Merge remote-tracking branch 'origin/upstream/main'

This commit is contained in:
Laisky.Cai
2024-02-19 07:23:30 +00:00
71 changed files with 2003 additions and 2097 deletions

View File

@@ -63,6 +63,7 @@ const (
ChannelTypeFastGPT = 22
ChannelTypeTencent = 23
ChannelTypeGemini = 24
ChannelTypeMoonshot = 25
)
var ChannelBaseURLs = []string{
@@ -91,4 +92,13 @@ var ChannelBaseURLs = []string{
"https://fastgpt.run/api/openapi", // 22
"https://hunyuan.cloud.tencent.com", // 23
"https://generativelanguage.googleapis.com", // 24
"https://api.moonshot.cn", // 25
}
const (
ConfigKeyPrefix = "cfg_"
ConfigKeyAPIVersion = ConfigKeyPrefix + "api_version"
ConfigKeyLibraryID = ConfigKeyPrefix + "library_id"
ConfigKeyPlugin = ConfigKeyPrefix + "plugin"
)

View File

@@ -30,6 +30,12 @@ var DalleImagePromptLengthLimitations = map[string]int{
"dall-e-3": 4000,
}
const (
USD2RMB = 7
USD = 500 // $0.002 = 1 -> $1 = 500
RMB = USD / USD2RMB
)
// ModelRatio
// https://platform.openai.com/docs/models/model-endpoint-compatibility
// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Blfmc9dlf
@@ -38,57 +44,60 @@ var DalleImagePromptLengthLimitations = map[string]int{
// 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-4-1106-preview": 5, // $0.01 / 1K tokens
"gpt-4-0125-preview": 5, // $0.01 / 1K tokens
"gpt-4-turbo-preview": 5, // $0.01 / 1K tokens
"gpt-4-vision-preview": 5, // $0.01 / 1K tokens
"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,
"gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens
"gpt-3.5-turbo-1106": 0.5, // $0.001 / 1K tokens
"gpt-3.5-turbo-0125": 0.25, // $0.0005 / 1K tokens
"davinci-002": 1, // $0.002 / 1K tokens
"babbage-002": 0.2, // $0.0004 / 1K tokens
"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
"tts-1": 7.5, // $0.015 / 1K characters
"tts-1-1106": 7.5,
"tts-1-hd": 15, // $0.030 / 1K characters
"tts-1-hd-1106": 15,
"davinci": 10,
"curie": 10,
"babbage": 10,
"ada": 10,
"text-embedding-ada-002": 0.05,
"text-embedding-3-small": 0.01,
"text-embedding-3-large": 0.065,
"text-search-ada-doc-001": 10,
"text-moderation-stable": 0.1,
"text-moderation-latest": 0.1,
"dall-e-2": 8, // $0.016 - $0.020 / image
"dall-e-3": 20, // $0.040 - $0.120 / image
"claude-instant-1": 0.815, // $1.63 / 1M tokens
"claude-2": 5.51, // $11.02 / 1M tokens
"claude-2.0": 5.51, // $11.02 / 1M tokens
"claude-2.1": 5.51, // $11.02 / 1M tokens
"ERNIE-Bot": 0.8572, // ¥0.012 / 1k tokens
"ERNIE-Bot-turbo": 0.5715, // ¥0.008 / 1k tokens
"ERNIE-Bot-4": 8.572, // ¥0.12 / 1k tokens
// https://openai.com/pricing
"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-4-1106-preview": 5, // $0.01 / 1K tokens
"gpt-4-0125-preview": 5, // $0.01 / 1K tokens
"gpt-4-turbo-preview": 5, // $0.01 / 1K tokens
"gpt-4-vision-preview": 5, // $0.01 / 1K tokens
"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,
"gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens
"gpt-3.5-turbo-1106": 0.5, // $0.001 / 1K tokens
"gpt-3.5-turbo-0125": 0.25, // $0.0005 / 1K tokens
"davinci-002": 1, // $0.002 / 1K tokens
"babbage-002": 0.2, // $0.0004 / 1K tokens
"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
"tts-1": 7.5, // $0.015 / 1K characters
"tts-1-1106": 7.5,
"tts-1-hd": 15, // $0.030 / 1K characters
"tts-1-hd-1106": 15,
"davinci": 10,
"curie": 10,
"babbage": 10,
"ada": 10,
"text-embedding-ada-002": 0.05,
"text-embedding-3-small": 0.01,
"text-embedding-3-large": 0.065,
"text-search-ada-doc-001": 10,
"text-moderation-stable": 0.1,
"text-moderation-latest": 0.1,
"dall-e-2": 8, // $0.016 - $0.020 / image
"dall-e-3": 20, // $0.040 - $0.120 / image
"claude-instant-1": 0.815, // $1.63 / 1M tokens
"claude-2": 5.51, // $11.02 / 1M tokens
"claude-2.0": 5.51, // $11.02 / 1M tokens
"claude-2.1": 5.51, // $11.02 / 1M tokens
// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
"ERNIE-Bot": 0.8572, // ¥0.012 / 1k tokens
"ERNIE-Bot-turbo": 0.5715, // ¥0.008 / 1k tokens
"ERNIE-Bot-4": 0.12 * RMB, // ¥0.12 / 1k tokens
"ERNIE-Bot-8k": 0.024 * RMB,
"Embedding-V1": 0.1429, // ¥0.002 / 1k tokens
"PaLM-2": 1,
"gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
@@ -103,11 +112,21 @@ var ModelRatio = map[string]float64{
"qwen-max-longcontext": 1.4286, // ¥0.02 / 1k tokens
"text-embedding-v1": 0.05, // ¥0.0007 / 1k tokens
"SparkDesk": 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-v3.1": 1.2858, // ¥0.018 / 1k tokens
"SparkDesk-v3.5": 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
"hunyuan": 7.143, // ¥0.1 / 1k tokens // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
"ChatStd": 0.01 * RMB,
"ChatPro": 0.1 * RMB,
// https://platform.moonshot.cn/pricing
"moonshot-v1-8k": 0.012 * RMB,
"moonshot-v1-32k": 0.024 * RMB,
"moonshot-v1-128k": 0.06 * RMB,
}
func ModelRatio2JSONString() string {