feat: update model ratio

common/model-ratio.go

@@ -5,7 +5,7 @@ import (
 	"strings"
 )
 
-//from songquanpeng/one-api
+// from songquanpeng/one-api
 const (
 	USD2RMB = 7.3 // 暂定 1 USD = 7.3 RMB
 	USD     = 500 // $0.002 = 1 -> $1 = 500
@@ -40,86 +40,86 @@ var DefaultModelRatio = map[string]float64{
 	"gpt-4-turbo-2024-04-09":    5,    // $0.01 / 1K tokens
 	"gpt-3.5-turbo":             0.25, // $0.0015 / 1K tokens
 	//"gpt-3.5-turbo-0301":           0.75, //deprecated
-	"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,
-	"babbage-002":                  0.2, // $0.0004 / 1K tokens
-	"davinci-002":                  1,   // $0.002 / 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, // 1k characters -> $0.015
-	"tts-1-1106":                   7.5, // 1k characters -> $0.015
-	"tts-1-hd":                     15,  // 1k characters -> $0.03
-	"tts-1-hd-1106":                15,  // 1k characters -> $0.03
-	"davinci":                      10,
-	"curie":                        10,
-	"babbage":                      10,
-	"ada":                          10,
-	"text-embedding-3-small":       0.01,
-	"text-embedding-3-large":       0.065,
-	"text-embedding-ada-002":       0.05,
-	"text-search-ada-doc-001":      10,
-	"text-moderation-stable":       0.1,
-	"text-moderation-latest":       0.1,
-	"claude-instant-1":             0.4,    // $0.8 / 1M tokens
-	"claude-2.0":                   4,      // $8 / 1M tokens
-	"claude-2.1":                   4,      // $8 / 1M tokens
-	"claude-3-haiku-20240307":      0.125,  // $0.25 / 1M tokens
-	"claude-3-sonnet-20240229":     1.5,    // $3 / 1M tokens
-	"claude-3-opus-20240229":       7.5,    // $15 / 1M tokens
-	"ERNIE-Bot":                    0.8572, // ￥0.012 / 1k tokens //renamed to ERNIE-3.5-8K
-	"ERNIE-Bot-turbo":              0.5715, // ￥0.008 / 1k tokens //renamed to ERNIE-Lite-8K
-	"ERNIE-Bot-4":                  8.572,  // ￥0.12 / 1k tokens //renamed to ERNIE-4.0-8K
-	"ERNIE-4.0-8K":                 8.572,  // ￥0.12 / 1k tokens
-	"ERNIE-3.5-8K":                 0.8572, // ￥0.012 / 1k tokens
-	"ERNIE-Speed-8K":               0.2858, // ￥0.004 / 1k tokens
-	"ERNIE-Speed-128K":             0.2858, // ￥0.004 / 1k tokens
-	"ERNIE-Lite-8K":                0.2143, // ￥0.003 / 1k tokens
-	"ERNIE-Tiny-8K":                0.0715, // ￥0.001 / 1k tokens
-	"ERNIE-Character-8K":           0.2858, // ￥0.004 / 1k tokens
-	"ERNIE-Functions-8K":           0.2858, // ￥0.004 / 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-vision":            1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-1.0-pro-vision-001":    1,
-	"gemini-1.0-pro-001":           1,
-	"gemini-1.5-pro-latest":        1,
-	"gemini-1.5-flash-latest":      1,
-	"gemini-1.0-pro-latest":        1,
-	"gemini-1.0-pro-vision-latest": 1,
-	"gemini-ultra":                 1,
-	"chatglm_turbo":                0.3572, // ￥0.005 / 1k tokens
-	"chatglm_pro":                  0.7143, // ￥0.01 / 1k tokens
-	"chatglm_std":                  0.3572, // ￥0.005 / 1k tokens
-	"chatglm_lite":                 0.1429, // ￥0.002 / 1k tokens
-	"glm-4":                        7.143,  // ￥0.1 / 1k tokens
-	"glm-4v":                       7.143,  // ￥0.1 / 1k tokens
-	"glm-3-turbo":                  0.3572,
-	"qwen-turbo":                   0.8572, // ￥0.012 / 1k tokens
-	"qwen-plus":                    10,     // ￥0.14 / 1k tokens
-	"text-embedding-v1":            0.05,   // ￥0.0007 / 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
-	"360gpt-turbo":                 0.0858, // ¥0.0012 / 1k tokens
+	"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,
+	"babbage-002":                    0.2, // $0.0004 / 1K tokens
+	"davinci-002":                    1,   // $0.002 / 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, // 1k characters -> $0.015
+	"tts-1-1106":                     7.5, // 1k characters -> $0.015
+	"tts-1-hd":                       15,  // 1k characters -> $0.03
+	"tts-1-hd-1106":                  15,  // 1k characters -> $0.03
+	"davinci":                        10,
+	"curie":                          10,
+	"babbage":                        10,
+	"ada":                            10,
+	"text-embedding-3-small":         0.01,
+	"text-embedding-3-large":         0.065,
+	"text-embedding-ada-002":         0.05,
+	"text-search-ada-doc-001":        10,
+	"text-moderation-stable":         0.1,
+	"text-moderation-latest":         0.1,
+	"claude-instant-1":               0.4,    // $0.8 / 1M tokens
+	"claude-2.0":                     4,      // $8 / 1M tokens
+	"claude-2.1":                     4,      // $8 / 1M tokens
+	"claude-3-haiku-20240307":        0.125,  // $0.25 / 1M tokens
+	"claude-3-sonnet-20240229":       1.5,    // $3 / 1M tokens
+	"claude-3-opus-20240229":         7.5,    // $15 / 1M tokens
+	"ERNIE-Bot":                      0.8572, // ￥0.012 / 1k tokens //renamed to ERNIE-3.5-8K
+	"ERNIE-Bot-turbo":                0.5715, // ￥0.008 / 1k tokens //renamed to ERNIE-Lite-8K
+	"ERNIE-Bot-4":                    8.572,  // ￥0.12 / 1k tokens //renamed to ERNIE-4.0-8K
+	"ERNIE-4.0-8K":                   8.572,  // ￥0.12 / 1k tokens
+	"ERNIE-3.5-8K":                   0.8572, // ￥0.012 / 1k tokens
+	"ERNIE-Speed-8K":                 0.2858, // ￥0.004 / 1k tokens
+	"ERNIE-Speed-128K":               0.2858, // ￥0.004 / 1k tokens
+	"ERNIE-Lite-8K":                  0.2143, // ￥0.003 / 1k tokens
+	"ERNIE-Tiny-8K":                  0.0715, // ￥0.001 / 1k tokens
+	"ERNIE-Character-8K":             0.2858, // ￥0.004 / 1k tokens
+	"ERNIE-Functions-8K":             0.2858, // ￥0.004 / 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-vision":              1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-1.0-pro-vision-001":      1,
+	"gemini-1.0-pro-001":             1,
+	"gemini-1.5-pro-latest":          1,
+	"gemini-1.5-flash-latest":        1,
+	"gemini-1.0-pro-latest":          1,
+	"gemini-1.0-pro-vision-latest":   1,
+	"gemini-ultra":                   1,
+	"chatglm_turbo":                  0.3572, // ￥0.005 / 1k tokens
+	"chatglm_pro":                    0.7143, // ￥0.01 / 1k tokens
+	"chatglm_std":                    0.3572, // ￥0.005 / 1k tokens
+	"chatglm_lite":                   0.1429, // ￥0.002 / 1k tokens
+	"glm-4":                          7.143,  // ￥0.1 / 1k tokens
+	"glm-4v":                         7.143,  // ￥0.1 / 1k tokens
+	"glm-3-turbo":                    0.3572,
+	"qwen-turbo":                     0.8572, // ￥0.012 / 1k tokens
+	"qwen-plus":                      10,     // ￥0.14 / 1k tokens
+	"text-embedding-v1":              0.05,   // ￥0.0007 / 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
+	"360gpt-turbo":                   0.0858, // ¥0.0012 / 1k tokens
 	"360gpt-turbo-responsibility-8k": 0.8572, // ¥0.012 / 1k tokens
-	"360gpt-pro":                   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
+	"360gpt-pro":                     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
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	// 已经按照 7.2 来换算美元价格
 	"yi-34b-chat-0205":      0.18,
@@ -143,10 +143,10 @@ var DefaultModelRatio = map[string]float64{
 	"deepseek-chat":         0.07,
 	"deepseek-coder":        0.07,
 	// Perplexity online 模型对搜索额外收费，有需要应自行调整，此处不计入搜索费用
-	"llama-3-sonar-small-32k-chat":    0.2 / 1000 * USD,
-	"llama-3-sonar-small-32k-online":  0.2 / 1000 * USD,
-	"llama-3-sonar-large-32k-chat":    1 / 1000 * USD,
-	"llama-3-sonar-large-32k-online":  1 / 1000 * USD,
+	"llama-3-sonar-small-32k-chat":   0.2 / 1000 * USD,
+	"llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
+	"llama-3-sonar-large-32k-chat":   1 / 1000 * USD,
+	"llama-3-sonar-large-32k-online": 1 / 1000 * USD,
 }
 
 var DefaultModelPrice = map[string]float64{
@@ -289,7 +289,7 @@ func GetCompletionRatio(name string) float64 {
 		}
 		return 4.0 / 3.0
 	}
-	if strings.HasPrefix(name, "gpt-4") && name != "gpt-4-all" && name != "gpt-4-gizmo-*" {
+	if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.Contains(name, "gizmo") {
 		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") || strings.HasPrefix(name, "gpt-4o") {
 			return 3
 		}