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.

service/convert.go

@@ -209,7 +209,7 @@ func StreamResponseOpenAI2Claude(openAIResponse *dto.ChatCompletionsStreamRespon
 			Type:  "message",
 			Role:  "assistant",
 			Usage: &dto.ClaudeUsage{
-				InputTokens:  info.PromptTokens,
+				InputTokens:  info.GetEstimatePromptTokens(),
 				OutputTokens: 0,
 			},
 		}
@@ -734,12 +734,18 @@ func StreamResponseOpenAI2Gemini(openAIResponse *dto.ChatCompletionsStreamRespon
 	geminiResponse := &dto.GeminiChatResponse{
 		Candidates: make([]dto.GeminiChatCandidate, 0, len(openAIResponse.Choices)),
 		UsageMetadata: dto.GeminiUsageMetadata{
-			PromptTokenCount:     info.PromptTokens,
+			PromptTokenCount:     info.GetEstimatePromptTokens(),
 			CandidatesTokenCount: 0, // 流式响应中可能没有完整的 usage 信息
-			TotalTokenCount:      info.PromptTokens,
+			TotalTokenCount:      info.GetEstimatePromptTokens(),
 		},
 	}
 
+	if openAIResponse.Usage != nil {
+		geminiResponse.UsageMetadata.PromptTokenCount = openAIResponse.Usage.PromptTokens
+		geminiResponse.UsageMetadata.CandidatesTokenCount = openAIResponse.Usage.CompletionTokens
+		geminiResponse.UsageMetadata.TotalTokenCount = openAIResponse.Usage.TotalTokens
+	}
+
 	for _, choice := range openAIResponse.Choices {
 		candidate := dto.GeminiChatCandidate{
 			Index:         int64(choice.Index),