diff --git a/ui/litellm-dashboard/src/components/llm_calls/chat_completion.test.tsx b/ui/litellm-dashboard/src/components/llm_calls/chat_completion.test.tsx index 129d51d50a2..71f36bdb6db 100644 --- a/ui/litellm-dashboard/src/components/llm_calls/chat_completion.test.tsx +++ b/ui/litellm-dashboard/src/components/llm_calls/chat_completion.test.tsx @@ -472,6 +472,12 @@ describe("chat_completion prompt cache usage", () => { expect(usageData).toEqual(expect.not.objectContaining({ cost: expect.anything() })); }); + + it("omits cost when the provider reports a blank value", async () => { + const usageData = await captureUsage({ cost: " " }); + + expect(usageData).toEqual(expect.not.objectContaining({ cost: expect.anything() })); + }); }); describe("chat_completion response cache", () => { diff --git a/ui/litellm-dashboard/src/components/llm_calls/chat_completion.tsx b/ui/litellm-dashboard/src/components/llm_calls/chat_completion.tsx index c12a2c3cfb4..ffa2877fbd9 100644 --- a/ui/litellm-dashboard/src/components/llm_calls/chat_completion.tsx +++ b/ui/litellm-dashboard/src/components/llm_calls/chat_completion.tsx @@ -5,6 +5,7 @@ import { VectorStoreSearchResponse } from "../chat_ui/types"; import { getProxyBaseUrl } from "@/components/networking"; import { MCPServer, MCPToolset, type MCPEvent } from "@/components/mcp_tools/types"; import { extractPromptCacheTokens } from "@/utils/promptCacheUsage"; +import { parseUsageCost } from "./usage_cost"; const completionAsSingleChunk = (completion: ChatCompletion): ChatCompletionChunk => ({ @@ -243,12 +244,9 @@ export async function makeOpenAIChatCompletionRequest( usageData.reasoningTokens = chunkWithUsage.usage.completion_tokens_details.reasoning_tokens; } - // Extract cost from usage object if available - if (chunkWithUsage.usage.cost !== undefined && chunkWithUsage.usage.cost !== null) { - const parsedCost = Number(chunkWithUsage.usage.cost); - if (Number.isFinite(parsedCost)) { - usageData.cost = parsedCost; - } + const parsedCost = parseUsageCost(chunkWithUsage.usage.cost); + if (parsedCost !== undefined) { + usageData.cost = parsedCost; } onUsageData(usageData); diff --git a/ui/litellm-dashboard/src/components/llm_calls/responses_api.test.tsx b/ui/litellm-dashboard/src/components/llm_calls/responses_api.test.tsx index 7b13f0ac2e3..b55df89d5cc 100644 --- a/ui/litellm-dashboard/src/components/llm_calls/responses_api.test.tsx +++ b/ui/litellm-dashboard/src/components/llm_calls/responses_api.test.tsx @@ -260,6 +260,35 @@ describe("responses_api", () => { expect(onUsageData).toHaveBeenCalledWith(expect.not.objectContaining({ cost: expect.anything() }), ""); }); + it("should omit cost when the proxy reports a blank cost", async () => { + async function* streamWithBlankCost() { + yield { + type: "response.completed", + response: { + id: "resp_blank_cost", + usage: { output_tokens: 12, input_tokens: 12, total_tokens: 24, cost: " " }, + }, + }; + } + mockResponsesCreate.mockResolvedValueOnce(streamWithBlankCost()); + + const onUsageData = vi.fn(); + + await makeOpenAIResponsesRequest( + messages, + mockUpdateTextUI, + "gpt-4", + "test-token", + undefined, + undefined, + undefined, + undefined, + onUsageData, + ); + + expect(onUsageData).toHaveBeenCalledWith(expect.not.objectContaining({ cost: expect.anything() }), ""); + }); + it("should replay MCP output items as events for a non-streaming response", async () => { mockResponsesCreate.mockReturnValueOnce( nonStreamingResponse({ diff --git a/ui/litellm-dashboard/src/components/llm_calls/responses_api.tsx b/ui/litellm-dashboard/src/components/llm_calls/responses_api.tsx index 63085a81b94..ce54c7c6b40 100644 --- a/ui/litellm-dashboard/src/components/llm_calls/responses_api.tsx +++ b/ui/litellm-dashboard/src/components/llm_calls/responses_api.tsx @@ -4,6 +4,7 @@ import { TokenUsage } from "../chat_ui/ResponseMetrics"; import { getProxyBaseUrl } from "@/components/networking"; import { toast } from "@/lib/toast"; import { extractPromptCacheTokens } from "@/utils/promptCacheUsage"; +import { parseUsageCost } from "./usage_cost"; import type { MCPEvent } from "@/components/mcp_tools/types"; import { MCPServer, MCPToolset } from "@/components/mcp_tools/types"; import { @@ -311,11 +312,9 @@ export async function makeOpenAIResponsesRequest( usageData.reasoningTokens = reasoningTokens; } - if (usage.cost !== undefined && usage.cost !== null) { - const parsedCost = Number(usage.cost); - if (Number.isFinite(parsedCost)) { - usageData.cost = parsedCost; - } + const parsedCost = parseUsageCost(usage.cost); + if (parsedCost !== undefined) { + usageData.cost = parsedCost; } onUsageData(usageData, mcpToolUsed); diff --git a/ui/litellm-dashboard/src/components/llm_calls/usage_cost.test.ts b/ui/litellm-dashboard/src/components/llm_calls/usage_cost.test.ts new file mode 100644 index 00000000000..ee1021c0629 --- /dev/null +++ b/ui/litellm-dashboard/src/components/llm_calls/usage_cost.test.ts @@ -0,0 +1,39 @@ +import { describe, expect, it } from "vitest"; +import { parseUsageCost } from "./usage_cost"; + +describe("parseUsageCost", () => { + it("keeps finite numbers, including zero", () => { + expect(parseUsageCost(0)).toBe(0); + expect(parseUsageCost(0.000063)).toBe(0.000063); + }); + + it("keeps numeric strings", () => { + expect(parseUsageCost("0.00019")).toBe(0.00019); + expect(parseUsageCost(" 0.00019 ")).toBe(0.00019); + }); + + it("drops blank strings instead of fabricating a zero cost", () => { + expect(parseUsageCost("")).toBeUndefined(); + expect(parseUsageCost(" ")).toBeUndefined(); + expect(parseUsageCost("\t\n")).toBeUndefined(); + }); + + it("drops strings with a numeric prefix instead of truncating them", () => { + expect(parseUsageCost("1oops")).toBeUndefined(); + expect(parseUsageCost("0.5 USD")).toBeUndefined(); + }); + + it("drops non-finite numbers", () => { + expect(parseUsageCost(Number.NaN)).toBeUndefined(); + expect(parseUsageCost(Number.POSITIVE_INFINITY)).toBeUndefined(); + }); + + it("drops values that are not numbers or strings", () => { + expect(parseUsageCost(null)).toBeUndefined(); + expect(parseUsageCost(undefined)).toBeUndefined(); + expect(parseUsageCost(true)).toBeUndefined(); + expect(parseUsageCost([])).toBeUndefined(); + expect(parseUsageCost(["0.5"])).toBeUndefined(); + expect(parseUsageCost({ total_cost: 0.5 })).toBeUndefined(); + }); +}); diff --git a/ui/litellm-dashboard/src/components/llm_calls/usage_cost.ts b/ui/litellm-dashboard/src/components/llm_calls/usage_cost.ts new file mode 100644 index 00000000000..79f56dcb2df --- /dev/null +++ b/ui/litellm-dashboard/src/components/llm_calls/usage_cost.ts @@ -0,0 +1,23 @@ +/** + * Providers and upstream gateways report `usage.cost` unvalidated: it arrives as a number, a numeric + * string, an empty string, or something non-numeric. A cost that does not resolve to a finite number + * must be dropped rather than coerced, because `NaN` survives `JSON.stringify` as `null` and crashes + * the metrics row on the next load. + */ +export function parseUsageCost(rawCost: unknown): number | undefined { + if (typeof rawCost === "number") { + return Number.isFinite(rawCost) ? rawCost : undefined; + } + + if (typeof rawCost !== "string") { + return undefined; + } + + const trimmed = rawCost.trim(); + if (trimmed === "") { + return undefined; + } + + const parsed = Number(trimmed); + return Number.isFinite(parsed) ? parsed : undefined; +}