CaIon 2 лет назад
Родитель
Сommit
6fbe1fe087
1 измененных файлов с 20 добавлено и 0 удалено
  1. 20 0
      common/model-ratio.go

+ 20 - 0
common/model-ratio.go

@@ -3,6 +3,7 @@ package common
 import (
 import (
 	"encoding/json"
 	"encoding/json"
 	"strings"
 	"strings"
+	"time"
 )
 )
 
 
 // ModelRatio
 // ModelRatio
@@ -19,12 +20,15 @@ var ModelRatio = map[string]float64{
 	"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-4-1106-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":             0.75, // $0.0015 / 1K tokens
 	"gpt-3.5-turbo-0301":        0.75,
 	"gpt-3.5-turbo-0301":        0.75,
 	"gpt-3.5-turbo-0613":        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":         1.5, // $0.003 / 1K tokens
 	"gpt-3.5-turbo-16k-0613":    1.5,
 	"gpt-3.5-turbo-16k-0613":    1.5,
 	"gpt-3.5-turbo-instruct":    0.75, // $0.0015 / 1K tokens
 	"gpt-3.5-turbo-instruct":    0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo-1106":        0.5,  // $0.001 / 1K tokens
 	"text-ada-001":              0.2,
 	"text-ada-001":              0.2,
 	"text-babbage-001":          0.25,
 	"text-babbage-001":          0.25,
 	"text-curie-001":            1,
 	"text-curie-001":            1,
@@ -49,6 +53,7 @@ var ModelRatio = map[string]float64{
 	"ERNIE-Bot-4":               8.572,  // ¥0.12 / 1k tokens
 	"ERNIE-Bot-4":               8.572,  // ¥0.12 / 1k tokens
 	"Embedding-V1":              0.1429, // ¥0.002 / 1k tokens
 	"Embedding-V1":              0.1429, // ¥0.002 / 1k tokens
 	"PaLM-2":                    1,
 	"PaLM-2":                    1,
+	"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
@@ -87,9 +92,24 @@ func GetModelRatio(name string) float64 {
 
 
 func GetCompletionRatio(name string) float64 {
 func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-3.5") {
 	if strings.HasPrefix(name, "gpt-3.5") {
+		if strings.HasSuffix(name, "1106") {
+			return 2
+		}
+		if name == "gpt-3.5-turbo" || name == "gpt-3.5-turbo-16k" {
+			// TODO: clear this after 2023-12-11
+			now := time.Now()
+			// https://platform.openai.com/docs/models/continuous-model-upgrades
+			// if after 2023-12-11, use 2
+			if now.After(time.Date(2023, 12, 11, 0, 0, 0, 0, time.UTC)) {
+				return 2
+			}
+		}
 		return 1.333333
 		return 1.333333
 	}
 	}
 	if strings.HasPrefix(name, "gpt-4") {
 	if strings.HasPrefix(name, "gpt-4") {
+		if strings.HasSuffix(name, "preview") {
+			return 3
+		}
 		return 2
 		return 2
 	}
 	}
 	if strings.HasPrefix(name, "claude-instant-1") {
 	if strings.HasPrefix(name, "claude-instant-1") {