feat: 算力引擎 Go 后端核心（new-api）
- 统一 OpenAI 兼容 /v1 中继 + 渠道/额度/令牌/流水 - 各领域包：relay 模型网关、model 数据层、controller 管理 API
This commit is contained in:
@@ -0,0 +1,337 @@
|
||||
package helper
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
|
||||
"github.com/QuantumNous/new-api/common"
|
||||
"github.com/QuantumNous/new-api/logger"
|
||||
"github.com/QuantumNous/new-api/model"
|
||||
"github.com/QuantumNous/new-api/pkg/billingexpr"
|
||||
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
||||
"github.com/QuantumNous/new-api/relaykit/types"
|
||||
"github.com/QuantumNous/new-api/setting/billing_setting"
|
||||
"github.com/QuantumNous/new-api/setting/operation_setting"
|
||||
"github.com/QuantumNous/new-api/setting/ratio_setting"
|
||||
hosttypes "github.com/QuantumNous/new-api/types"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
)
|
||||
|
||||
func modelPriceNotConfiguredError(modelName string, userId int) error {
|
||||
if model.IsAdmin(userId) {
|
||||
return fmt.Errorf(
|
||||
"模型 %s 的价格未配置。请前往「系统设置 → 运营设置」开启自用模式，或在「系统设置 → 分组与模型定价设置」中为该模型配置价格；"+
|
||||
"Model %s price not configured. Go to System Settings → Operation Settings to enable self-use mode, or configure the model price in System Settings → Group & Model Pricing.",
|
||||
modelName, modelName,
|
||||
)
|
||||
}
|
||||
return fmt.Errorf(
|
||||
"模型 %s 的价格尚未由管理员配置，暂时无法使用，请联系站点管理员开启该模型；"+
|
||||
"Model %s has not been priced by the administrator yet. Please contact the site administrator to enable this model.",
|
||||
modelName, modelName,
|
||||
)
|
||||
}
|
||||
|
||||
// https://docs.claude.com/en/docs/build-with-claude/prompt-caching#1-hour-cache-duration
|
||||
const claudeCacheCreation1hMultiplier = 6 / 3.75
|
||||
|
||||
// defaultTieredPreConsumeMaxTokens is the fallback completion-token estimate
|
||||
// used for tiered expression pre-consume when the client omits max_tokens, so
|
||||
// the pre-consumed quota still reflects a plausible output cost in paid groups.
|
||||
const defaultTieredPreConsumeMaxTokens = 8192
|
||||
|
||||
// HandleGroupRatio checks for "auto_group" in the context and updates the group ratio and relayInfo.UsingGroup if present
|
||||
func HandleGroupRatio(ctx *gin.Context, relayInfo *relaycommon.RelayInfo) hosttypes.GroupRatioInfo {
|
||||
groupRatioInfo := hosttypes.GroupRatioInfo{
|
||||
GroupRatio: 1.0, // default ratio
|
||||
GroupSpecialRatio: -1,
|
||||
}
|
||||
|
||||
// check auto group
|
||||
autoGroup, exists := ctx.Get("auto_group")
|
||||
if exists {
|
||||
logger.LogDebug(ctx, "final group: %s", autoGroup)
|
||||
relayInfo.UsingGroup = autoGroup.(string)
|
||||
}
|
||||
|
||||
// check user group special ratio
|
||||
userGroupRatio, ok := ratio_setting.GetGroupGroupRatio(relayInfo.UserGroup, relayInfo.UsingGroup)
|
||||
if ok {
|
||||
// user group special ratio
|
||||
groupRatioInfo.GroupSpecialRatio = userGroupRatio
|
||||
groupRatioInfo.GroupRatio = userGroupRatio
|
||||
groupRatioInfo.HasSpecialRatio = true
|
||||
} else {
|
||||
// normal group ratio
|
||||
groupRatioInfo.GroupRatio = ratio_setting.GetGroupRatio(relayInfo.UsingGroup)
|
||||
}
|
||||
|
||||
return groupRatioInfo
|
||||
}
|
||||
|
||||
func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens int, meta *types.TokenCountMeta) (hosttypes.PriceData, error) {
|
||||
modelPrice, usePrice := ratio_setting.GetModelPrice(info.OriginModelName, false)
|
||||
|
||||
groupRatioInfo := HandleGroupRatio(c, info)
|
||||
|
||||
// Check if this model uses tiered_expr billing
|
||||
if billing_setting.GetBillingMode(info.OriginModelName) == billing_setting.BillingModeTieredExpr {
|
||||
return modelPriceHelperTiered(c, info, promptTokens, meta, groupRatioInfo)
|
||||
}
|
||||
|
||||
var preConsumedQuota int
|
||||
var modelRatio float64
|
||||
var completionRatio float64
|
||||
var cacheRatio float64
|
||||
var imageRatio float64
|
||||
var cacheCreationRatio float64
|
||||
var cacheCreationRatio5m float64
|
||||
var cacheCreationRatio1h float64
|
||||
var audioRatio float64
|
||||
var audioCompletionRatio float64
|
||||
var freeModel bool
|
||||
if !usePrice {
|
||||
preConsumedTokens := common.Max(promptTokens, common.PreConsumedQuota)
|
||||
if meta.MaxTokens != 0 {
|
||||
preConsumedTokens += meta.MaxTokens
|
||||
}
|
||||
var success bool
|
||||
var matchName string
|
||||
modelRatio, success, matchName = ratio_setting.GetModelRatio(info.OriginModelName)
|
||||
if !success {
|
||||
acceptUnsetRatio := false
|
||||
if info.UserSetting.AcceptUnsetRatioModel {
|
||||
acceptUnsetRatio = true
|
||||
}
|
||||
if !acceptUnsetRatio {
|
||||
return hosttypes.PriceData{}, modelPriceNotConfiguredError(matchName, info.UserId)
|
||||
}
|
||||
}
|
||||
completionRatio = ratio_setting.GetCompletionRatio(info.OriginModelName)
|
||||
cacheRatio, _ = ratio_setting.GetCacheRatio(info.OriginModelName)
|
||||
cacheCreationRatio, _ = ratio_setting.GetCreateCacheRatio(info.OriginModelName)
|
||||
cacheCreationRatio5m = cacheCreationRatio
|
||||
// 固定1h和5min缓存写入价格的比例
|
||||
cacheCreationRatio1h = cacheCreationRatio * claudeCacheCreation1hMultiplier
|
||||
imageRatio, _ = ratio_setting.GetImageRatio(info.OriginModelName)
|
||||
audioRatio = ratio_setting.GetAudioRatio(info.OriginModelName)
|
||||
audioCompletionRatio = ratio_setting.GetAudioCompletionRatio(info.OriginModelName)
|
||||
ratio := modelRatio * groupRatioInfo.GroupRatio
|
||||
quota, err := common.QuotaFromFloatStrict(float64(preConsumedTokens) * ratio)
|
||||
if err != nil {
|
||||
return hosttypes.PriceData{}, err
|
||||
}
|
||||
preConsumedQuota = quota
|
||||
} else {
|
||||
if meta.ImagePriceRatio != 0 {
|
||||
modelPrice = modelPrice * meta.ImagePriceRatio
|
||||
}
|
||||
}
|
||||
|
||||
// check if free model pre-consume is disabled
|
||||
if !operation_setting.GetQuotaSetting().EnableFreeModelPreConsume {
|
||||
// if model price or ratio is 0, do not pre-consume quota
|
||||
if groupRatioInfo.GroupRatio == 0 {
|
||||
preConsumedQuota = 0
|
||||
freeModel = true
|
||||
} else if usePrice {
|
||||
if modelPrice == 0 {
|
||||
preConsumedQuota = 0
|
||||
freeModel = true
|
||||
}
|
||||
} else {
|
||||
if modelRatio == 0 {
|
||||
preConsumedQuota = 0
|
||||
freeModel = true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
priceData := hosttypes.PriceData{
|
||||
FreeModel: freeModel,
|
||||
ModelPrice: modelPrice,
|
||||
ModelRatio: modelRatio,
|
||||
CompletionRatio: completionRatio,
|
||||
GroupRatioInfo: groupRatioInfo,
|
||||
UsePrice: usePrice,
|
||||
CacheRatio: cacheRatio,
|
||||
ImageRatio: imageRatio,
|
||||
AudioRatio: audioRatio,
|
||||
AudioCompletionRatio: audioCompletionRatio,
|
||||
CacheCreationRatio: cacheCreationRatio,
|
||||
CacheCreation5mRatio: cacheCreationRatio5m,
|
||||
CacheCreation1hRatio: cacheCreationRatio1h,
|
||||
QuotaToPreConsume: preConsumedQuota,
|
||||
}
|
||||
if usePrice {
|
||||
for name, ratio := range meta.BillingRatios {
|
||||
priceData.AddOtherRatio(name, ratio)
|
||||
}
|
||||
quotaToPreConsume := priceData.ApplyOtherRatiosToFloat(modelPrice * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
|
||||
quota, err := common.QuotaFromFloatStrict(quotaToPreConsume)
|
||||
if err != nil {
|
||||
return hosttypes.PriceData{}, err
|
||||
}
|
||||
priceData.QuotaToPreConsume = quota
|
||||
}
|
||||
|
||||
if common.DebugEnabled {
|
||||
logger.LogDebug(c, "model_price_helper result: %s", priceData.ToSetting())
|
||||
}
|
||||
info.PriceData = priceData
|
||||
return priceData, nil
|
||||
}
|
||||
|
||||
// ModelPriceHelperPerCall 按次/按量计费的 PriceHelper (MJ、Task)
|
||||
func ModelPriceHelperPerCall(c *gin.Context, info *relaycommon.RelayInfo) (hosttypes.PriceData, error) {
|
||||
groupRatioInfo := HandleGroupRatio(c, info)
|
||||
|
||||
modelPrice, success := ratio_setting.GetModelPrice(info.OriginModelName, true)
|
||||
usePrice := success
|
||||
var modelRatio float64
|
||||
|
||||
if !success {
|
||||
defaultPrice, ok := ratio_setting.GetDefaultModelPriceMap()[info.OriginModelName]
|
||||
if ok {
|
||||
modelPrice = defaultPrice
|
||||
usePrice = true
|
||||
} else {
|
||||
var ratioSuccess bool
|
||||
var matchName string
|
||||
modelRatio, ratioSuccess, matchName = ratio_setting.GetModelRatio(info.OriginModelName)
|
||||
acceptUnsetRatio := false
|
||||
if info.UserSetting.AcceptUnsetRatioModel {
|
||||
acceptUnsetRatio = true
|
||||
}
|
||||
if !ratioSuccess && !acceptUnsetRatio {
|
||||
return hosttypes.PriceData{}, modelPriceNotConfiguredError(matchName, info.UserId)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
var quota int
|
||||
freeModel := false
|
||||
|
||||
if usePrice {
|
||||
var err error
|
||||
quota, err = common.QuotaFromFloatStrict(modelPrice * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
|
||||
if err != nil {
|
||||
return hosttypes.PriceData{}, err
|
||||
}
|
||||
if !operation_setting.GetQuotaSetting().EnableFreeModelPreConsume {
|
||||
if groupRatioInfo.GroupRatio == 0 || modelPrice == 0 {
|
||||
quota = 0
|
||||
freeModel = true
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// 按量计费：以模型倍率的一半作为预扣额度
|
||||
var err error
|
||||
quota, err = common.QuotaFromFloatStrict(modelRatio / 2 * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
|
||||
if err != nil {
|
||||
return hosttypes.PriceData{}, err
|
||||
}
|
||||
modelPrice = -1
|
||||
if !operation_setting.GetQuotaSetting().EnableFreeModelPreConsume {
|
||||
if groupRatioInfo.GroupRatio == 0 || modelRatio == 0 {
|
||||
quota = 0
|
||||
freeModel = true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
priceData := hosttypes.PriceData{
|
||||
FreeModel: freeModel,
|
||||
ModelPrice: modelPrice,
|
||||
ModelRatio: modelRatio,
|
||||
UsePrice: usePrice,
|
||||
Quota: quota,
|
||||
GroupRatioInfo: groupRatioInfo,
|
||||
}
|
||||
return priceData, nil
|
||||
}
|
||||
|
||||
func HasModelBillingConfig(modelName string) bool {
|
||||
if _, ok := ratio_setting.GetModelPrice(modelName, false); ok {
|
||||
return true
|
||||
}
|
||||
if _, ok, _ := ratio_setting.GetModelRatio(modelName); ok {
|
||||
return true
|
||||
}
|
||||
if billing_setting.GetBillingMode(modelName) != billing_setting.BillingModeTieredExpr {
|
||||
return false
|
||||
}
|
||||
expr, ok := billing_setting.GetBillingExpr(modelName)
|
||||
return ok && strings.TrimSpace(expr) != ""
|
||||
}
|
||||
|
||||
func modelPriceHelperTiered(c *gin.Context, info *relaycommon.RelayInfo, promptTokens int, meta *types.TokenCountMeta, groupRatioInfo hosttypes.GroupRatioInfo) (hosttypes.PriceData, error) {
|
||||
exprStr, ok := billing_setting.GetBillingExpr(info.OriginModelName)
|
||||
if !ok {
|
||||
return hosttypes.PriceData{}, fmt.Errorf("model %s is configured as tiered_expr but has no billing expression", info.OriginModelName)
|
||||
}
|
||||
|
||||
estimatedCompletionTokens := meta.MaxTokens
|
||||
if estimatedCompletionTokens == 0 && groupRatioInfo.GroupRatio != 0 {
|
||||
estimatedCompletionTokens = defaultTieredPreConsumeMaxTokens
|
||||
}
|
||||
|
||||
requestInput, err := ResolveIncomingBillingExprRequestInput(c, info)
|
||||
if err != nil {
|
||||
return hosttypes.PriceData{}, err
|
||||
}
|
||||
|
||||
rawCost, trace, err := billingexpr.RunExprWithRequest(exprStr, billingexpr.TokenParams{
|
||||
P: float64(promptTokens),
|
||||
C: float64(estimatedCompletionTokens),
|
||||
Len: float64(promptTokens),
|
||||
}, requestInput)
|
||||
if err != nil {
|
||||
return hosttypes.PriceData{}, fmt.Errorf("model %s tiered expr run failed: %w", info.OriginModelName, err)
|
||||
}
|
||||
|
||||
// Expression coefficients are $/1M tokens prices; convert to quota the same way per-call billing does.
|
||||
quotaBeforeGroup := rawCost / 1_000_000 * common.QuotaPerUnit
|
||||
preConsumedQuota, err := billingexpr.QuotaRoundStrict(quotaBeforeGroup * groupRatioInfo.GroupRatio)
|
||||
if err != nil {
|
||||
return hosttypes.PriceData{}, err
|
||||
}
|
||||
|
||||
freeModel := false
|
||||
if !operation_setting.GetQuotaSetting().EnableFreeModelPreConsume {
|
||||
if groupRatioInfo.GroupRatio == 0 {
|
||||
preConsumedQuota = 0
|
||||
freeModel = true
|
||||
}
|
||||
}
|
||||
|
||||
exprHash := billingexpr.ExprHashString(exprStr)
|
||||
snapshot := &billingexpr.BillingSnapshot{
|
||||
BillingMode: billing_setting.BillingModeTieredExpr,
|
||||
ModelName: info.OriginModelName,
|
||||
ExprString: exprStr,
|
||||
ExprHash: exprHash,
|
||||
GroupRatio: groupRatioInfo.GroupRatio,
|
||||
EstimatedPromptTokens: promptTokens,
|
||||
EstimatedCompletionTokens: estimatedCompletionTokens,
|
||||
EstimatedQuotaBeforeGroup: quotaBeforeGroup,
|
||||
EstimatedQuotaAfterGroup: preConsumedQuota,
|
||||
EstimatedTier: trace.MatchedTier,
|
||||
QuotaPerUnit: common.QuotaPerUnit,
|
||||
ExprVersion: billingexpr.ExprVersion(exprStr),
|
||||
}
|
||||
info.TieredBillingSnapshot = snapshot
|
||||
info.BillingRequestInput = &requestInput
|
||||
|
||||
priceData := hosttypes.PriceData{
|
||||
FreeModel: freeModel,
|
||||
GroupRatioInfo: groupRatioInfo,
|
||||
QuotaToPreConsume: preConsumedQuota,
|
||||
}
|
||||
|
||||
logger.LogDebug(c, "model_price_helper_tiered result: model=%s preConsume=%d quotaBeforeGroup=%.2f groupRatio=%.2f tier=%s", info.OriginModelName, preConsumedQuota, quotaBeforeGroup, groupRatioInfo.GroupRatio, trace.MatchedTier)
|
||||
|
||||
info.PriceData = priceData
|
||||
return priceData, nil
|
||||
}
|
||||
Reference in New Issue
Block a user