feat: refactor token estimation logic

- Introduced new OpenAI text models in `common/model.go`.
- Added `IsOpenAITextModel` function to check for OpenAI text models.
- Refactored token estimation methods across various channels to use estimated prompt tokens instead of direct prompt token counts.
- Updated related functions and structures to accommodate the new token estimation approach, enhancing overall token management.

relay/compatible_handler.go

@@ -192,9 +192,9 @@ func TextHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *types
 func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage, extraContent string) {
 	if usage == nil {
 		usage = &dto.Usage{
-			PromptTokens:     relayInfo.PromptTokens,
+			PromptTokens:     relayInfo.GetEstimatePromptTokens(),
 			CompletionTokens: 0,
-			TotalTokens:      relayInfo.PromptTokens,
+			TotalTokens:      relayInfo.GetEstimatePromptTokens(),
 		}
 		extraContent += "（可能是请求出错）"
 	}