Added chatglm_turbo model, fixed URL duplication,

improved quota calculation, and updated
localModels in EditChannel.js

common/model-ratio.go

@@ -49,6 +49,7 @@ var ModelRatio = map[string]float64{
 	"ERNIE-Bot-4":               8.572,  // ￥0.12 / 1k tokens
 	"Embedding-V1":              0.1429, // ￥0.002 / 1k tokens
 	"PaLM-2":                    1,
+	"chatglm_turbo":             0.3572, // ￥0.005 / 1k tokens
 	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
 	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
 	"chatglm_lite":              0.1429, // ￥0.002 / 1k tokens

controller/channel-test.go

@@ -7,6 +7,7 @@ import (
 	"errors"
 	"fmt"
 	"log"
+	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
@@ -14,8 +15,6 @@ import (
 	"strings"
 	"sync"
 	"time"
-
-	"github.com/gin-gonic/gin"
 )
 
 func testChannel(channel *model.Channel, request ChatRequest) (err error, openaiErr *OpenAIError) {
@@ -53,6 +52,8 @@ func testChannel(channel *model.Channel, request ChatRequest) (err error, openai
 		}
 		requestURL += "/v1/chat/completions"
 	}
+	// for Cloudflare AI gateway: https://github.com/songquanpeng/one-api/pull/639
+	requestURL = strings.Replace(requestURL, "/v1/v1", "/v1", 1)
 
 	jsonData, err := json.Marshal(request)
 	if err != nil {

controller/model.go

@@ -333,6 +333,15 @@ func init() {
 			Root:       "PaLM-2",
 			Parent:     nil,
 		},
+		{
+			Id:         "chatglm_turbo",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "zhipu",
+			Permission: permission,
+			Root:       "chatglm_turbo",
+			Parent:     nil,
+		},
 		{
 			Id:         "chatglm_pro",
 			Object:     "model",

controller/relay-text.go

@@ -7,6 +7,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"math"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
@@ -433,9 +434,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 				completionRatio := common.GetCompletionRatio(textRequest.Model)
 				promptTokens = textResponse.Usage.PromptTokens
 				completionTokens = textResponse.Usage.CompletionTokens
-
-				quota = promptTokens + int(float64(completionTokens)*completionRatio)
-				quota = int(float64(quota) * ratio)
+				quota = int(math.Ceil((float64(promptTokens) + float64(completionTokens)*completionRatio) * ratio))
 				if ratio != 0 && quota <= 0 {
 					quota = 1
 				}

web/src/pages/Channel/EditChannel.js

@@ -74,7 +74,7 @@ const EditChannel = () => {
           localModels = ['qwen-turbo', 'qwen-plus', 'text-embedding-v1'];
           break;
         case 16:
-          localModels = ['chatglm_pro', 'chatglm_std', 'chatglm_lite'];
+          localModels = ['chatglm_turbo', 'chatglm_pro', 'chatglm_std', 'chatglm_lite'];
           break;
         case 18:
           localModels = ['SparkDesk'];