xinyin025/new-api
1
0
Fork 0
mirror of https://github.com/linux-do/new-api.git synced 2025-09-18 00:16:37 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

add gpt-4o model ratio

Browse Source 
Signed-off-by: wozulong <>
This commit is contained in:
wozulong 2024-05-14 02:38:44 +08:00
parent 310f8c247e
commit 4f6c171a08
1 changed files with 84 additions and 82 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

166
common/model-ratio.go
View File

@ -15,65 +15,67 @@ import (
var DefaultModelRatio = map[string]float64{ var DefaultModelRatio = map[string]float64{
//"midjourney": 50, //"midjourney": 50,
"gpt-4-gizmo-*": 15, "gpt-4-gizmo-*": 15,
"gpt-4": 15, "gpt-4": 15,
"gpt-4-0314": 15, "gpt-4-0314": 15,
"gpt-4-0613": 15, "gpt-4-0613": 15,
"gpt-4-32k": 30, "gpt-4-32k": 30,
"gpt-4-32k-0314": 30, "gpt-4-32k-0314": 30,
"gpt-4-32k-0613": 30, "gpt-4-32k-0613": 30,
"gpt-4-turbo": 5, // $0.01 / 1K tokens "gpt-4o": 2.5, // $0.005 / 1K tokens
"gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens "gpt-4o-2024-05-13": 2.5, // $0.005 / 1K tokens
"gpt-4-1106-preview": 5, // $0.01 / 1K tokens "gpt-4-turbo": 5, // $0.01 / 1K tokens
"gpt-4-0125-preview": 5, // $0.01 / 1K tokens "gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens
"gpt-4-turbo-preview": 5, // $0.01 / 1K tokens "gpt-4-1106-preview": 5, // $0.01 / 1K tokens
"gpt-4-vision-preview": 5, // $0.01 / 1K tokens "gpt-4-0125-preview": 5, // $0.01 / 1K tokens
"gpt-4-1106-vision-preview": 5, // $0.01 / 1K tokens "gpt-4-turbo-preview": 5, // $0.01 / 1K tokens
"gpt-3.5-turbo": 0.25, // $0.0005 / 1K tokens "gpt-4-vision-preview": 5, // $0.01 / 1K tokens
"gpt-3.5-turbo-0301": 0.75, "gpt-4-1106-vision-preview": 5, // $0.01 / 1K tokens
"gpt-3.5-turbo-0613": 0.75, "gpt-3.5-turbo": 0.25, // $0.0005 / 1K tokens
"gpt-3.5-turbo-16k": 1.5, // $0.003 / 1K tokens "gpt-3.5-turbo-0301": 0.75,
"gpt-3.5-turbo-16k-0613": 1.5, "gpt-3.5-turbo-0613": 0.75,
"gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens "gpt-3.5-turbo-16k": 1.5, // $0.003 / 1K tokens
"gpt-3.5-turbo-1106": 0.5, // $0.001 / 1K tokens "gpt-3.5-turbo-16k-0613": 1.5,
"gpt-3.5-turbo-0125": 0.25, "gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens
"babbage-002": 0.2, // $0.0004 / 1K tokens "gpt-3.5-turbo-1106": 0.5, // $0.001 / 1K tokens
"davinci-002": 1, // $0.002 / 1K tokens "gpt-3.5-turbo-0125": 0.25,
"text-ada-001": 0.2, "babbage-002": 0.2, // $0.0004 / 1K tokens
"text-babbage-001": 0.25, "davinci-002": 1, // $0.002 / 1K tokens
"text-curie-001": 1, "text-ada-001": 0.2,
"text-davinci-002": 10, "text-babbage-001": 0.25,
"text-davinci-003": 10, "text-curie-001": 1,
"text-davinci-edit-001": 10, "text-davinci-002": 10,
"code-davinci-edit-001": 10, "text-davinci-003": 10,
"whisper-1": 15, // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens "text-davinci-edit-001": 10,
"tts-1": 7.5, // 1k characters -> $0.015 "code-davinci-edit-001": 10,
"tts-1-1106": 7.5, // 1k characters -> $0.015 "whisper-1": 15, // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
"tts-1-hd": 15, // 1k characters -> $0.03 "tts-1": 7.5, // 1k characters -> $0.015
"tts-1-hd-1106": 15, // 1k characters -> $0.03 "tts-1-1106": 7.5, // 1k characters -> $0.015
"davinci": 10, "tts-1-hd": 15, // 1k characters -> $0.03
"curie": 10, "tts-1-hd-1106": 15, // 1k characters -> $0.03
"babbage": 10, "davinci": 10,
"ada": 10, "curie": 10,
"text-embedding-3-small": 0.01, "babbage": 10,
"text-embedding-3-large": 0.065, "ada": 10,
"text-embedding-ada-002": 0.05, "text-embedding-3-small": 0.01,
"text-search-ada-doc-001": 10, "text-embedding-3-large": 0.065,
"text-moderation-stable": 0.1, "text-embedding-ada-002": 0.05,
"text-moderation-latest": 0.1, "text-search-ada-doc-001": 10,
"dall-e-2": 8, "text-moderation-stable": 0.1,
"dall-e-3": 16, "text-moderation-latest": 0.1,
"claude-instant-1": 0.4, // $0.8 / 1M tokens "dall-e-2": 8,
"claude-2.0": 4, // $8 / 1M tokens "dall-e-3": 16,
"claude-2.1": 4, // $8 / 1M tokens "claude-instant-1": 0.4, // $0.8 / 1M tokens
"claude-3-haiku-20240307": 0.125, // $0.25 / 1M tokens "claude-2.0": 4, // $8 / 1M tokens
"claude-3-sonnet-20240229": 1.5, // $3 / 1M tokens "claude-2.1": 4, // $8 / 1M tokens
"claude-3-opus-20240229": 7.5, // $15 / 1M tokens "claude-3-haiku-20240307": 0.125, // $0.25 / 1M tokens
"ERNIE-Bot": 0.8572, // ￥0.012 / 1k tokens "claude-3-sonnet-20240229": 1.5, // $3 / 1M tokens
"ERNIE-Bot-turbo": 0.5715, // ￥0.008 / 1k tokens "claude-3-opus-20240229": 7.5, // $15 / 1M tokens
"ERNIE-Bot-4": 8.572, // ￥0.12 / 1k tokens "ERNIE-Bot": 0.8572, // ￥0.012 / 1k tokens
"Embedding-V1": 0.1429, // ￥0.002 / 1k tokens "ERNIE-Bot-turbo": 0.5715, // ￥0.008 / 1k tokens
"PaLM-2": 1, "ERNIE-Bot-4": 8.572, // ￥0.12 / 1k tokens
"Embedding-V1": 0.1429, // ￥0.002 / 1k tokens
"PaLM-2": 1,
"gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens "gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
"gemini-pro-vision": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens "gemini-pro-vision": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
"gemini-1.0-pro-vision-001": 1, "gemini-1.0-pro-vision-001": 1,
@ -82,30 +84,30 @@ var DefaultModelRatio = map[string]float64{
"gemini-1.0-pro-latest": 1, "gemini-1.0-pro-latest": 1,
"gemini-1.0-pro-vision-latest": 1, "gemini-1.0-pro-vision-latest": 1,
"gemini-ultra": 1, "gemini-ultra": 1,
"chatglm_turbo": 0.3572, // ￥0.005 / 1k tokens "chatglm_turbo": 0.3572, // ￥0.005 / 1k tokens
"chatglm_pro": 0.7143, // ￥0.01 / 1k tokens "chatglm_pro": 0.7143, // ￥0.01 / 1k tokens
"chatglm_std": 0.3572, // ￥0.005 / 1k tokens "chatglm_std": 0.3572, // ￥0.005 / 1k tokens
"chatglm_lite": 0.1429, // ￥0.002 / 1k tokens "chatglm_lite": 0.1429, // ￥0.002 / 1k tokens
"glm-4": 7.143, // ￥0.1 / 1k tokens "glm-4": 7.143, // ￥0.1 / 1k tokens
"glm-4v": 7.143, // ￥0.1 / 1k tokens "glm-4v": 7.143, // ￥0.1 / 1k tokens
"glm-3-turbo": 0.3572, "glm-3-turbo": 0.3572,
"qwen-turbo": 0.8572, // ￥0.012 / 1k tokens "qwen-turbo": 0.8572, // ￥0.012 / 1k tokens
"qwen-plus": 10, // ￥0.14 / 1k tokens "qwen-plus": 10, // ￥0.14 / 1k tokens
"text-embedding-v1": 0.05, // ￥0.0007 / 1k tokens "text-embedding-v1": 0.05, // ￥0.0007 / 1k tokens
"SparkDesk-v1.1": 1.2858, // ￥0.018 / 1k tokens "SparkDesk-v1.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v2.1": 1.2858, // ￥0.018 / 1k tokens "SparkDesk-v2.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.1": 1.2858, // ￥0.018 / 1k tokens "SparkDesk-v3.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.5": 1.2858, // ￥0.018 / 1k tokens "SparkDesk-v3.5": 1.2858, // ￥0.018 / 1k tokens
"360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens "360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens
"embedding-bert-512-v1": 0.0715, // ¥0.001 / 1k tokens "embedding-bert-512-v1": 0.0715, // ¥0.001 / 1k tokens
"embedding_s1_v1": 0.0715, // ¥0.001 / 1k tokens "embedding_s1_v1": 0.0715, // ¥0.001 / 1k tokens
"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens "semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
"hunyuan": 7.143, // ¥0.1 / 1k tokens // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0 "hunyuan": 7.143, // ¥0.1 / 1k tokens // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
// https://platform.lingyiwanwu.com/docs#-计费单元 // https://platform.lingyiwanwu.com/docs#-计费单元
// 已经按照 7.2 来换算美元价格 // 已经按照 7.2 来换算美元价格
"yi-34b-chat-0205": 0.018, "yi-34b-chat-0205": 0.018,
"yi-34b-chat-200k": 0.0864, "yi-34b-chat-200k": 0.0864,
"yi-vl-plus": 0.0432, "yi-vl-plus": 0.0432,
"command": 0.5, "command": 0.5,
"command-nightly": 0.5, "command-nightly": 0.5,
"command-light": 0.5, "command-light": 0.5,
@ -217,7 +219,7 @@ func GetCompletionRatio(name string) float64 {
return 1.333333 return 1.333333
} }
if strings.HasPrefix(name, "gpt-4") { if strings.HasPrefix(name, "gpt-4") {
if strings.HasSuffix(name, "preview") || strings.HasPrefix(name, "gpt-4-turbo") { if strings.HasSuffix(name, "preview") || strings.HasPrefix(name, "gpt-4-turbo") || strings.HasPrefix(name, "gpt-4o") {
return 3 return 3
} }
return 2 return 2