ext/new-api
2
0
Fork 0
mirror of https://github.com/QuantumNous/new-api.git synced 2026-09-13 15:54:34 +00:00
Code Activity

fix(billing): reject saturated pre-consume quota

Browse Source
This commit is contained in:
CaIon
2026-07-11 13:14:21 +08:00
parent dad57a6bb8
commit 621927f710
5 changed files with 124 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
relay/helper/price.go
+28 -5
View File
@@ -32,6 +32,10 @@ func modelPriceNotConfiguredError(modelName string, userId int) error {
)
}
func preConsumeQuotaRangeError(modelName string, clamp *common.QuotaClamp) error {
return fmt.Errorf("model %s pre-consume quota is out of range: operation=%s kind=%s value=%g", modelName, clamp.Op, clamp.Kind, clamp.Original)
}
// https://docs.claude.com/en/docs/build-with-claude/prompt-caching#1-hour-cache-duration
const claudeCacheCreation1hMultiplier = 6 / 3.75
@@ -117,12 +121,20 @@ func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens
audioRatio = ratio_setting.GetAudioRatio(info.OriginModelName)
audioCompletionRatio = ratio_setting.GetAudioCompletionRatio(info.OriginModelName)
ratio := modelRatio * groupRatioInfo.GroupRatio
preConsumedQuota = common.QuotaFromFloat(float64(preConsumedTokens) * ratio)
var clamp *common.QuotaClamp
preConsumedQuota, clamp = common.QuotaFromFloatChecked(float64(preConsumedTokens) * ratio)
if clamp != nil {
return types.PriceData{}, preConsumeQuotaRangeError(info.OriginModelName, clamp)
}
} else {
if meta.ImagePriceRatio != 0 {
modelPrice = modelPrice * meta.ImagePriceRatio
}
preConsumedQuota = common.QuotaFromFloat(modelPrice * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
var clamp *common.QuotaClamp
preConsumedQuota, clamp = common.QuotaFromFloatChecked(modelPrice * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
if clamp != nil {
return types.PriceData{}, preConsumeQuotaRangeError(info.OriginModelName, clamp)
}
}
// check if free model pre-consume is disabled
@@ -199,7 +211,11 @@ func ModelPriceHelperPerCall(c *gin.Context, info *relaycommon.RelayInfo) (types
freeModel := false
if usePrice {
quota = common.QuotaFromFloat(modelPrice * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
var clamp *common.QuotaClamp
quota, clamp = common.QuotaFromFloatChecked(modelPrice * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
if clamp != nil {
return types.PriceData{}, preConsumeQuotaRangeError(info.OriginModelName, clamp)
}
if !operation_setting.GetQuotaSetting().EnableFreeModelPreConsume {
if groupRatioInfo.GroupRatio == 0 || modelPrice == 0 {
quota = 0
@@ -208,7 +224,11 @@ func ModelPriceHelperPerCall(c *gin.Context, info *relaycommon.RelayInfo) (types
}
} else {
// 按量计费：以模型倍率的一半作为预扣额度
quota = common.QuotaFromFloat(modelRatio / 2 * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
var clamp *common.QuotaClamp
quota, clamp = common.QuotaFromFloatChecked(modelRatio / 2 * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
if clamp != nil {
return types.PriceData{}, preConsumeQuotaRangeError(info.OriginModelName, clamp)
}
modelPrice = -1
if !operation_setting.GetQuotaSetting().EnableFreeModelPreConsume {
if groupRatioInfo.GroupRatio == 0 || modelRatio == 0 {
@@ -270,7 +290,10 @@ func modelPriceHelperTiered(c *gin.Context, info *relaycommon.RelayInfo, promptT
// Expression coefficients are $/1M tokens prices; convert to quota the same way per-call billing does.
quotaBeforeGroup := rawCost / 1_000_000 * common.QuotaPerUnit
preConsumedQuota := billingexpr.QuotaRound(quotaBeforeGroup * groupRatioInfo.GroupRatio)
preConsumedQuota, clamp := billingexpr.QuotaRoundChecked(quotaBeforeGroup * groupRatioInfo.GroupRatio)
if clamp != nil {
return types.PriceData{}, preConsumeQuotaRangeError(info.OriginModelName, clamp)
}
freeModel := false
if !operation_setting.GetQuotaSetting().EnableFreeModelPreConsume {
relay/helper/price_test.go
+36
View File
@@ -138,3 +138,39 @@ func TestModelPriceHelperTieredPreConsumeMaxTokensFallback(t *testing.T) {
})
}
}
func TestModelPriceHelperTieredRejectsPreConsumeOverflow(t *testing.T) {
gin.SetMode(gin.TestMode)
saved := map[string]string{}
require.NoError(t, config.GlobalConfig.SaveToDB(func(key, value string) error {
saved[key] = value
return nil
}))
t.Cleanup(func() {
require.NoError(t, config.GlobalConfig.LoadFromDB(saved))
})
require.NoError(t, config.GlobalConfig.LoadFromDB(map[string]string{
"billing_setting.billing_mode": `{"tiered-overflow-model":"tiered_expr"}`,
"billing_setting.billing_expr": `{"tiered-overflow-model":"tier(\"overflow\", p * 1000000000000000)"}`,
"group_ratio_setting.group_ratio": `{"default":1}`,
}))
recorder := httptest.NewRecorder()
ctx, _ := gin.CreateTestContext(recorder)
ctx.Request = httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
ctx.Set("group", "default")
info := &relaycommon.RelayInfo{
OriginModelName: "tiered-overflow-model",
UserGroup: "default",
UsingGroup: "default",
BillingRequestInput: &billingexpr.RequestInput{
Body: []byte(`{}`),
},
}
_, err := ModelPriceHelper(ctx, info, 1000, &types.TokenCountMeta{})
require.ErrorContains(t, err, "pre-consume quota is out of range")
}