|
|
@@ -139,6 +139,7 @@ var defaultModelRatio = map[string]float64{
|
|
|
"gemini-2.0-flash": 0.05,
|
|
|
"gemini-2.5-pro-exp-03-25": 0.625,
|
|
|
"gemini-2.5-pro-preview-03-25": 0.625,
|
|
|
+ "gemini-2.5-pro": 0.625,
|
|
|
"gemini-2.5-flash-preview-04-17": 0.075,
|
|
|
"gemini-2.5-flash-preview-04-17-thinking": 0.075,
|
|
|
"gemini-2.5-flash-preview-04-17-nothinking": 0.075,
|
|
|
@@ -147,6 +148,8 @@ var defaultModelRatio = map[string]float64{
|
|
|
"gemini-2.5-flash-preview-05-20-nothinking": 0.075,
|
|
|
"gemini-2.5-flash-thinking-*": 0.075, // 用于为后续所有2.5 flash thinking budget 模型设置默认倍率
|
|
|
"gemini-2.5-pro-thinking-*": 0.625, // 用于为后续所有2.5 pro thinking budget 模型设置默认倍率
|
|
|
+ "gemini-2.5-flash-lite-preview-06-17": 0.05,
|
|
|
+ "gemini-2.5-flash": 0.15,
|
|
|
"text-embedding-004": 0.001,
|
|
|
"chatglm_turbo": 0.3572, // ￥0.005 / 1k tokens
|
|
|
"chatglm_pro": 0.7143, // ￥0.01 / 1k tokens
|
|
|
@@ -487,12 +490,17 @@ func getHardcodedCompletionModelRatio(name string) (float64, bool) {
|
|
|
return 4, true
|
|
|
} else if strings.HasPrefix(name, "gemini-2.5-pro") { // 移除preview来增加兼容性，这里假设正式版的倍率和preview一致
|
|
|
return 8, true
|
|
|
- } else if strings.HasPrefix(name, "gemini-2.5-flash") { // 同上
|
|
|
- if strings.HasSuffix(name, "-nothinking") {
|
|
|
- return 4, false
|
|
|
- } else {
|
|
|
- return 3.5 / 0.6, false
|
|
|
+ } else if strings.HasPrefix(name, "gemini-2.5-flash") { // 处理不同的flash模型倍率
|
|
|
+ if strings.HasPrefix(name, "gemini-2.5-flash-preview") {
|
|
|
+ if strings.HasSuffix(name, "-nothinking") {
|
|
|
+ return 4, true
|
|
|
+ }
|
|
|
+ return 3.5 / 0.15, true
|
|
|
}
|
|
|
+ if strings.HasPrefix(name, "gemini-2.5-flash-lite-preview") {
|
|
|
+ return 4, true
|
|
|
+ }
|
|
|
+ return 2.5 / 0.3, true
|
|
|
}
|
|
|
return 4, false
|
|
|
}
|
RedwindA