zack3d/OAI-Proxy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

model pricing update

Browse Source
This commit is contained in:
Nopm
2025-06-03 23:09:39 -03:00
parent 4e3fb9d152
commit 41bc4998fc
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/shared/stats.ts
+8 -8
View File
@@ -3,7 +3,7 @@ import { ModelFamily } from "./models";
// Prices are per 1 million tokens. // Prices are per 1 million tokens.
const MODEL_PRICING: Record<ModelFamily, { input: number; output: number } | undefined> = { const MODEL_PRICING: Record<ModelFamily, { input: number; output: number } | undefined> = {
"deepseek": { input: 0.14, output: 0.28 }, // DeepSeek-V2: $0.14/$0.28 per 1M tokens "deepseek": { input: 0.55, output: 2.19 }, // DeepSeek Reasoner (standard price, input cache miss)
"xai": { input: 5.6, output: 16.8 }, // Grok: Derived from avg $14/1M (assuming 1:3 in/out ratio) - needs official pricing "xai": { input: 5.6, output: 16.8 }, // Grok: Derived from avg $14/1M (assuming 1:3 in/out ratio) - needs official pricing
"gpt41": { input: 2.00, output: 8.00 }, "gpt41": { input: 2.00, output: 8.00 },
"azure-gpt41": { input: 2.00, output: 8.00 }, "azure-gpt41": { input: 2.00, output: 8.00 },
@@ -13,8 +13,8 @@ const MODEL_PRICING: Record<ModelFamily, { input: number; output: number } | und
"azure-gpt41-nano": { input: 0.10, output: 0.40 }, "azure-gpt41-nano": { input: 0.10, output: 0.40 },
"gpt45": { input: 75.00, output: 150.00 }, // Example, needs verification if this model family is still current with this pricing "gpt45": { input: 75.00, output: 150.00 }, // Example, needs verification if this model family is still current with this pricing
"azure-gpt45": { input: 75.00, output: 150.00 }, // Example, needs verification "azure-gpt45": { input: 75.00, output: 150.00 }, // Example, needs verification
"gpt4o": { input: 5.00, output: 20.00 }, "gpt4o": { input: 2.50, output: 10.00 },
"azure-gpt4o": { input: 5.00, output: 20.00 }, "azure-gpt4o": { input: 2.50, output: 10.00 },
"gpt4-turbo": { input: 10.00, output: 30.00 }, "gpt4-turbo": { input: 10.00, output: 30.00 },
"azure-gpt4-turbo": { input: 10.00, output: 30.00 }, "azure-gpt4-turbo": { input: 10.00, output: 30.00 },
"o1-pro": { input: 150.00, output: 600.00 }, "o1-pro": { input: 150.00, output: 600.00 },
@@ -35,8 +35,8 @@ const MODEL_PRICING: Record<ModelFamily, { input: number; output: number } | und
"azure-gpt4-32k": { input: 60.00, output: 120.00 }, "azure-gpt4-32k": { input: 60.00, output: 120.00 },
"gpt4": { input: 30.00, output: 60.00 }, "gpt4": { input: 30.00, output: 60.00 },
"azure-gpt4": { input: 30.00, output: 60.00 }, "azure-gpt4": { input: 30.00, output: 60.00 },
"turbo": { input: 0.60, output: 2.40 }, // Maps to GPT-4o mini "turbo": { input: 0.15, output: 0.60 }, // Maps to GPT-4o mini
"azure-turbo": { input: 0.60, output: 2.40 }, "azure-turbo": { input: 0.15, output: 0.60 },
"dall-e": { input: 0, output: 0 }, // Pricing is per image, not token based in this context. "dall-e": { input: 0, output: 0 }, // Pricing is per image, not token based in this context.
"azure-dall-e": { input: 0, output: 0 }, // Pricing is per image. "azure-dall-e": { input: 0, output: 0 }, // Pricing is per image.
"gpt-image": { input: 0, output: 0 }, // Complex pricing (text, image input, image output tokens), handle separately. "gpt-image": { input: 0, output: 0 }, // Complex pricing (text, image input, image output tokens), handle separately.
@@ -55,12 +55,12 @@ const MODEL_PRICING: Record<ModelFamily, { input: number; output: number } | und
"aws-mistral-medium": { input: 0.40, output: 2.00 }, "aws-mistral-medium": { input: 0.40, output: 2.00 },
"mistral-large": { input: 2.00, output: 6.00 }, "mistral-large": { input: 2.00, output: 6.00 },
"aws-mistral-large": { input: 2.00, output: 6.00 }, "aws-mistral-large": { input: 2.00, output: 6.00 },
"gemini-flash": { input: 0.35, output: 1.05 }, // Gemini 1.5 Flash "gemini-flash": { input: 0.15, output: 0.60 }, // Updated to Gemini 2.5 Flash Preview (text input, non-thinking output)
"gemini-pro": { input: 0.125, output: 0.375 }, // Gemini 1.0 Pro "gemini-pro": { input: 1.25, output: 10.00 }, // Updated to Gemini 2.5 Pro Preview (<=200k tokens)
"gemini-ultra": { input: 25.00, output: 75.00 }, // Estimated based on Gemini Pro (5-10x) and character to token conversion. Official per-token pricing needed. "gemini-ultra": { input: 25.00, output: 75.00 }, // Estimated based on Gemini Pro (5-10x) and character to token conversion. Official per-token pricing needed.
// Ensure all ModelFamily entries from models.ts are covered or have a default. // Ensure all ModelFamily entries from models.ts are covered or have a default.
// Adding placeholders for families in models.ts but not yet priced here. // Adding placeholders for families in models.ts but not yet priced here.
"cohere": { input: 0.25, output: 0.50 }, // Cohere Command R, as an example "cohere": { input: 0.15, output: 0.60 }, // Updated to Command R
"qwen": { input: 1.40, output: 2.80 }, // Qwen-plus, as an example "qwen": { input: 1.40, output: 2.80 }, // Qwen-plus, as an example
}; };