Skip to content

Add cached read and writes to stats and cost calculation for LiteLLM provider #4206

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 1, 2025
Merged

Add cached read and writes to stats and cost calculation for LiteLLM provider #4206

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3716053
Add cached read and writes to cost calculation for LiteLLM
mollux Jun 1, 2025
08ac3fe
Fixed property issue
mollux Jun 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions src/api/providers/fetchers/litellm.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,8 @@ export async function getLiteLLMModels(apiKey: string, baseUrl: string): Promise
outputPrice: modelInfo.output_cost_per_token
? modelInfo.output_cost_per_token * 1000000
: undefined,
cacheWritesPrice: modelInfo.cache_creation_input_token_cost ? modelInfo.cache_creation_input_token_cost * 1000000 : undefined,
cacheReadsPrice: modelInfo.cache_read_input_token_cost ? modelInfo.cache_read_input_token_cost * 1000000 : undefined,
description: `${modelName} via LiteLLM proxy`,
}
}
Expand Down
13 changes: 12 additions & 1 deletion src/api/providers/lite-llm.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,8 @@ import { Anthropic } from "@anthropic-ai/sdk" // Keep for type usage only

import { litellmDefaultModelId, litellmDefaultModelInfo } from "@roo-code/types"

import { calculateApiCostOpenAI } from "../../shared/cost"

import { ApiHandlerOptions } from "../../shared/api"

import { ApiStream, ApiStreamUsageChunk } from "../transform/stream"
Expand Down Expand Up @@ -66,7 +68,7 @@ export class LiteLLMHandler extends RouterProvider implements SingleCompletionHa

for await (const chunk of completion) {
const delta = chunk.choices[0]?.delta
const usage = chunk.usage as OpenAI.CompletionUsage
const usage = chunk.usage as LiteLLMUsage

if (delta?.content) {
yield { type: "text", text: delta.content }
Expand All @@ -82,8 +84,12 @@ export class LiteLLMHandler extends RouterProvider implements SingleCompletionHa
type: "usage",
inputTokens: lastUsage.prompt_tokens || 0,
outputTokens: lastUsage.completion_tokens || 0,
cacheWriteTokens: lastUsage.cache_creation_input_tokens || 0,
cacheReadTokens: lastUsage.prompt_tokens_details?.cached_tokens || 0,
}

usageData.totalCost = calculateApiCostOpenAI(info, usageData.inputTokens, usageData.outputTokens, usageData.cacheWriteTokens, usageData.cacheReadTokens)

yield usageData
}
} catch (error) {
Expand Down Expand Up @@ -119,3 +125,8 @@ export class LiteLLMHandler extends RouterProvider implements SingleCompletionHa
}
}
}

// LiteLLM usage may include an extra field for Anthropic use cases.
interface LiteLLMUsage extends OpenAI.CompletionUsage {
cache_creation_input_tokens?: number
}
Loading