Merge pull request #79 from minhoryang/chore/new-models

[Chore] add new gpt models
bricks-cloud · Jul 8, 2024 · fa136da · fa136da
2 parents 662db32 + a1a1765
commit fa136da
Show file tree

Hide file tree

Showing 2 changed files with 48 additions and 16 deletions.
diff --git a/internal/manager/route.go b/internal/manager/route.go
@@ -96,6 +96,11 @@ func checkModelValidity(provider, model string) bool {
 
 var (
 	azureSupportedModels = []string{
+		"gpt-4o-2024-05-13",
+		"gpt-4o",
+		"gpt-4-turbo-2024-04-09",
+		"gpt-4-0125-preview",
+		"gpt-4-vision-preview",
 		"gpt-4-1106-preview",
 		"gpt-4-1106-vision-preview",
 		"gpt-4",
@@ -108,6 +113,7 @@ var (
 		"gpt-4o-2024-05-13",
 		"gpt-4o",
 		"gpt-35-turbo",
+		"gpt-35-turbo-0125",
 		"gpt-35-turbo-1106",
 		"gpt-35-turbo-0301",
 		"gpt-35-turbo-instruct",
@@ -118,6 +124,11 @@ var (
 	}
 
 	openaiSupportedModels = []string{
+		"gpt-4o-2024-05-13",
+		"gpt-4o",
+		"gpt-4-turbo-2024-04-09",
+		"gpt-4-0125-preview",
+		"gpt-4-vision-preview",
 		"gpt-4-1106-preview",
 		"gpt-4-1106-vision-preview",
 		"gpt-4",
@@ -133,6 +144,7 @@ var (
 		"gpt-4o-2024-05-13",
 		"gpt-4o",
 		"gpt-3.5-turbo",
+		"gpt-3.5-turbo-0125",
 		"gpt-3.5-turbo-1106",
 		"gpt-3.5-turbo-0301",
 		"gpt-3.5-turbo-instruct",
@@ -143,6 +155,11 @@ var (
 	}
 
 	supportedModels = []string{
+		"gpt-4o-2024-05-13",
+		"gpt-4o",
+		"gpt-4-turbo-2024-04-09",
+		"gpt-4-0125-preview",
+		"gpt-4-vision-preview",
 		"gpt-4-1106-preview",
 		"gpt-4-1106-vision-preview",
 		"gpt-4",
@@ -158,13 +175,15 @@ var (
 		"gpt-4o-2024-05-13",
 		"gpt-4o",
 		"gpt-35-turbo",
+		"gpt-35-turbo-0125",
 		"gpt-35-turbo-1106",
 		"gpt-35-turbo-0301",
 		"gpt-35-turbo-instruct",
 		"gpt-35-turbo-0613",
 		"gpt-35-turbo-16k",
 		"gpt-35-turbo-16k-0613",
 		"gpt-3.5-turbo",
+		"gpt-3.5-turbo-0125",
 		"gpt-3.5-turbo-1106",
 		"gpt-3.5-turbo-0301",
 		"gpt-3.5-turbo-instruct",
@@ -184,12 +203,18 @@ var (
 
 	chatCompletionModels = []string{
 		"gpt-35-turbo",
+		"gpt-35-turbo-0125",
 		"gpt-35-turbo-1106",
 		"gpt-35-turbo-0301",
 		"gpt-35-turbo-instruct",
 		"gpt-35-turbo-0613",
 		"gpt-35-turbo-16k",
 		"gpt-35-turbo-16k-0613",
+		"gpt-4o-2024-05-13",
+		"gpt-4o",
+		"gpt-4-turbo-2024-04-09",
+		"gpt-4-0125-preview",
+		"gpt-4-vision-preview",
 		"gpt-4-1106-preview",
 		"gpt-4-1106-vision-preview",
 		"gpt-4",
@@ -205,6 +230,7 @@ var (
 		"gpt-4o-2024-05-13",
 		"gpt-4o",
 		"gpt-3.5-turbo",
+		"gpt-3.5-turbo-0125",
 		"gpt-3.5-turbo-1106",
 		"gpt-3.5-turbo-0301",
 		"gpt-3.5-turbo-instruct",

diff --git a/internal/provider/azure/cost.go b/internal/provider/azure/cost.go
@@ -10,29 +10,35 @@ import (
 
 var AzureOpenAiPerThousandTokenCost = map[string]map[string]float64{
 	"prompt": {
-		"gpt-4o":                0.005,
-		"gpt-4o-2024-05-13":     0.005,
-		"gpt-4":                 0.03,
-		"gpt-4-32k":             0.06,
-		"gpt-4-vision":          0.06,
-		"gpt-35-turbo":          0.0015,
-		"gpt-35-turbo-instruct": 0.0015,
-		"gpt-35-turbo-16k":      0.003,
+		"gpt-4o":                 0.005,
+		"gpt-4o-2024-05-13":      0.005,
+		"gpt-4-turbo":            0.01,
+		"gpt-4-turbo-2024-04-09": 0.01,
+		"gpt-4":                  0.03,
+		"gpt-4-0125-preview":     0.03,
+		"gpt-4-32k":              0.06,
+		"gpt-4-vision":           0.06,
+		"gpt-35-turbo":           0.0015,
+		"gpt-35-turbo-instruct":  0.0015,
+		"gpt-35-turbo-16k":       0.003,
 	},
 	"embeddings": {
 		"ada":                    0.0001,
 		"text-embedding-3-large": 0.00013,
 		"text-embedding-3-small": 0.00002,
 	},
 	"completion": {
-		"gpt-4o":                0.015,
-		"gpt-4o-2024-05-13":     0.015,
-		"gpt-4":                 0.06,
-		"gpt-4-32k":             0.12,
-		"gpt-4-vision":          0.12,
-		"gpt-35-turbo":          0.002,
-		"gpt-35-turbo-instruct": 0.002,
-		"gpt-35-turbo-16k":      0.004,
+		"gpt-4o":                 0.015,
+		"gpt-4o-2024-05-13":      0.015,
+		"gpt-4-turbo":            0.03,
+		"gpt-4-turbo-2024-04-09": 0.03,
+		"gpt-4":                  0.06,
+		"gpt-4-0125-preview":     0.06,
+		"gpt-4-32k":              0.12,
+		"gpt-4-vision":           0.12,
+		"gpt-35-turbo":           0.002,
+		"gpt-35-turbo-instruct":  0.002,
+		"gpt-35-turbo-16k":       0.004,
 	},
 }