Merge branch 'main' into fix/volcengine-image-model

dto/openai_response.go

@@ -6,6 +6,10 @@ import (
 	"one-api/types"
 )
 
+const (
+	ResponsesOutputTypeImageGenerationCall = "image_generation_call"
+)
+
 type SimpleResponse struct {
 	Usage `json:"usage"`
 	Error any `json:"error"`
@@ -273,6 +277,42 @@ func (o *OpenAIResponsesResponse) GetOpenAIError() *types.OpenAIError {
 	return GetOpenAIError(o.Error)
 }
 
+func (o *OpenAIResponsesResponse) HasImageGenerationCall() bool {
+	if len(o.Output) == 0 {
+		return false
+	}
+	for _, output := range o.Output {
+		if output.Type == ResponsesOutputTypeImageGenerationCall {
+			return true
+		}
+	}
+	return false
+}
+
+func (o *OpenAIResponsesResponse) GetQuality() string {
+	if len(o.Output) == 0 {
+		return ""
+	}
+	for _, output := range o.Output {
+		if output.Type == ResponsesOutputTypeImageGenerationCall {
+			return output.Quality
+		}
+	}
+	return ""
+}
+
+func (o *OpenAIResponsesResponse) GetSize() string {
+	if len(o.Output) == 0 {
+		return ""
+	}
+	for _, output := range o.Output {
+		if output.Type == ResponsesOutputTypeImageGenerationCall {
+			return output.Size
+		}
+	}
+	return ""
+}
+
 type IncompleteDetails struct {
 	Reasoning string `json:"reasoning"`
 }
@@ -283,6 +323,8 @@ type ResponsesOutput struct {
 	Status  string                   `json:"status"`
 	Role    string                   `json:"role"`
 	Content []ResponsesOutputContent `json:"content"`
+	Quality string                   `json:"quality"`
+	Size    string                   `json:"size"`
 }
 
 type ResponsesOutputContent struct {

relay/channel/openai/relay_responses.go

@@ -33,6 +33,12 @@ func OaiResponsesHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http
 		return nil, types.WithOpenAIError(*oaiError, resp.StatusCode)
 	}
 
+	if responsesResponse.HasImageGenerationCall() {
+		c.Set("image_generation_call", true)
+		c.Set("image_generation_call_quality", responsesResponse.GetQuality())
+		c.Set("image_generation_call_size", responsesResponse.GetSize())
+	}
+
 	// 写入新的 response body
 	service.IOCopyBytesGracefully(c, resp, responseBody)
 
@@ -80,18 +86,25 @@ func OaiResponsesStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp
 			sendResponsesStreamData(c, streamResponse, data)
 			switch streamResponse.Type {
 			case "response.completed":
-				if streamResponse.Response != nil && streamResponse.Response.Usage != nil {
+				if streamResponse.Response != nil {
-					if streamResponse.Response.Usage.InputTokens != 0 {
+					if streamResponse.Response.Usage != nil {
-						usage.PromptTokens = streamResponse.Response.Usage.InputTokens
+						if streamResponse.Response.Usage.InputTokens != 0 {
+							usage.PromptTokens = streamResponse.Response.Usage.InputTokens
+						}
+						if streamResponse.Response.Usage.OutputTokens != 0 {
+							usage.CompletionTokens = streamResponse.Response.Usage.OutputTokens
+						}
+						if streamResponse.Response.Usage.TotalTokens != 0 {
+							usage.TotalTokens = streamResponse.Response.Usage.TotalTokens
+						}
+						if streamResponse.Response.Usage.InputTokensDetails != nil {
+							usage.PromptTokensDetails.CachedTokens = streamResponse.Response.Usage.InputTokensDetails.CachedTokens
+						}
 					}
-					if streamResponse.Response.Usage.OutputTokens != 0 {
+					if streamResponse.Response.HasImageGenerationCall() {
-						usage.CompletionTokens = streamResponse.Response.Usage.OutputTokens
+						c.Set("image_generation_call", true)
-					}
+						c.Set("image_generation_call_quality", streamResponse.Response.GetQuality())
-					if streamResponse.Response.Usage.TotalTokens != 0 {
+						c.Set("image_generation_call_size", streamResponse.Response.GetSize())
-						usage.TotalTokens = streamResponse.Response.Usage.TotalTokens
-					}
-					if streamResponse.Response.Usage.InputTokensDetails != nil {
-						usage.PromptTokensDetails.CachedTokens = streamResponse.Response.Usage.InputTokensDetails.CachedTokens
 					}
 				}
 			case "response.output_text.delta":

relay/compatible_handler.go

@@ -276,6 +276,13 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage
 				fileSearchTool.CallCount, dFileSearchQuota.String())
 		}
 	}
+	var dImageGenerationCallQuota decimal.Decimal
+	var imageGenerationCallPrice float64
+	if ctx.GetBool("image_generation_call") {
+		imageGenerationCallPrice = operation_setting.GetGPTImage1PriceOnceCall(ctx.GetString("image_generation_call_quality"), ctx.GetString("image_generation_call_size"))
+		dImageGenerationCallQuota = decimal.NewFromFloat(imageGenerationCallPrice).Mul(dGroupRatio).Mul(dQuotaPerUnit)
+		extraContent += fmt.Sprintf("Image Generation Call 花费 %s", dImageGenerationCallQuota.String())
+	}
 
 	var quotaCalculateDecimal decimal.Decimal
 
@@ -331,6 +338,8 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage
 	quotaCalculateDecimal = quotaCalculateDecimal.Add(dFileSearchQuota)
 	// 添加 audio input 独立计费
 	quotaCalculateDecimal = quotaCalculateDecimal.Add(audioInputQuota)
+	// 添加 image generation call 计费
+	quotaCalculateDecimal = quotaCalculateDecimal.Add(dImageGenerationCallQuota)
 
 	quota := int(quotaCalculateDecimal.Round(0).IntPart())
 	totalTokens := promptTokens + completionTokens
@@ -429,6 +438,10 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage
 		other["audio_input_token_count"] = audioTokens
 		other["audio_input_price"] = audioInputPrice
 	}
+	if !dImageGenerationCallQuota.IsZero() {
+		other["image_generation_call"] = true
+		other["image_generation_call_price"] = imageGenerationCallPrice
+	}
 	model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
 		ChannelId:        relayInfo.ChannelId,
 		PromptTokens:     promptTokens,

setting/operation_setting/tools.go

@@ -10,6 +10,18 @@ const (
 	FileSearchPrice = 2.5
 )
 
+const (
+	GPTImage1Low1024x1024    = 0.011
+	GPTImage1Low1024x1536    = 0.016
+	GPTImage1Low1536x1024    = 0.016
+	GPTImage1Medium1024x1024 = 0.042
+	GPTImage1Medium1024x1536 = 0.063
+	GPTImage1Medium1536x1024 = 0.063
+	GPTImage1High1024x1024   = 0.167
+	GPTImage1High1024x1536   = 0.25
+	GPTImage1High1536x1024   = 0.25
+)
+
 const (
 	// Gemini Audio Input Price
 	Gemini25FlashPreviewInputAudioPrice     = 1.00
@@ -65,3 +77,31 @@ func GetGeminiInputAudioPricePerMillionTokens(modelName string) float64 {
 	}
 	return 0
 }
+
+func GetGPTImage1PriceOnceCall(quality string, size string) float64 {
+	prices := map[string]map[string]float64{
+		"low": {
+			"1024x1024": GPTImage1Low1024x1024,
+			"1024x1536": GPTImage1Low1024x1536,
+			"1536x1024": GPTImage1Low1536x1024,
+		},
+		"medium": {
+			"1024x1024": GPTImage1Medium1024x1024,
+			"1024x1536": GPTImage1Medium1024x1536,
+			"1536x1024": GPTImage1Medium1536x1024,
+		},
+		"high": {
+			"1024x1024": GPTImage1High1024x1024,
+			"1024x1536": GPTImage1High1024x1536,
+			"1536x1024": GPTImage1High1536x1024,
+		},
+	}
+
+	if qualityMap, exists := prices[quality]; exists {
+		if price, exists := qualityMap[size]; exists {
+			return price
+		}
+	}
+
+	return GPTImage1High1024x1024
+}

web/src/helpers/render.jsx

@@ -1027,6 +1027,8 @@ export function renderModelPrice(
   audioInputSeperatePrice = false,
   audioInputTokens = 0,
   audioInputPrice = 0,
+  imageGenerationCall = false,
+  imageGenerationCallPrice = 0,
 ) {
   const { ratio: effectiveGroupRatio, label: ratioLabel } = getEffectiveRatio(
     groupRatio,
@@ -1069,7 +1071,8 @@ export function renderModelPrice(
       (audioInputTokens / 1000000) * audioInputPrice * groupRatio +
       (completionTokens / 1000000) * completionRatioPrice * groupRatio +
       (webSearchCallCount / 1000) * webSearchPrice * groupRatio +
-      (fileSearchCallCount / 1000) * fileSearchPrice * groupRatio;
+      (fileSearchCallCount / 1000) * fileSearchPrice * groupRatio +
+      (imageGenerationCallPrice * groupRatio);
 
     return (
       <>
@@ -1131,7 +1134,13 @@ export function renderModelPrice(
               })}
             </p>
           )}
-          <p></p>
+          {imageGenerationCall && imageGenerationCallPrice > 0 && (
+            <p>
+              {i18next.t('图片生成调用：${{price}} / 1次', {
+                price: imageGenerationCallPrice,
+              })}
+            </p>
+          )}
           <p>
             {(() => {
               // 构建输入部分描述
@@ -1211,6 +1220,16 @@ export function renderModelPrice(
                       },
                     )
                   : '',
+                imageGenerationCall && imageGenerationCallPrice > 0
+                  ? i18next.t(
+                      ' + 图片生成调用 ${{price}} / 1次 * {{ratioType}} {{ratio}}',
+                      {
+                        price: imageGenerationCallPrice,
+                        ratio: groupRatio,
+                        ratioType: ratioLabel,
+                      },
+                    )
+                  : '',
               ].join('');
 
               return i18next.t(

web/src/hooks/usage-logs/useUsageLogsData.jsx

@@ -447,6 +447,8 @@ export const useLogsData = () => {
             other?.audio_input_seperate_price || false,
             other?.audio_input_token_count || 0,
             other?.audio_input_price || 0,
+            other?.image_generation_call || false,
+            other?.image_generation_call_price || 0,
           );
         }
         expandDataLocal.push({