cneicy
a5f7b8e586
Publish Docker image (Multi-arch) / Build & push (amd64) (push) Failing after 1m40s
Release (Linux, macOS, Windows) / Linux Release (push) Failing after 42m16s
Publish Docker image (Multi-arch) / Build & push (arm64) (push) Canceled after 0s
Release (Linux, macOS, Windows) / macOS Release (push) Canceled after 0s
Release (Linux, macOS, Windows) / Windows Release (push) Canceled after 0s
Publish Docker image (Multi-arch) / Create multi-arch manifests (push) Canceled after 0s
Sync production source including routing, billing, Astra detection and public uptime. Update custom build instructions and license packaging.
187 lines
7.0 KiB
Go
187 lines
7.0 KiB
Go
package ratio_setting
|
|
|
|
import (
|
|
"github.com/QuantumNous/new-api/types"
|
|
)
|
|
|
|
const (
|
|
DefaultCacheRatio = 1.0
|
|
DefaultCreateCacheRatio = 1.25
|
|
)
|
|
|
|
var defaultCacheRatio = map[string]float64{
|
|
"gemini-3-flash-preview": 0.1,
|
|
"gemini-3-pro-preview": 0.1,
|
|
"gemini-3.1-pro-preview": 0.1,
|
|
"gpt-4": 0.5,
|
|
"o1": 0.5,
|
|
"o1-2024-12-17": 0.5,
|
|
"o1-preview-2024-09-12": 0.5,
|
|
"o1-preview": 0.5,
|
|
"o1-mini-2024-09-12": 0.5,
|
|
"o1-mini": 0.5,
|
|
"o3-mini": 0.5,
|
|
"o3-mini-2025-01-31": 0.5,
|
|
"gpt-4o-2024-11-20": 0.5,
|
|
"gpt-4o-2024-08-06": 0.5,
|
|
"gpt-4o": 0.5,
|
|
"gpt-4o-mini-2024-07-18": 0.5,
|
|
"gpt-4o-mini": 0.5,
|
|
"gpt-4o-realtime-preview": 0.5,
|
|
"gpt-4o-mini-realtime-preview": 0.5,
|
|
"gpt-4.5-preview": 0.5,
|
|
"gpt-4.5-preview-2025-02-27": 0.5,
|
|
"gpt-4.1": 0.25,
|
|
"gpt-4.1-mini": 0.25,
|
|
"gpt-4.1-nano": 0.25,
|
|
"gpt-5": 0.1,
|
|
"gpt-5-2025-08-07": 0.1,
|
|
"gpt-5-chat-latest": 0.1,
|
|
"gpt-5-mini": 0.1,
|
|
"gpt-5-mini-2025-08-07": 0.1,
|
|
"gpt-5-nano": 0.1,
|
|
"gpt-5-nano-2025-08-07": 0.1,
|
|
"deepseek-chat": 0.25,
|
|
"deepseek-reasoner": 0.25,
|
|
"deepseek-coder": 0.25,
|
|
"claude-3-sonnet-20240229": 0.1,
|
|
"claude-3-opus-20240229": 0.1,
|
|
"claude-3-haiku-20240307": 0.1,
|
|
"claude-3-5-haiku-20241022": 0.1,
|
|
"claude-haiku-4-5-20251001": 0.1,
|
|
"claude-3-5-sonnet-20240620": 0.1,
|
|
"claude-3-5-sonnet-20241022": 0.1,
|
|
"claude-3-7-sonnet-20250219": 0.1,
|
|
"claude-3-7-sonnet-20250219-thinking": 0.1,
|
|
"claude-sonnet-4-20250514": 0.1,
|
|
"claude-sonnet-4-20250514-thinking": 0.1,
|
|
"claude-opus-4-20250514": 0.1,
|
|
"claude-opus-4-20250514-thinking": 0.1,
|
|
"claude-opus-4-1-20250805": 0.1,
|
|
"claude-opus-4-1-20250805-thinking": 0.1,
|
|
"claude-sonnet-4-5-20250929": 0.1,
|
|
"claude-sonnet-4-5-20250929-thinking": 0.1,
|
|
"claude-opus-4-5-20251101": 0.1,
|
|
"claude-opus-4-5-20251101-thinking": 0.1,
|
|
"claude-opus-4-6": 0.1,
|
|
"claude-opus-4-6-thinking": 0.1,
|
|
"claude-opus-4-6-max": 0.1,
|
|
"claude-opus-4-6-high": 0.1,
|
|
"claude-opus-4-6-medium": 0.1,
|
|
"claude-opus-4-6-low": 0.1,
|
|
"claude-opus-4-7": 0.1,
|
|
"claude-opus-4-7-thinking": 0.1,
|
|
"claude-opus-4-7-max": 0.1,
|
|
"claude-opus-4-7-xhigh": 0.1,
|
|
"claude-opus-4-7-high": 0.1,
|
|
"claude-opus-4-7-medium": 0.1,
|
|
"claude-opus-4-7-low": 0.1,
|
|
"claude-opus-4-8": 0.1,
|
|
"claude-opus-4-8-thinking": 0.1,
|
|
"claude-opus-4-8-max": 0.1,
|
|
"claude-opus-4-8-xhigh": 0.1,
|
|
"claude-opus-4-8-high": 0.1,
|
|
"claude-opus-4-8-medium": 0.1,
|
|
"claude-opus-4-8-low": 0.1,
|
|
}
|
|
|
|
var defaultCreateCacheRatio = map[string]float64{
|
|
"gpt-5.6-sol": 1.25,
|
|
"gpt-5.6-terra": 1.25,
|
|
"gpt-5.6-luna": 1.25,
|
|
"claude-3-sonnet-20240229": 1.25,
|
|
"claude-3-opus-20240229": 1.25,
|
|
"claude-3-haiku-20240307": 1.25,
|
|
"claude-3-5-haiku-20241022": 1.25,
|
|
"claude-haiku-4-5-20251001": 1.25,
|
|
"claude-3-5-sonnet-20240620": 1.25,
|
|
"claude-3-5-sonnet-20241022": 1.25,
|
|
"claude-3-7-sonnet-20250219": 1.25,
|
|
"claude-3-7-sonnet-20250219-thinking": 1.25,
|
|
"claude-sonnet-4-20250514": 1.25,
|
|
"claude-sonnet-4-20250514-thinking": 1.25,
|
|
"claude-opus-4-20250514": 1.25,
|
|
"claude-opus-4-20250514-thinking": 1.25,
|
|
"claude-opus-4-1-20250805": 1.25,
|
|
"claude-opus-4-1-20250805-thinking": 1.25,
|
|
"claude-sonnet-4-5-20250929": 1.25,
|
|
"claude-sonnet-4-5-20250929-thinking": 1.25,
|
|
"claude-opus-4-5-20251101": 1.25,
|
|
"claude-opus-4-5-20251101-thinking": 1.25,
|
|
"claude-opus-4-6": 1.25,
|
|
"claude-opus-4-6-thinking": 1.25,
|
|
"claude-opus-4-6-max": 1.25,
|
|
"claude-opus-4-6-high": 1.25,
|
|
"claude-opus-4-6-medium": 1.25,
|
|
"claude-opus-4-6-low": 1.25,
|
|
"claude-opus-4-7": 1.25,
|
|
"claude-opus-4-7-thinking": 1.25,
|
|
"claude-opus-4-7-max": 1.25,
|
|
"claude-opus-4-7-xhigh": 1.25,
|
|
"claude-opus-4-7-high": 1.25,
|
|
"claude-opus-4-7-medium": 1.25,
|
|
"claude-opus-4-7-low": 1.25,
|
|
"claude-opus-4-8": 1.25,
|
|
"claude-opus-4-8-thinking": 1.25,
|
|
"claude-opus-4-8-max": 1.25,
|
|
"claude-opus-4-8-xhigh": 1.25,
|
|
"claude-opus-4-8-high": 1.25,
|
|
"claude-opus-4-8-medium": 1.25,
|
|
"claude-opus-4-8-low": 1.25,
|
|
}
|
|
|
|
//var defaultCreateCacheRatio = map[string]float64{}
|
|
|
|
var cacheRatioMap = types.NewRWMap[string, float64]()
|
|
var createCacheRatioMap = types.NewRWMap[string, float64]()
|
|
|
|
// GetCacheRatioMap returns a copy of the cache ratio map
|
|
func GetCacheRatioMap() map[string]float64 {
|
|
return cacheRatioMap.ReadAll()
|
|
}
|
|
|
|
// CacheRatio2JSONString converts the cache ratio map to a JSON string
|
|
func CacheRatio2JSONString() string {
|
|
return cacheRatioMap.MarshalJSONString()
|
|
}
|
|
|
|
// CreateCacheRatio2JSONString converts the create cache ratio map to a JSON string
|
|
func CreateCacheRatio2JSONString() string {
|
|
return createCacheRatioMap.MarshalJSONString()
|
|
}
|
|
|
|
// UpdateCacheRatioByJSONString updates the cache ratio map from a JSON string
|
|
func UpdateCacheRatioByJSONString(jsonStr string) error {
|
|
return types.LoadFromJsonStringWithCallback(cacheRatioMap, jsonStr, InvalidateExposedDataCache)
|
|
}
|
|
|
|
// UpdateCreateCacheRatioByJSONString updates the create cache ratio map from a JSON string
|
|
func UpdateCreateCacheRatioByJSONString(jsonStr string) error {
|
|
return types.LoadFromJsonStringWithCallback(createCacheRatioMap, jsonStr, InvalidateExposedDataCache)
|
|
}
|
|
|
|
// GetCacheRatio returns the cache ratio for a model
|
|
func GetCacheRatio(name string) (float64, bool) {
|
|
ratio, ok := cacheRatioMap.Get(name)
|
|
if !ok {
|
|
return DefaultCacheRatio, false
|
|
}
|
|
return ratio, true
|
|
}
|
|
|
|
func GetCreateCacheRatio(name string) (float64, bool) {
|
|
ratio, ok := createCacheRatioMap.Get(name)
|
|
if !ok {
|
|
return DefaultCreateCacheRatio, false
|
|
}
|
|
return ratio, true
|
|
}
|
|
|
|
func GetCacheRatioCopy() map[string]float64 {
|
|
return cacheRatioMap.ReadAll()
|
|
}
|
|
|
|
func GetCreateCacheRatioCopy() map[string]float64 {
|
|
return createCacheRatioMap.ReadAll()
|
|
}
|