ProviderEntry, type RankedRoute, type ReferenceSpec, type RouteAttempt, cheapestRoute, classifyError, classifyErrorKind, comparePrices, createFalMediaAdapter, createHttpSink, createKunavoMediaAdapter, createLCR, createMediaLCR, createRunwareMediaAdapter, formatCallRecord, normalizedCents, rankRoutes, referenceMegapixels };

package/dist/index.js

@@ -152,6 +152,11 @@ function costForUsage(cost, inputTokens, outputTokens, cacheReadTokens) {
   const cachedRate = cost.cacheRead ?? cost.input;
   return fullInput / 1e6 * cost.input + cached / 1e6 * cachedRate + outputTokens / 1e6 * cost.output;
 }
+function cacheSavingForUsage(cost, inputTokens, cacheReadTokens) {
+  if (cost.cacheRead === void 0) return 0;
+  const cached = Math.min(Math.max(cacheReadTokens, 0), inputTokens);
+  return cached / 1e6 * (cost.input - cost.cacheRead);
+}
 function requestIdFrom(options) {
   const raw = options.providerOptions?.lcr?.requestId;
   return typeof raw === "string" && raw.length > 0 ? raw : void 0;
@@ -256,19 +261,22 @@ var LcrFallbackModel = class {
     });
   }
   /**
-   * Baseline = what this same usage would have cost on the most expensive
-   * *priced* provider in the chain (typically the OpenRouter fallback leg). The
-   * winner's savings is `baselineUsd - costUsd`. Undefined when no provider in
-   * the chain carries a price (nothing to compare against).
+   * Baseline = what this same usage would have cost on the always-on fallback:
+   * the LAST priced leg of the chain (by convention the list-price provider you'd
+   * use without routing — e.g. OpenRouter, always last). The winner's saving is
+   * `baselineUsd - costUsd`. We take the last priced leg, NOT the most expensive
+   * one: prompt caching can make a sticker-cheaper provider (no `cacheRead`) cost
+   * MORE on a cache-heavy call, and a max-of-chain baseline would then fabricate a
+   * "saving" even on calls the fallback itself served. Undefined when no provider
+   * in the chain carries a price (nothing to compare against).
    */
   baselineUsd(inputTokens, outputTokens, cacheReadTokens) {
-    let max;
+    let baseline;
     for (const p of this.opts.providers) {
       if (!p.cost) continue;
-      const c = costForUsage(p.cost, inputTokens, outputTokens, cacheReadTokens);
-      if (max === void 0 || c > max) max = c;
+      baseline = costForUsage(p.cost, inputTokens, outputTokens, cacheReadTokens);
     }
-    return max;
+    return baseline;
   }
   /** Winner settled: record the attempt, fire `onCost` (compat) + `onCall`. */
   finalizeOk(ctx, provider, attemptStart, usage, ttftMs) {
@@ -277,6 +285,7 @@ var LcrFallbackModel = class {
     const outputTokens = usage?.outputTokens?.total ?? 0;
     const cacheReadTokens = usage?.inputTokens?.cacheRead ?? 0;
     const costUsd = provider.cost ? costForUsage(provider.cost, inputTokens, outputTokens, cacheReadTokens) : 0;
+    const cachedSavingUsd = provider.cost ? cacheSavingForUsage(provider.cost, inputTokens, cacheReadTokens) : 0;
     const usageMissing = inputTokens === 0 && outputTokens === 0;
     this.emitCost({
       model: this.opts.modelName,
@@ -299,6 +308,7 @@ var LcrFallbackModel = class {
       ...cacheReadTokens > 0 ? { cachedInputTokens: cacheReadTokens } : {},
       costUsd,
       baselineUsd: this.baselineUsd(inputTokens, outputTokens, cacheReadTokens),
+      ...cachedSavingUsd > 0 ? { cachedSavingUsd } : {},
       ...ctx.requestId ? { requestId: ctx.requestId } : {},
       ...usageMissing ? { usageMissing: true } : {}
     });
@@ -528,6 +538,68 @@ function createHttpSink(options) {
   };
 }
 
+// src/media-official.ts
+var OFFICIAL_PRICES = {
+  "alibaba/qwen-image": { unit: "image", cents: 3.5 },
+  "alibaba/qwen-image-edit": { unit: "image", cents: 4.5 },
+  "alibaba/wan-2-2-i2v": { unit: "call", cents: 50 },
+  "alibaba/wan-2-2-t2v": { unit: "call", cents: 50 },
+  "alibaba/wan-2-5-i2v": { unit: "call", cents: 75 },
+  "alibaba/wan-2-5-t2v": { unit: "call", cents: 75 },
+  "alibaba/wan-2-7-image-pro": { unit: "image", cents: 7.5 },
+  "alibaba/wan-2-7-t2v": { unit: "call", cents: 75 },
+  "alibaba/z-image-turbo": { unit: "image", cents: 1.5 },
+  "bfl/flux-1.1-pro": { unit: "image", cents: 4 },
+  "bfl/flux-2-flex": { unit: "image", cents: 6 },
+  "bfl/flux-2-klein-4b": { unit: "image", cents: 1.4 },
+  "bfl/flux-2-klein-9b": { unit: "image", cents: 1.5 },
+  "bfl/flux-2-pro": { unit: "image", cents: 3 },
+  "bfl/flux-kontext-max": { unit: "image", cents: 8 },
+  "bfl/flux-kontext-pro": { unit: "image", cents: 4 },
+  "bria/rmbg-2": { unit: "image", cents: 1.8 },
+  "bytedance/seedance-2-0": { unit: "call", cents: 187 },
+  "bytedance/seedance-2-0-fast": { unit: "call", cents: 60 },
+  "bytedance/seedance-2-0-fast-i2v": { unit: "call", cents: 60 },
+  "bytedance/seedance-v1-pro": { unit: "call", cents: 61 },
+  "bytedance/seedance-v1-pro-i2v": { unit: "call", cents: 61 },
+  "bytedance/seedream-4-5": { unit: "image", cents: 3 },
+  "bytedance/seedream-5-lite": { unit: "image", cents: 3.5 },
+  "google/imagen-4-ultra": { unit: "image", cents: 6 },
+  "google/nano-banana": { unit: "image", cents: 3.9 },
+  "google/nano-banana-2": { unit: "image", cents: 6.7 },
+  "google/nano-banana-pro": { unit: "image", cents: 13.4 },
+  "google/veo-3-1": { unit: "call", cents: 200 },
+  "google/veo-3-1-lite": { unit: "call", cents: 40 },
+  "google/veo-3-quality": { unit: "call", cents: 200 },
+  "ideogram/v3-balanced": { unit: "image", cents: 6 },
+  "kuaishou/kling-image-3": { unit: "image", cents: 2.8 },
+  "kuaishou/kling-image-o3": { unit: "image", cents: 2.8 },
+  "kuaishou/kling-motion-control": { unit: "call", cents: 56 },
+  "kuaishou/kling-v21-master": { unit: "call", cents: 56 },
+  "kuaishou/kling-v21-master-i2v": { unit: "call", cents: 56 },
+  "kuaishou/kling-v26-pro-i2v": { unit: "call", cents: 56 },
+  "kuaishou/kling-v3-pro": { unit: "call", cents: 56 },
+  "kuaishou/kling-v3-pro-i2v": { unit: "call", cents: 56 },
+  "lightricks/ltx-2": { unit: "call", cents: 30 },
+  "lightricks/ltx-2-i2v": { unit: "call", cents: 30 },
+  "minimax/hailuo-02-pro": { unit: "call", cents: 53 },
+  "minimax/hailuo-02-standard": { unit: "call", cents: 27 },
+  "minimax/hailuo-2-3-pro": { unit: "call", cents: 53 },
+  "openai/gpt-image-1-5": { unit: "image", cents: 3.4 },
+  "openai/gpt-image-2": { unit: "image", cents: 5.3 },
+  "openai/gpt-image-2-high": { unit: "image", cents: 21.1 },
+  "openai/sora-2": { unit: "call", cents: 50 },
+  "openai/sora-2-i2v": { unit: "call", cents: 50 },
+  "pixverse/v5-5-i2v": { unit: "call", cents: 60 },
+  "pixverse/v6": { unit: "call", cents: 45 },
+  "recraft/v3": { unit: "image", cents: 4 },
+  "recraft/v4-1": { unit: "image", cents: 25 },
+  "runway/gen-4-image": { unit: "image", cents: 8 },
+  "stability/fast-sdxl": { unit: "image", cents: 0.9 },
+  "stability/stable-diffusion-3": { unit: "image", cents: 6.5 },
+  "xai/grok-image-quality": { unit: "image", cents: 7 }
+};
+
 // src/media.ts
 var DEFAULT_REFERENCE = {
   image: { width: 1920, height: 1080 },
@@ -579,7 +651,15 @@ function newMediaCallId() {
   return c?.randomUUID ? c.randomUUID() : `lcr_${Date.now().toString(36)}`;
 }
 function createMediaLCR(config) {
-  const { registry, adapters, reference = DEFAULT_REFERENCE, onError, onCost, onCall } = config;
+  const {
+    registry,
+    adapters,
+    reference = DEFAULT_REFERENCE,
+    officialPrices = OFFICIAL_PRICES,
+    onError,
+    onCost,
+    onCall
+  } = config;
   const safeError = (error, provider) => {
     try {
       onError?.(error, provider);
@@ -604,7 +684,8 @@ function createMediaLCR(config) {
       throw new Error(`ai-lcr: unknown media model "${modelId}" \u2014 add it to the registry`);
     }
     const ranked = rankRoutes(def, reference);
-    const baselineUsd = ranked.length > 0 ? Math.max(...ranked.map((r) => r.refCents)) / 100 : 0;
+    const official = def.official ?? officialPrices[modelId];
+    const baselineUsd = official !== void 0 ? normalizedCents(official, reference) / 100 : ranked.length > 0 ? Math.max(...ranked.map((r) => r.refCents)) / 100 : 0;
     const startedAt = Date.now();
     const attempts = [];
     let lastErr;
@@ -1088,6 +1169,7 @@ function createLCR(config) {
 export {
   DEFAULT_REFERENCE,
   MEDIA_PRICING,
+  OFFICIAL_PRICES,
   cheapestRoute,
   classifyError,
   classifyErrorKind,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-lcr",
-  "version": "0.4.0",
+  "version": "0.5.1",
   "description": "Least Cost Routing for LLMs — route every model call to the cheapest available provider, fall back automatically, and track real cost. Built for the Vercel AI SDK.",
   "keywords": [
     "ai",