diff --git a/src/cost-tracker.ts b/src/cost-tracker.ts
index b03184c6..56920c5a 100644
--- a/src/cost-tracker.ts
+++ b/src/cost-tracker.ts
@@ -181,7 +181,7 @@ function formatCost(cost: number, maxDecimalPlaces: number = 4): string {
 function formatModelUsage(): string {
   const modelUsageMap = getModelUsage()
   if (Object.keys(modelUsageMap).length === 0) {
-    return 'Usage:                 0 input, 0 output, 0 cache read, 0 cache write'
+    return 'Usage:                 0 input, 0 output'
   }
 
   // Accumulate usage by short name
@@ -211,15 +211,19 @@ function formatModelUsage(): string {
 
   let result = 'Usage by model:'
   for (const [shortName, usage] of Object.entries(usageByShortName)) {
-    const usageString =
+    let usageString =
       `  ${formatNumber(usage.inputTokens)} input, ` +
-      `${formatNumber(usage.outputTokens)} output, ` +
-      `${formatNumber(usage.cacheReadInputTokens)} cache read, ` +
-      `${formatNumber(usage.cacheCreationInputTokens)} cache write` +
-      (usage.webSearchRequests > 0
-        ? `, ${formatNumber(usage.webSearchRequests)} web search`
-        : '') +
-      ` (${formatCost(usage.costUSD)})`
+      `${formatNumber(usage.outputTokens)} output`
+    if (usage.cacheReadInputTokens > 0) {
+      usageString += `, ${formatNumber(usage.cacheReadInputTokens)} cache read`
+    }
+    if (usage.cacheCreationInputTokens > 0) {
+      usageString += `, ${formatNumber(usage.cacheCreationInputTokens)} cache write`
+    }
+    if (usage.webSearchRequests > 0) {
+      usageString += `, ${formatNumber(usage.webSearchRequests)} web search`
+    }
+    usageString += ` (${formatCost(usage.costUSD)})`
     result += `\n` + `${shortName}:`.padStart(21) + usageString
   }
   return result
diff --git a/src/services/api/codexShim.ts b/src/services/api/codexShim.ts
index 4b7260e7..4c823a3d 100644
--- a/src/services/api/codexShim.ts
+++ b/src/services/api/codexShim.ts
@@ -80,12 +80,17 @@ type CodexSseEvent = {
 function makeUsage(usage?: {
   input_tokens?: number
   output_tokens?: number
+  input_tokens_details?: { cached_tokens?: number }
+  prompt_tokens_details?: { cached_tokens?: number }
 }): AnthropicUsage {
   return {
     input_tokens: usage?.input_tokens ?? 0,
     output_tokens: usage?.output_tokens ?? 0,
     cache_creation_input_tokens: 0,
-    cache_read_input_tokens: 0,
+    cache_read_input_tokens:
+      usage?.input_tokens_details?.cached_tokens ??
+      usage?.prompt_tokens_details?.cached_tokens ??
+      0,
   }
 }
 
@@ -890,8 +895,16 @@ export async function* codexStreamToAnthropic(
       stop_sequence: null,
     },
     usage: {
-      input_tokens: finalResponse?.usage?.input_tokens ?? 0,
+      // Subtract cached tokens: OpenAI includes them in input_tokens,
+      // but Anthropic convention treats input_tokens as non-cached only.
+      input_tokens: (finalResponse?.usage?.input_tokens ?? 0) -
+        (finalResponse?.usage?.input_tokens_details?.cached_tokens ??
+         finalResponse?.usage?.prompt_tokens_details?.cached_tokens ?? 0),
       output_tokens: finalResponse?.usage?.output_tokens ?? 0,
+      cache_read_input_tokens:
+        finalResponse?.usage?.input_tokens_details?.cached_tokens ??
+        finalResponse?.usage?.prompt_tokens_details?.cached_tokens ??
+        0,
     },
   }
   yield { type: 'message_stop' }
diff --git a/src/services/api/openaiShim.ts b/src/services/api/openaiShim.ts
index 727e4ca9..978ecf57 100644
--- a/src/services/api/openaiShim.ts
+++ b/src/services/api/openaiShim.ts
@@ -564,11 +564,14 @@ function convertChunkUsage(
 ): Partial<AnthropicUsage> | undefined {
   if (!usage) return undefined
 
+  const cached = usage.prompt_tokens_details?.cached_tokens ?? 0
   return {
-    input_tokens: usage.prompt_tokens ?? 0,
+    // Subtract cached tokens: OpenAI includes them in prompt_tokens,
+    // but Anthropic convention treats input_tokens as non-cached only.
+    input_tokens: (usage.prompt_tokens ?? 0) - cached,
     output_tokens: usage.completion_tokens ?? 0,
     cache_creation_input_tokens: 0,
-    cache_read_input_tokens: usage.prompt_tokens_details?.cached_tokens ?? 0,
+    cache_read_input_tokens: cached,
   }
 }