xintaofei · Adam-Dalloul · Aug 16, 2026
diff --git a/src-tauri/src/acp/opencode_catalog.rs b/src-tauri/src/acp/opencode_catalog.rs
@@ -53,6 +53,10 @@ pub struct CatalogModel {
     pub cost_in: Option<f64>,
     #[serde(default)]
     pub cost_out: Option<f64>,
+    #[serde(default)]
+    pub cost_cache_read: Option<f64>,
+    #[serde(default)]
+    pub cost_cache_write: Option<f64>,
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -149,6 +153,14 @@ pub fn normalize_models_dev(raw: &str) -> Result<Vec<CatalogProvider>, AppComman
                         .get("cost")
                         .and_then(|v| v.get("output"))
                         .and_then(|v| v.as_f64()),
+                    cost_cache_read: m
+                        .get("cost")
+                        .and_then(|v| v.get("cache_read"))
+                        .and_then(|v| v.as_f64()),
+                    cost_cache_write: m
+                        .get("cost")
+                        .and_then(|v| v.get("cache_write"))
+                        .and_then(|v| v.as_f64()),
                 });
             }
         }
@@ -181,7 +193,13 @@ pub fn bundled_catalog() -> Vec<CatalogProvider> {
 }
 
 fn cache_path(data_dir: &Path) -> PathBuf {
-    data_dir.join("cache").join("opencode").join("models-dev.json")
+    // v2: cache_read / cache_write joined the slim shape. A new filename so
+    // an existing 24h cache is not served without those fields until it ages
+    // out, which would leave cache tokens unpriced on Token Usage.
+    data_dir
+        .join("cache")
+        .join("opencode")
+        .join("models-dev-v2.json")
 }
 
 fn read_cache(data_dir: &Path, require_fresh: bool) -> Option<Vec<CatalogProvider>> {
@@ -303,7 +321,17 @@ mod tests {
                         "reasoning": true,
                         "tool_call": true,
                         "limit": { "context": 128000, "output": 8192 },
-                        "cost": { "input": 1.5, "output": 6.0 }
+                        "cost": {
+                            "input": 1.5,
+                            "output": 6.0,
+                            "cache_read": 0.15,
+                            "cache_write": 1.875
+                        }
+                    },
+                    "demo-free": {
+                        "id": "demo-free",
+                        "name": "Demo Free",
+                        "cost": { "input": 0.0, "output": 0.0 }
                     }
                 }
             }
@@ -316,14 +344,27 @@ mod tests {
         assert_eq!(p.npm.as_deref(), Some("@ai-sdk/openai-compatible"));
         assert_eq!(p.env, vec!["DEMO_API_KEY".to_string()]);
         assert_eq!(p.auth_kind, "api");
-        assert_eq!(p.models.len(), 1);
-        let m = &p.models[0];
-        assert_eq!(m.id, "demo-large");
+        assert_eq!(p.models.len(), 2);
+        let m = p
+            .models
+            .iter()
+            .find(|m| m.id == "demo-large")
+            .expect("demo-large");
         assert!(m.reasoning);
         assert!(m.tool_call);
         assert_eq!(m.context, Some(128000));
         assert_eq!(m.cost_in, Some(1.5));
         assert_eq!(m.cost_out, Some(6.0));
+        assert_eq!(m.cost_cache_read, Some(0.15));
+        assert_eq!(m.cost_cache_write, Some(1.875));
+        let free = p
+            .models
+            .iter()
+            .find(|m| m.id == "demo-free")
+            .expect("demo-free");
+        assert_eq!(free.cost_in, Some(0.0));
+        assert_eq!(free.cost_cache_read, None);
+        assert_eq!(free.cost_cache_write, None);
     }
 
     #[test]

diff --git a/src/components/token-usage/token-usage-page.tsx b/src/components/token-usage/token-usage-page.tsx
@@ -45,6 +45,7 @@ import { WorkbenchPageTitle } from "@/components/workbench/workbench-page-title"
 import { FolderAliasLabel } from "@/components/conversations/folder-alias-label"
 import { formatFolderLabelWithAlias } from "@/lib/folder-display"
 import {
+  opencodeProviderCatalog,
   tokenUsageFacets,
   tokenUsageReport,
   tokenUsageStatus,
@@ -65,6 +66,7 @@ import {
   foldBreakdown,
   formatDuration,
   formatTokensPrecise,
+  formatUsd,
   freshTokens,
   idleDays,
   localTzOffsetMinutes,
@@ -75,9 +77,16 @@ import {
   suggestBucket,
   type TokenUsageRangePreset,
 } from "@/lib/token-usage"
+import {
+  buildRateIndex,
+  estimateItemCost,
+  estimateReportCost,
+  resolveRate,
+} from "@/lib/model-api-rates"
 import { cn } from "@/lib/utils"
 import type {
   AgentType,
+  OpenCodeCatalogProvider,
   TokenUsageBucket,
   TokenUsageFacets,
   TokenUsageReport,
@@ -328,6 +337,7 @@ export function TokenUsagePage() {
   const [facets, setFacets] = useState<TokenUsageFacets | null>(null)
   const [status, setStatus] = useState<TokenUsageSyncStatus | null>(null)
   const [report, setReport] = useState<TokenUsageReport | null>(null)
+  const [catalog, setCatalog] = useState<OpenCodeCatalogProvider[] | null>(null)
   const [loading, setLoading] = useState(true)
   const [error, setError] = useState<string | null>(null)
   const [syncing, setSyncing] = useState(false)
@@ -432,6 +442,23 @@ export function TokenUsagePage() {
     void load()
   }, [load])
 
+  // Independent of the usage report: the same 24h models.dev catalog the
+  // OpenCode settings page already loads. Failures stay quiet and hide the
+  // dollar line instead of blocking the token counts.
+  useEffect(() => {
+    let cancelled = false
+    void opencodeProviderCatalog()
+      .then((list) => {
+        if (!cancelled) setCatalog(list)
+      })
+      .catch(() => {
+        if (!cancelled) setCatalog([])
+      })
+    return () => {
+      cancelled = true
+    }
+  }, [])
+
   // Latest-ref so the event subscription below is set up once, not torn down
   // and re-established on every filter change (`load`'s identity tracks the
   // filters). Same idiom as tasks-view-context.
@@ -561,6 +588,15 @@ export function TokenUsagePage() {
 
   const totals = report?.totals
   const cache = totals ? cacheHitRate(totals) : null
+  const rateIndex = useMemo(
+    () => (catalog && catalog.length > 0 ? buildRateIndex(catalog) : null),
+    [catalog]
+  )
+  const apiEstimate = useMemo(() => {
+    if (!report || !rateIndex) return null
+    const estimate = estimateReportCost(report.by_model, rateIndex)
+    return estimate.coverage > 0 && estimate.usd > 0 ? estimate : null
+  }, [report, rateIndex])
   const heat = useMemo(
     () => buildHeatMatrix(report?.heatmap ?? []),
     [report?.heatmap]
@@ -687,13 +723,23 @@ export function TokenUsagePage() {
     const { shown, other } = foldBreakdown(breakdownItems, BREAKDOWN_LIMIT)
     const share = (v: number) =>
       totals.total_tokens > 0 ? v / totals.total_tokens : null
-    const rows: RankedDatum[] = shown.map((it) => ({
-      key: it.key,
-      label: breakdownLabel(it.key, it.label),
-      value: it.total_tokens,
-      share: share(it.total_tokens),
-      hint: t("sessionsCount", { count: it.conversation_count }),
-    }))
+    const rows: RankedDatum[] = shown.map((it) => {
+      const sessions = t("sessionsCount", { count: it.conversation_count })
+      let hint = sessions
+      if (dim === "model" && rateIndex) {
+        const cost = estimateItemCost(it, resolveRate(rateIndex, it.key))
+        if (cost.usd != null && cost.usd > 0) {
+          hint = `${sessions} · ${formatUsd(cost.usd)}`
+        }
+      }
+      return {
+        key: it.key,
+        label: breakdownLabel(it.key, it.label),
+        value: it.total_tokens,
+        share: share(it.total_tokens),
+        hint,
+      }
+    })
     if (other) {
       rows.push({
         key: other.key,
@@ -705,7 +751,7 @@ export function TokenUsagePage() {
       })
     }
     return rows
-  }, [breakdownItems, breakdownLabel, totals, t])
+  }, [breakdownItems, breakdownLabel, totals, t, dim, rateIndex])
 
   const onBreakdownSelect = useCallback(
     (key: string) => {
@@ -1106,6 +1152,22 @@ export function TokenUsagePage() {
                                 />
                               )}
                             </div>
+                            {apiEstimate && (
+                              <div className="mt-2 text-sm text-muted-foreground">
+                                <span title={t("apiListEstimateHint")}>
+                                  {apiEstimate.coverage < 0.99
+                                    ? t("apiListEstimatePartial", {
+                                        amount: formatUsd(apiEstimate.usd),
+                                        percent: Math.floor(
+                                          apiEstimate.coverage * 100
+                                        ),
+                                      })
+                                    : t("apiListEstimate", {
+                                        amount: formatUsd(apiEstimate.usd),
+                                      })}
+                                </span>
+                              </div>
+                            )}
                             {archetype && totals.total_tokens > 0 && (
                               // The outer wrapper owns the spacing: mt-auto pins
                               // the strip to the card's bottom edge on wide

diff --git a/src/i18n/messages/ar.json b/src/i18n/messages/ar.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "يقرأ codeg أعداد الرموز مباشرة من سجل كل وكيل. حدّث لتُحسب الجلسات الموجودة على هذا الجهاز.",
     "emptyAction": "احسب جلساتي",
     "loadFailed": "تعذّر تحميل بيانات الاستهلاك",
-    "truncatedNotice": "هذا النطاق واسع جدًا — الأرقام تغطي أحدث جزء منه فقط."
+    "truncatedNotice": "هذا النطاق واسع جدًا — الأرقام تغطي أحدث جزء منه فقط.",
+    "apiListEstimate": "≈ {amount} قائمة API",
+    "apiListEstimatePartial": "≈ {amount} قائمة API · {percent}٪ من الرموز",
+    "apiListEstimateHint": "أسعار قائمة API العامة من models.dev، وتشمل قراءة وكتابة الذاكرة المؤقتة. خطط الاشتراك تُحاسب بشكل مختلف."
   }
 }
diff --git a/src/i18n/messages/de.json b/src/i18n/messages/de.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "Codeg liest die Token-Zahlen direkt aus dem Protokoll jedes Agenten. Aktualisiere, um zu zählen, was schon auf diesem Rechner liegt.",
     "emptyAction": "Meine Sitzungen zählen",
     "loadFailed": "Verbrauch konnte nicht geladen werden",
-    "truncatedNotice": "Dieser Zeitraum ist sehr groß — die Zahlen decken nur seinen jüngsten Abschnitt ab."
+    "truncatedNotice": "Dieser Zeitraum ist sehr groß — die Zahlen decken nur seinen jüngsten Abschnitt ab.",
+    "apiListEstimate": "≈ {amount} API-Liste",
+    "apiListEstimatePartial": "≈ {amount} API-Liste · {percent}% der Tokens",
+    "apiListEstimateHint": "Öffentliche API-Listenpreise von models.dev, inklusive Cache-Lesen und -Schreiben. Abo-Tarife rechnen anders ab."
   }
 }
diff --git a/src/i18n/messages/en.json b/src/i18n/messages/en.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "Codeg reads token counts straight from each agent's own transcript. Run a refresh to count what's already on this machine.",
     "emptyAction": "Count my sessions",
     "loadFailed": "Could not load usage",
-    "truncatedNotice": "This range is very large — the numbers cover only the most recent slice of it."
+    "truncatedNotice": "This range is very large — the numbers cover only the most recent slice of it.",
+    "apiListEstimate": "≈ {amount} API list",
+    "apiListEstimatePartial": "≈ {amount} API list · {percent}% of tokens",
+    "apiListEstimateHint": "Public API list rates from models.dev, including cache reads and writes. Subscription plans bill differently."
   }
 }
diff --git a/src/i18n/messages/es.json b/src/i18n/messages/es.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "Codeg lee los tokens directamente de la transcripción de cada agente. Actualiza para contabilizar lo que ya hay en esta máquina.",
     "emptyAction": "Contabilizar mis sesiones",
     "loadFailed": "No se pudo cargar el uso",
-    "truncatedNotice": "Este periodo es muy amplio: las cifras cubren solo su tramo más reciente."
+    "truncatedNotice": "Este periodo es muy amplio: las cifras cubren solo su tramo más reciente.",
+    "apiListEstimate": "≈ {amount} tarifa API",
+    "apiListEstimatePartial": "≈ {amount} tarifa API · {percent}% de tokens",
+    "apiListEstimateHint": "Tarifas públicas de API de models.dev, con lecturas y escrituras de caché. Los planes de suscripción facturan distinto."
   }
 }
diff --git a/src/i18n/messages/fr.json b/src/i18n/messages/fr.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "Codeg lit les tokens directement dans la transcription de chaque agent. Actualisez pour compter ce qui est déjà sur cette machine.",
     "emptyAction": "Compter mes sessions",
     "loadFailed": "Impossible de charger la consommation",
-    "truncatedNotice": "Cette période est très large — les chiffres ne couvrent que sa portion la plus récente."
+    "truncatedNotice": "Cette période est très large — les chiffres ne couvrent que sa portion la plus récente.",
+    "apiListEstimate": "≈ {amount} tarif API",
+    "apiListEstimatePartial": "≈ {amount} tarif API · {percent}% des jetons",
+    "apiListEstimateHint": "Tarifs publics API issus de models.dev, lectures et écritures de cache comprises. Les abonnements facturent autrement."
   }
 }
diff --git a/src/i18n/messages/ja.json b/src/i18n/messages/ja.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "codeg は各エージェント自身のセッション記録から直接トークン数を読み取ります。更新すると、このマシンにある記録を集計します。",
     "emptyAction": "セッションを集計",
     "loadFailed": "使用量を読み込めませんでした",
-    "truncatedNotice": "期間が非常に長いため、表示中の数値は直近の一部のみを対象としています。"
+    "truncatedNotice": "期間が非常に長いため、表示中の数値は直近の一部のみを対象としています。",
+    "apiListEstimate": "≈ {amount} APIリスト",
+    "apiListEstimatePartial": "≈ {amount} APIリスト · トークンの {percent}%",
+    "apiListEstimateHint": "models.dev の公開 API リスト料金です。キャッシュの読み書きを含みます。サブスクリプションの課金とは異なります。"
   }
 }
diff --git a/src/i18n/messages/ko.json b/src/i18n/messages/ko.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "codeg는 각 에이전트의 세션 기록에서 토큰 수를 직접 읽습니다. 새로 고침하면 이 컴퓨터에 있는 기록을 집계합니다.",
     "emptyAction": "내 세션 집계",
     "loadFailed": "사용량을 불러오지 못했습니다",
-    "truncatedNotice": "기간이 매우 길어 표시된 수치는 가장 최근 구간만 반영합니다."
+    "truncatedNotice": "기간이 매우 길어 표시된 수치는 가장 최근 구간만 반영합니다.",
+    "apiListEstimate": "≈ {amount} API 정가",
+    "apiListEstimatePartial": "≈ {amount} API 정가 · 토큰 {percent}%",
+    "apiListEstimateHint": "models.dev의 공개 API 정가이며 캐시 읽기/쓰기를 포함합니다. 구독 요금과는 다릅니다."
   }
 }
diff --git a/src/i18n/messages/pt.json b/src/i18n/messages/pt.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "O codeg lê os tokens direto da transcrição de cada agente. Atualize para contabilizar o que já existe nesta máquina.",
     "emptyAction": "Contabilizar minhas sessões",
     "loadFailed": "Não foi possível carregar o uso",
-    "truncatedNotice": "Este período é muito amplo — os números cobrem apenas o trecho mais recente."
+    "truncatedNotice": "Este período é muito amplo — os números cobrem apenas o trecho mais recente.",
+    "apiListEstimate": "≈ {amount} lista da API",
+    "apiListEstimatePartial": "≈ {amount} lista da API · {percent}% dos tokens",
+    "apiListEstimateHint": "Preços públicos da API em models.dev, incluindo leituras e escritas de cache. Planos de assinatura cobram diferente."
   }
 }
diff --git a/src/i18n/messages/zh-CN.json b/src/i18n/messages/zh-CN.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "codeg 直接从各智能体自己的会话记录里读取 Token 数。点一下刷新，把本机已有的会话统计进来。",
     "emptyAction": "统计我的会话",
     "loadFailed": "用量加载失败",
-    "truncatedNotice": "该范围过大 —— 下面的数字只覆盖了其中最近的一段。"
+    "truncatedNotice": "该范围过大 —— 下面的数字只覆盖了其中最近的一段。",
+    "apiListEstimate": "≈ {amount} API 标价",
+    "apiListEstimatePartial": "≈ {amount} API 标价 · {percent}% 的 token",
+    "apiListEstimateHint": "来自 models.dev 的公开 API 标价，含缓存读写。订阅套餐的计费方式不同。"
   }
 }
diff --git a/src/i18n/messages/zh-TW.json b/src/i18n/messages/zh-TW.json
@@ -4951,6 +4951,9 @@
     "emptyHint": "codeg 直接從各智慧代理自己的工作階段紀錄讀取 Token 數。點一下重新整理，把本機已有的紀錄統計進來。",
     "emptyAction": "統計我的工作階段",
     "loadFailed": "用量載入失敗",
-    "truncatedNotice": "此範圍過大 —— 下面的數字只涵蓋其中最近的一段。"
+    "truncatedNotice": "此範圍過大 —— 下面的數字只涵蓋其中最近的一段。",
+    "apiListEstimate": "≈ {amount} API 標價",
+    "apiListEstimatePartial": "≈ {amount} API 標價 · {percent}% 的 token",
+    "apiListEstimateHint": "來自 models.dev 的公開 API 標價，含快取讀寫。訂閱方案的計費方式不同。"
   }
 }