chore: update quota calc logic (close #599) (#627)

* fix: change quota calc code (close #599)

Use float64 during calc and do math.Ceil after calc. This will result in the quota being used slightly more than the official standard, but it will be guaranteed that it will not be less.

* chore: remove blank line

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>

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

@@ -5,14 +5,14 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strconv"
+	"strings"
 	"sync"
 	"time"
-
-	"github.com/gin-gonic/gin"
 )
 
 func testChannel(channel *model.Channel, request ChatRequest) (err error, openaiErr *OpenAIError) {
@@ -50,6 +50,8 @@ 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

@@ -274,7 +274,7 @@ func init() {
 			Id:         "claude-instant-1",
 			Object:     "model",
 			Created:    1677649963,
-			OwnedBy:    "anturopic",
+			OwnedBy:    "anthropic",
 			Permission: permission,
 			Root:       "claude-instant-1",
 			Parent:     nil,
@@ -283,7 +283,7 @@ func init() {
 			Id:         "claude-2",
 			Object:     "model",
 			Created:    1677649963,
-			OwnedBy:    "anturopic",
+			OwnedBy:    "anthropic",
 			Permission: permission,
 			Root:       "claude-2",
 			Parent:     nil,
@@ -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"
@@ -414,9 +415,7 @@ 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

@@ -72,7 +72,7 @@ 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'];