@@ -181,6 +181,31 @@ describe("OpenAiHandler with usage tracking fix", () => {
 			})
 		})
 
+		it("should report OpenAI-compatible cached prompt tokens", async () => {
+			mockCreate.mockImplementationOnce(async () =>
+				asyncStreamFrom([
+					{
+						choices: [{ delta: { content: "Cached response" }, index: 0 }],
+						usage: {
+							prompt_tokens: 5_053,
+							completion_tokens: 16,
+							total_tokens: 5_069,
+							prompt_tokens_details: { cached_tokens: 4_864 },
+						},
+					},
+				]),
+			)
+
+			const chunks = await collectStream(handler.createMessage(systemPrompt, messages))
+
+			expect(chunks).toContainEqual({
+				type: "usage",
+				inputTokens: 5_053,
+				outputTokens: 16,
+				cacheReadTokens: 4_864,
+			})
+		})
+
 		it("should handle case where no usage is provided", async () => {
 			// Override the mock for this specific test
 			mockCreate.mockImplementationOnce(async (options) => {
@@ -212,4 +237,27 @@ describe("OpenAiHandler with usage tracking fix", () => {
 			expect(usageChunks).toHaveLength(0)
 		})
 	})
+
+	it("should report cached prompt tokens from a non-streaming response", async () => {
+		const nonStreamingHandler = new OpenAiHandler({ ...mockOptions, openAiStreamingEnabled: false })
+		mockCreate.mockImplementationOnce(async () => ({
+			id: "test-completion",
+			choices: [{ message: { role: "assistant", content: "Cached response" } }],
+			usage: {
+				prompt_tokens: 4_621,
+				completion_tokens: 16,
+				total_tokens: 4_637,
+				prompt_tokens_details: { cached_tokens: 4_608 },
+			},
+		}))
+
+		const chunks = await collectStream(nonStreamingHandler.createMessage("system prompt", []))
+
+		expect(chunks).toContainEqual({
+			type: "usage",
+			inputTokens: 4_621,
+			outputTokens: 16,
+			cacheReadTokens: 4_608,
+		})
+	})
 })
@@ -282,12 +282,14 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
 	}
 
 	protected processUsageMetrics(usage: any, _modelInfo?: ModelInfo): ApiStreamUsageChunk {
+		const cacheReadTokens = usage?.cache_read_input_tokens ?? usage?.prompt_tokens_details?.cached_tokens
+
 		return {
 			type: "usage",
 			inputTokens: usage?.prompt_tokens || 0,
 			outputTokens: usage?.completion_tokens || 0,
 			cacheWriteTokens: usage?.cache_creation_input_tokens || undefined,
-			cacheReadTokens: usage?.cache_read_input_tokens || undefined,
+			cacheReadTokens: cacheReadTokens || undefined,
 		}
 	}
Original file line number	Diff line number	Diff line change
`@@ -282,12 +282,14 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl`
`282`	`282`	`}`
`283`	`283`
`284`	`284`	`protected processUsageMetrics(usage: any, _modelInfo?: ModelInfo): ApiStreamUsageChunk {`
	`285`	`+ const cacheReadTokens = usage?.cache_read_input_tokens ?? usage?.prompt_tokens_details?.cached_tokens`
	`286`	`+`
`285`	`287`	`return {`
`286`	`288`	`type: "usage",`
`287`	`289`	`inputTokens: usage?.prompt_tokens \|\| 0,`
`288`	`290`	`outputTokens: usage?.completion_tokens \|\| 0,`
`289`	`291`	`cacheWriteTokens: usage?.cache_creation_input_tokens \|\| undefined,`
`290`		`- cacheReadTokens: usage?.cache_read_input_tokens \|\| undefined,`
	`292`	`+ cacheReadTokens: cacheReadTokens \|\| undefined,`
`291`	`293`	`}`
`292`	`294`	`}`
`293`	`295`