xinyin025/new-api
1
0
Fork 0
mirror of https://github.com/linux-do/new-api.git synced 2025-11-13 01:23:41 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main'

Browse Source 
# Conflicts:
#	controller/relay.go
#	main.go
#	middleware/distributor.go
This commit is contained in:
CaIon
2023-09-09 03:15:55 +08:00
parent 9ab4f7a271 d0a0e871e1
commit 9c08d78349
26 changed files with 1027 additions and 187 deletions
Download Patch File Download Diff File Expand all files Collapse all files

91
common/constants.go
View File

@@ -98,6 +98,9 @@ var RequestInterval = time.Duration(requestInterval) * time.Second
var SyncFrequency = 10 * 60 // unit is second, will be overwritten by SYNC_FREQUENCY
var BatchUpdateEnabled = false
var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)
const (
RoleGuestUser = 0
RoleCommonUser = 1
@@ -115,10 +118,10 @@ var (
// All duration's unit is seconds
// Shouldn't larger then RateLimitKeyExpirationDuration
var (
GlobalApiRateLimitNum = 180
GlobalApiRateLimitNum = GetOrDefault("GLOBAL_API_RATE_LIMIT", 180)
GlobalApiRateLimitDuration int64 = 3 * 60
GlobalWebRateLimitNum = 60
GlobalWebRateLimitNum = GetOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
GlobalWebRateLimitDuration int64 = 3 * 60
UploadRateLimitNum = 10
@@ -158,45 +161,53 @@ const (
)
const (
ChannelTypeUnknown = 0
ChannelTypeOpenAI = 1
ChannelTypeAPI2D = 2
ChannelTypeAzure = 3
ChannelTypeCloseAI = 4
ChannelTypeOpenAISB = 5
ChannelTypeOpenAIMax = 6
ChannelTypeOhMyGPT = 7
ChannelTypeCustom = 8
ChannelTypeAILS = 9
ChannelTypeAIProxy = 10
ChannelTypePaLM = 11
ChannelTypeAPI2GPT = 12
ChannelTypeAIGC2D = 13
ChannelTypeAnthropic = 14
ChannelTypeBaidu = 15
ChannelTypeZhipu = 16
ChannelTypeAli = 17
ChannelTypeXunfei = 18
ChannelTypeUnknown = 0
ChannelTypeOpenAI = 1
ChannelTypeAPI2D = 2
ChannelTypeAzure = 3
ChannelTypeCloseAI = 4
ChannelTypeOpenAISB = 5
ChannelTypeOpenAIMax = 6
ChannelTypeOhMyGPT = 7
ChannelTypeCustom = 8
ChannelTypeAILS = 9
ChannelTypeAIProxy = 10
ChannelTypePaLM = 11
ChannelTypeAPI2GPT = 12
ChannelTypeAIGC2D = 13
ChannelTypeAnthropic = 14
ChannelTypeBaidu = 15
ChannelTypeZhipu = 16
ChannelTypeAli = 17
ChannelTypeXunfei = 18
ChannelType360 = 19
ChannelTypeOpenRouter = 20
ChannelTypeAIProxyLibrary = 21
ChannelTypeFastGPT = 22
)
var ChannelBaseURLs = []string{
"", // 0
"https://api.openai.com", // 1
"https://oa.api2d.net", // 2
"", // 3
"https://api.closeai-proxy.xyz", // 4
"https://api.openai-sb.com", // 5
"https://api.openaimax.com", // 6
"https://api.ohmygpt.com", // 7
"", // 8
"https://api.caipacity.com", // 9
"https://api.aiproxy.io", // 10
"", // 11
"https://api.api2gpt.com", // 12
"https://api.aigc2d.com", // 13
"https://api.anthropic.com", // 14
"https://aip.baidubce.com", // 15
"https://open.bigmodel.cn", // 16
"https://dashscope.aliyuncs.com", // 17
"", // 18
"", // 0
"https://api.openai.com", // 1
"https://oa.api2d.net", // 2
"", // 3
"https://api.closeai-proxy.xyz", // 4
"https://api.openai-sb.com", // 5
"https://api.openaimax.com", // 6
"https://api.ohmygpt.com", // 7
"", // 8
"https://api.caipacity.com", // 9
"https://api.aiproxy.io", // 10
"", // 11
"https://api.api2gpt.com", // 12
"https://api.aigc2d.com", // 13
"https://api.anthropic.com", // 14
"https://aip.baidubce.com", // 15
"https://open.bigmodel.cn", // 16
"https://dashscope.aliyuncs.com", // 17
"", // 18
"https://ai.360.cn", // 19
"https://openrouter.ai/api", // 20
"https://api.aiproxy.io", // 21
"https://fastgpt.run/api/openapi", // 22
}

86
common/model-ratio.go
View File

@@ -13,46 +13,52 @@ import (
// 1 === $0.002 / 1K tokens
// 1 === ￥0.014 / 1k tokens
var ModelRatio = map[string]float64{
"gpt-4": 15,
"gpt-4-0314": 15,
"gpt-4-0613": 15,
"gpt-4-32k": 30,
"gpt-4-32k-0314": 30,
"gpt-4-32k-0613": 30,
"gpt-3.5-turbo": 0.75, // $0.0015 / 1K tokens
"gpt-3.5-turbo-0301": 0.75,
"gpt-3.5-turbo-0613": 0.75,
"gpt-3.5-turbo-16k": 1.5, // $0.003 / 1K tokens
"gpt-3.5-turbo-16k-0613": 1.5,
"text-ada-001": 0.2,
"text-babbage-001": 0.25,
"text-curie-001": 1,
"text-davinci-002": 10,
"text-davinci-003": 10,
"text-davinci-edit-001": 10,
"code-davinci-edit-001": 10,
"whisper-1": 10,
"davinci": 10,
"curie": 10,
"babbage": 10,
"ada": 10,
"text-embedding-ada-002": 0.05,
"text-search-ada-doc-001": 10,
"text-moderation-stable": 0.1,
"text-moderation-latest": 0.1,
"dall-e": 8,
"claude-instant-1": 0.815, // $1.63 / 1M tokens
"claude-2": 5.51, // $11.02 / 1M tokens
"ERNIE-Bot": 0.8572, // ￥0.012 / 1k tokens
"ERNIE-Bot-turbo": 0.5715, // ￥0.008 / 1k tokens
"Embedding-V1": 0.1429, // ￥0.002 / 1k tokens
"PaLM-2": 1,
"chatglm_pro": 0.7143, // ￥0.01 / 1k tokens
"chatglm_std": 0.3572, // ￥0.005 / 1k tokens
"chatglm_lite": 0.1429, // ￥0.002 / 1k tokens
"qwen-v1": 0.8572, // TBD: https://help.aliyun.com/document_detail/2399482.html?spm=a2c4g.2399482.0.0.1ad347feilAgag
"qwen-plus-v1": 0.5715, // Same as above
"SparkDesk": 0.8572, // TBD
"gpt-4": 15,
"gpt-4-0314": 15,
"gpt-4-0613": 15,
"gpt-4-32k": 30,
"gpt-4-32k-0314": 30,
"gpt-4-32k-0613": 30,
"gpt-3.5-turbo": 0.75, // $0.0015 / 1K tokens
"gpt-3.5-turbo-0301": 0.75,
"gpt-3.5-turbo-0613": 0.75,
"gpt-3.5-turbo-16k": 1.5, // $0.003 / 1K tokens
"gpt-3.5-turbo-16k-0613": 1.5,
"text-ada-001": 0.2,
"text-babbage-001": 0.25,
"text-curie-001": 1,
"text-davinci-002": 10,
"text-davinci-003": 10,
"text-davinci-edit-001": 10,
"code-davinci-edit-001": 10,
"whisper-1": 15, // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
"davinci": 10,
"curie": 10,
"babbage": 10,
"ada": 10,
"text-embedding-ada-002": 0.05,
"text-search-ada-doc-001": 10,
"text-moderation-stable": 0.1,
"text-moderation-latest": 0.1,
"dall-e": 8,
"claude-instant-1": 0.815, // $1.63 / 1M tokens
"claude-2": 5.51, // $11.02 / 1M tokens
"ERNIE-Bot": 0.8572, // ￥0.012 / 1k tokens
"ERNIE-Bot-turbo": 0.5715, // ￥0.008 / 1k tokens
"Embedding-V1": 0.1429, // ￥0.002 / 1k tokens
"PaLM-2": 1,
"chatglm_pro": 0.7143, // ￥0.01 / 1k tokens
"chatglm_std": 0.3572, // ￥0.005 / 1k tokens
"chatglm_lite": 0.1429, // ￥0.002 / 1k tokens
"qwen-v1": 0.8572, // ￥0.012 / 1k tokens
"qwen-plus-v1": 1, // ￥0.014 / 1k tokens
"text-embedding-v1": 0.05, // ￥0.0007 / 1k tokens
"SparkDesk": 1.2858, // ￥0.018 / 1k tokens
"360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens
"embedding-bert-512-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
"360GPT_S2_V9.4": 0.8572, // ¥0.012 / 1k tokens
}
func ModelRatio2JSONString() string {