github/sub2api
4
0
Fork 0
mirror of https://github.com/Wei-Shaw/sub2api.git synced 2026-10-29 00:10:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6514 from StarryKira/codex/anthropic-reasoning-pricing

Browse Source 
feat: add Anthropic reasoning effort and Fable 5.1 max pricing
This commit is contained in:
Wesley Liddick
2026-09-05 16:19:18 +08:00
committed by GitHub
parent c42d78e26c 8249ab37db
commit fb44e2dd09
47 changed files with 664 additions and 247 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/internal/handler/admin/channel_handler.go
+77 -71
View File
@@ -57,21 +57,22 @@ type updateChannelRequest struct {
}
type channelModelPricingRequest struct {
Platform string `json:"platform" binding:"omitempty,max=50"`
Models []string `json:"models" binding:"required,min=1,max=100"`
BillingMode string `json:"billing_mode" binding:"omitempty,oneof=token per_request image"`
InputPrice *float64 `json:"input_price" binding:"omitempty,min=0"`
OutputPrice *float64 `json:"output_price" binding:"omitempty,min=0"`
CacheWritePrice *float64 `json:"cache_write_price" binding:"omitempty,min=0"`
CacheWrite1hPrice *float64 `json:"cache_write_1h_price" binding:"omitempty,min=0"`
CacheReadPrice *float64 `json:"cache_read_price" binding:"omitempty,min=0"`
FastMultiplier *float64 `json:"fast_multiplier" binding:"omitempty,gt=0"`
FlexMultiplier *float64 `json:"flex_multiplier" binding:"omitempty,gt=0"`
ImageInputPrice *float64 `json:"image_input_price" binding:"omitempty,min=0"`
ImageOutputPrice *float64 `json:"image_output_price" binding:"omitempty,min=0"`
PerRequestPrice *float64 `json:"per_request_price" binding:"omitempty,min=0"`
Intervals []pricingIntervalRequest `json:"intervals"`
TimePricing *channelTimePricingRequest `json:"time_pricing"`
Platform string `json:"platform" binding:"omitempty,max=50"`
Models []string `json:"models" binding:"required,min=1,max=100"`
BillingMode string `json:"billing_mode" binding:"omitempty,oneof=token per_request image"`
InputPrice *float64 `json:"input_price" binding:"omitempty,min=0"`
OutputPrice *float64 `json:"output_price" binding:"omitempty,min=0"`
CacheWritePrice *float64 `json:"cache_write_price" binding:"omitempty,min=0"`
CacheWrite1hPrice *float64 `json:"cache_write_1h_price" binding:"omitempty,min=0"`
CacheReadPrice *float64 `json:"cache_read_price" binding:"omitempty,min=0"`
FastMultiplier *float64 `json:"fast_multiplier" binding:"omitempty,gt=0"`
FlexMultiplier *float64 `json:"flex_multiplier" binding:"omitempty,gt=0"`
MaxReasoningEffortMultiplier *float64 `json:"max_reasoning_effort_multiplier" binding:"omitempty,gt=0"`
ImageInputPrice *float64 `json:"image_input_price" binding:"omitempty,min=0"`
ImageOutputPrice *float64 `json:"image_output_price" binding:"omitempty,min=0"`
PerRequestPrice *float64 `json:"per_request_price" binding:"omitempty,min=0"`
Intervals []pricingIntervalRequest `json:"intervals"`
TimePricing *channelTimePricingRequest `json:"time_pricing"`
}
type channelTimePricingRequest struct {
@@ -129,22 +130,23 @@ type channelResponse struct {
}
type channelModelPricingResponse struct {
ID int64 `json:"id"`
Platform string `json:"platform"`
Models []string `json:"models"`
BillingMode string `json:"billing_mode"`
InputPrice *float64 `json:"input_price"`
OutputPrice *float64 `json:"output_price"`
CacheWritePrice *float64 `json:"cache_write_price"`
CacheWrite1hPrice *float64 `json:"cache_write_1h_price"`
CacheReadPrice *float64 `json:"cache_read_price"`
FastMultiplier *float64 `json:"fast_multiplier"`
FlexMultiplier *float64 `json:"flex_multiplier"`
ImageInputPrice *float64 `json:"image_input_price"`
ImageOutputPrice *float64 `json:"image_output_price"`
PerRequestPrice *float64 `json:"per_request_price"`
Intervals []pricingIntervalResponse `json:"intervals"`
TimePricing *channelTimePricingResponse `json:"time_pricing"`
ID int64 `json:"id"`
Platform string `json:"platform"`
Models []string `json:"models"`
BillingMode string `json:"billing_mode"`
InputPrice *float64 `json:"input_price"`
OutputPrice *float64 `json:"output_price"`
CacheWritePrice *float64 `json:"cache_write_price"`
CacheWrite1hPrice *float64 `json:"cache_write_1h_price"`
CacheReadPrice *float64 `json:"cache_read_price"`
FastMultiplier *float64 `json:"fast_multiplier"`
FlexMultiplier *float64 `json:"flex_multiplier"`
MaxReasoningEffortMultiplier *float64 `json:"max_reasoning_effort_multiplier"`
ImageInputPrice *float64 `json:"image_input_price"`
ImageOutputPrice *float64 `json:"image_output_price"`
PerRequestPrice *float64 `json:"per_request_price"`
Intervals []pricingIntervalResponse `json:"intervals"`
TimePricing *channelTimePricingResponse `json:"time_pricing"`
}
type channelTimePricingResponse struct {
@@ -258,22 +260,23 @@ func pricingToResponse(p *service.ChannelModelPricing) channelModelPricingRespon
intervals = append(intervals, intervalToResponse(iv))
}
return channelModelPricingResponse{
ID: p.ID,
Platform: platform,
Models: models,
BillingMode: billingMode,
InputPrice: p.InputPrice,
OutputPrice: p.OutputPrice,
CacheWritePrice: p.CacheWritePrice,
CacheWrite1hPrice: p.CacheWrite1hPrice,
CacheReadPrice: p.CacheReadPrice,
FastMultiplier: p.FastMultiplier,
FlexMultiplier: p.FlexMultiplier,
ImageInputPrice: p.ImageInputPrice,
ImageOutputPrice: p.ImageOutputPrice,
PerRequestPrice: p.PerRequestPrice,
Intervals: intervals,
TimePricing: timePricingToResponse(p.TimePricing),
ID: p.ID,
Platform: platform,
Models: models,
BillingMode: billingMode,
InputPrice: p.InputPrice,
OutputPrice: p.OutputPrice,
CacheWritePrice: p.CacheWritePrice,
CacheWrite1hPrice: p.CacheWrite1hPrice,
CacheReadPrice: p.CacheReadPrice,
FastMultiplier: p.FastMultiplier,
FlexMultiplier: p.FlexMultiplier,
MaxReasoningEffortMultiplier: p.MaxReasoningEffortMultiplier,
ImageInputPrice: p.ImageInputPrice,
ImageOutputPrice: p.ImageOutputPrice,
PerRequestPrice: p.PerRequestPrice,
Intervals: intervals,
TimePricing: timePricingToResponse(p.TimePricing),
}
}
@@ -350,27 +353,29 @@ func pricingRequestToService(reqs []channelModelPricingRequest, allowChannelMult
SortOrder: iv.SortOrder,
})
}
var fastMultiplier, flexMultiplier *float64
var fastMultiplier, flexMultiplier, maxReasoningEffortMultiplier *float64
if allowChannelMultipliers {
fastMultiplier = r.FastMultiplier
flexMultiplier = r.FlexMultiplier
maxReasoningEffortMultiplier = r.MaxReasoningEffortMultiplier
}
result = append(result, service.ChannelModelPricing{
Platform: platform,
Models: r.Models,
BillingMode: billingMode,
InputPrice: r.InputPrice,
OutputPrice: r.OutputPrice,
CacheWritePrice: r.CacheWritePrice,
CacheWrite1hPrice: r.CacheWrite1hPrice,
CacheReadPrice: r.CacheReadPrice,
FastMultiplier: fastMultiplier,
FlexMultiplier: flexMultiplier,
ImageInputPrice: r.ImageInputPrice,
ImageOutputPrice: r.ImageOutputPrice,
PerRequestPrice: r.PerRequestPrice,
Intervals: intervals,
TimePricing: timePricingRequestToService(r.TimePricing),
Platform: platform,
Models: r.Models,
BillingMode: billingMode,
InputPrice: r.InputPrice,
OutputPrice: r.OutputPrice,
CacheWritePrice: r.CacheWritePrice,
CacheWrite1hPrice: r.CacheWrite1hPrice,
CacheReadPrice: r.CacheReadPrice,
FastMultiplier: fastMultiplier,
FlexMultiplier: flexMultiplier,
MaxReasoningEffortMultiplier: maxReasoningEffortMultiplier,
ImageInputPrice: r.ImageInputPrice,
ImageOutputPrice: r.ImageOutputPrice,
PerRequestPrice: r.PerRequestPrice,
Intervals: intervals,
TimePricing: timePricingRequestToService(r.TimePricing),
})
}
return result
@@ -615,14 +620,15 @@ func (h *ChannelHandler) GetModelDefaultPricing(c *gin.Context) {
}
response.Success(c, gin.H{
"found": true,
"input_price": pricing.InputPricePerToken,
"output_price": pricing.OutputPricePerToken,
"cache_write_price": cacheWritePrice,
"cache_write_1h_price": cacheWrite1hPrice,
"cache_read_price": pricing.CacheReadPricePerToken,
"image_input_price": pricing.ImageInputPricePerToken,
"image_output_price": pricing.ImageOutputPricePerToken,
"found": true,
"input_price": pricing.InputPricePerToken,
"output_price": pricing.OutputPricePerToken,
"cache_write_price": cacheWritePrice,
"cache_write_1h_price": cacheWrite1hPrice,
"cache_read_price": pricing.CacheReadPricePerToken,
"max_reasoning_effort_multiplier": pricing.MaxReasoningEffortMultiplier,
"image_input_price": pricing.ImageInputPricePerToken,
"image_output_price": pricing.ImageOutputPricePerToken,
})
}
backend/internal/handler/admin/channel_handler_test.go
+13 -7
View File
@@ -453,10 +453,11 @@ func TestPricingRequestToService_TimePricingNil(t *testing.T) {
// 避免渠道倍率意外污染账号成本口径。
func TestPricingRequestToService_MultipliersGatedByFlag(t *testing.T) {
req := channelModelPricingRequest{
Models: []string{"gpt-5"},
BillingMode: "token",
FastMultiplier: float64Ptr(2.5),
FlexMultiplier: float64Ptr(0.5),
Models: []string{"gpt-5"},
BillingMode: "token",
FastMultiplier: float64Ptr(2.5),
FlexMultiplier: float64Ptr(0.5),
MaxReasoningEffortMultiplier: float64Ptr(3),
Intervals: []pricingIntervalRequest{{
MinTokens: 272000,
InputMultiplier: float64Ptr(2),
@@ -469,6 +470,7 @@ func TestPricingRequestToService_MultipliersGatedByFlag(t *testing.T) {
allowed := pricingRequestToService([]channelModelPricingRequest{req}, true)
require.Equal(t, float64Ptr(2.5), allowed[0].FastMultiplier)
require.Equal(t, float64Ptr(0.5), allowed[0].FlexMultiplier)
require.Equal(t, float64Ptr(3), allowed[0].MaxReasoningEffortMultiplier)
require.Equal(t, float64Ptr(2), allowed[0].Intervals[0].InputMultiplier)
require.Equal(t, float64Ptr(1.5), allowed[0].Intervals[0].OutputMultiplier)
require.Equal(t, float64Ptr(2), allowed[0].Intervals[0].CacheWriteMultiplier)
@@ -477,6 +479,7 @@ func TestPricingRequestToService_MultipliersGatedByFlag(t *testing.T) {
dropped := pricingRequestToService([]channelModelPricingRequest{req}, false)
require.Nil(t, dropped[0].FastMultiplier)
require.Nil(t, dropped[0].FlexMultiplier)
require.Nil(t, dropped[0].MaxReasoningEffortMultiplier)
require.Nil(t, dropped[0].Intervals[0].InputMultiplier)
require.Nil(t, dropped[0].Intervals[0].OutputMultiplier)
require.Nil(t, dropped[0].Intervals[0].CacheWriteMultiplier)
@@ -580,9 +583,10 @@ func TestGetModelDefaultPricing_ReturnsFable51CacheTTLs(t *testing.T) {
require.Equal(t, http.StatusOK, w.Code)
var body struct {
Data struct {
Found bool `json:"found"`
CacheWritePrice float64 `json:"cache_write_price"`
CacheWrite1hPrice *float64 `json:"cache_write_1h_price"`
Found bool `json:"found"`
CacheWritePrice float64 `json:"cache_write_price"`
CacheWrite1hPrice *float64 `json:"cache_write_1h_price"`
MaxReasoningEffortMultiplier *float64 `json:"max_reasoning_effort_multiplier"`
} `json:"data"`
}
require.NoError(t, json.Unmarshal(w.Body.Bytes(), &body))
@@ -590,6 +594,8 @@ func TestGetModelDefaultPricing_ReturnsFable51CacheTTLs(t *testing.T) {
require.InDelta(t, 12.5e-6, body.Data.CacheWritePrice, 1e-12)
require.NotNil(t, body.Data.CacheWrite1hPrice)
require.InDelta(t, 20e-6, *body.Data.CacheWrite1hPrice, 1e-12)
require.NotNil(t, body.Data.MaxReasoningEffortMultiplier)
require.Equal(t, 3.0, *body.Data.MaxReasoningEffortMultiplier)
}
func TestGetModelDefaultPricing_OmitsUnsupportedCache1hPrice(t *testing.T) {
backend/internal/handler/admin/group_handler.go
+3 -3
View File
@@ -158,11 +158,11 @@ type CreateGroupRequest struct {
CodexModelsManifestConfig service.GroupCodexModelsManifestConfig `json:"codex_models_manifest_config"`
// 分组 RPM 上限（0 = 不限制）
RPMLimit int `json:"rpm_limit"`
// OpenAI/Codex 请求推理强度上限，空字符串表示不限制。
// Anthropic/OpenAI 请求推理强度上限，空字符串表示不限制。
MaxReasoningEffort string `json:"max_reasoning_effort"`
// 超过上限时的访问控制：downgrade（默认）或 deny。
MaxReasoningEffortOverLimit string `json:"max_reasoning_effort_over_limit"`
// OpenAI/Codex 推理强度映射，可按模型精确名、前缀或后缀限定。
// Anthropic/OpenAI 推理强度映射，可按模型精确名、前缀或后缀限定。
ReasoningEffortMappings []service.ReasoningEffortMapping `json:"reasoning_effort_mappings"`
// 从指定分组复制账号（创建后自动绑定）
CopyAccountsFromGroupIDs []int64 `json:"copy_accounts_from_group_ids"`
@@ -233,7 +233,7 @@ type UpdateGroupRequest struct {
CodexModelsManifestConfig *service.GroupCodexModelsManifestConfig `json:"codex_models_manifest_config"`
// 分组 RPM 上限（0 = 不限制）；nil 表示未提供不改动
RPMLimit *int `json:"rpm_limit"`
// OpenAI/Codex 请求推理强度上限；空字符串清除，nil 不修改。
// Anthropic/OpenAI 请求推理强度上限；空字符串清除，nil 不修改。
MaxReasoningEffort *string `json:"max_reasoning_effort"`
// 超过上限时的访问控制；空字符串视为 downgrade，nil 不修改。
MaxReasoningEffortOverLimit *string `json:"max_reasoning_effort_over_limit"`