github/new-api
1
0
Fork 0
mirror of https://github.com/QuantumNous/new-api.git synced 2026-04-24 11:38:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #10 from QuantumNous/main

Browse Source 
Fork Sync: Update from parent repository
This commit is contained in:
github-actions[bot]
2025-10-01 09:46:00 +00:00
committed by GitHub
parent 991ab6440b 96b172e93b
commit c3c4e9a2fc
2 changed files with 17 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
setting/operation_setting/tools.go
View File

@@ -29,6 +29,7 @@ const (
Gemini25FlashLitePreviewInputAudioPrice = 0.50 Gemini25FlashLitePreviewInputAudioPrice = 0.50
Gemini25FlashNativeAudioInputAudioPrice = 3.00 Gemini25FlashNativeAudioInputAudioPrice = 3.00
Gemini20FlashInputAudioPrice = 0.70 Gemini20FlashInputAudioPrice = 0.70
GeminiRoboticsER15InputAudioPrice = 1.00
) )
const ( const (
@@ -74,6 +75,8 @@ func GetGeminiInputAudioPricePerMillionTokens(modelName string) float64 {
return Gemini25FlashProductionInputAudioPrice return Gemini25FlashProductionInputAudioPrice
} else if strings.HasPrefix(modelName, "gemini-2.0-flash") { } else if strings.HasPrefix(modelName, "gemini-2.0-flash") {
return Gemini20FlashInputAudioPrice return Gemini20FlashInputAudioPrice
} else if strings.HasPrefix(modelName, "gemini-robotics-er-1.5") {
return GeminiRoboticsER15InputAudioPrice
} }
return 0 return 0
} }

25
setting/ratio_setting/model_ratio.go
View File

@@ -179,6 +179,7 @@ var defaultModelRatio = map[string]float64{
"gemini-2.5-flash-lite-preview-thinking-*": 0.05, "gemini-2.5-flash-lite-preview-thinking-*": 0.05,
"gemini-2.5-flash-lite-preview-06-17": 0.05, "gemini-2.5-flash-lite-preview-06-17": 0.05,
"gemini-2.5-flash": 0.15, "gemini-2.5-flash": 0.15,
"gemini-robotics-er-1.5-preview": 0.15,
"gemini-embedding-001": 0.075, "gemini-embedding-001": 0.075,
"text-embedding-004": 0.001, "text-embedding-004": 0.001,
"chatglm_turbo": 0.3572, // ￥0.005 / 1k tokens "chatglm_turbo": 0.3572, // ￥0.005 / 1k tokens
@@ -252,17 +253,17 @@ var defaultModelRatio = map[string]float64{
"grok-vision-beta": 2.5, "grok-vision-beta": 2.5,
"grok-3-fast-beta": 2.5, "grok-3-fast-beta": 2.5,
"grok-3-mini-fast-beta": 0.3, "grok-3-mini-fast-beta": 0.3,
// submodel // submodel
"NousResearch/Hermes-4-405B-FP8": 0.8, "NousResearch/Hermes-4-405B-FP8": 0.8,
"Qwen/Qwen3-235B-A22B-Thinking-2507": 0.6, "Qwen/Qwen3-235B-A22B-Thinking-2507": 0.6,
"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": 0.8, "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": 0.8,
"Qwen/Qwen3-235B-A22B-Instruct-2507": 0.3, "Qwen/Qwen3-235B-A22B-Instruct-2507": 0.3,
"zai-org/GLM-4.5-FP8": 0.8, "zai-org/GLM-4.5-FP8": 0.8,
"openai/gpt-oss-120b": 0.5, "openai/gpt-oss-120b": 0.5,
"deepseek-ai/DeepSeek-R1-0528": 0.8, "deepseek-ai/DeepSeek-R1-0528": 0.8,
"deepseek-ai/DeepSeek-R1": 0.8, "deepseek-ai/DeepSeek-R1": 0.8,
"deepseek-ai/DeepSeek-V3-0324": 0.8, "deepseek-ai/DeepSeek-V3-0324": 0.8,
"deepseek-ai/DeepSeek-V3.1": 0.8, "deepseek-ai/DeepSeek-V3.1": 0.8,
} }
var defaultModelPrice = map[string]float64{ var defaultModelPrice = map[string]float64{
@@ -587,6 +588,8 @@ func getHardcodedCompletionModelRatio(name string) (float64, bool) {
return 4, false return 4, false
} }
return 2.5 / 0.3, false return 2.5 / 0.3, false
} else if strings.HasPrefix(name, "gemini-robotics-er-1.5") {
return 2.5 / 0.3, false
} }
return 4, false return 4, false
} }