mirror of
https://github.com/songquanpeng/one-api.git
synced 2025-11-10 10:33:41 +08:00
Merge remote-tracking branch 'origin/upstream/main'
This commit is contained in:
@@ -7,29 +7,6 @@ import (
|
||||
"time"
|
||||
)
|
||||
|
||||
var DalleSizeRatios = map[string]map[string]float64{
|
||||
"dall-e-2": {
|
||||
"256x256": 1,
|
||||
"512x512": 1.125,
|
||||
"1024x1024": 1.25,
|
||||
},
|
||||
"dall-e-3": {
|
||||
"1024x1024": 1,
|
||||
"1024x1792": 2,
|
||||
"1792x1024": 2,
|
||||
},
|
||||
}
|
||||
|
||||
var DalleGenerationImageAmounts = map[string][2]int{
|
||||
"dall-e-2": {1, 10},
|
||||
"dall-e-3": {1, 1}, // OpenAI allows n=1 currently.
|
||||
}
|
||||
|
||||
var DalleImagePromptLengthLimitations = map[string]int{
|
||||
"dall-e-2": 1000,
|
||||
"dall-e-3": 4000,
|
||||
}
|
||||
|
||||
const (
|
||||
USD2RMB = 7
|
||||
USD = 500 // $0.002 = 1 -> $1 = 500
|
||||
@@ -40,7 +17,6 @@ const (
|
||||
// https://platform.openai.com/docs/models/model-endpoint-compatibility
|
||||
// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Blfmc9dlf
|
||||
// https://openai.com/pricing
|
||||
// TODO: when a new api is enabled, check the pricing here
|
||||
// 1 === $0.002 / 1K tokens
|
||||
// 1 === ¥0.014 / 1k tokens
|
||||
var ModelRatio = map[string]float64{
|
||||
@@ -94,14 +70,18 @@ var ModelRatio = map[string]float64{
|
||||
"claude-2.0": 5.51, // $11.02 / 1M tokens
|
||||
"claude-2.1": 5.51, // $11.02 / 1M tokens
|
||||
// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
|
||||
"ERNIE-Bot": 0.8572, // ¥0.012 / 1k tokens
|
||||
"ERNIE-Bot-turbo": 0.5715, // ¥0.008 / 1k tokens
|
||||
"ERNIE-Bot-4": 0.12 * RMB, // ¥0.12 / 1k tokens
|
||||
"ERNIE-Bot-8k": 0.024 * RMB,
|
||||
"Embedding-V1": 0.1429, // ¥0.002 / 1k tokens
|
||||
"PaLM-2": 1,
|
||||
"gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
|
||||
"gemini-pro-vision": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
|
||||
"ERNIE-Bot": 0.8572, // ¥0.012 / 1k tokens
|
||||
"ERNIE-Bot-turbo": 0.5715, // ¥0.008 / 1k tokens
|
||||
"ERNIE-Bot-4": 0.12 * RMB, // ¥0.12 / 1k tokens
|
||||
"ERNIE-Bot-8k": 0.024 * RMB,
|
||||
"Embedding-V1": 0.1429, // ¥0.002 / 1k tokens
|
||||
"PaLM-2": 1,
|
||||
"gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
|
||||
"gemini-pro-vision": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
|
||||
// https://open.bigmodel.cn/pricing
|
||||
"glm-4": 0.1 * RMB,
|
||||
"glm-4v": 0.1 * RMB,
|
||||
"glm-3-turbo": 0.005 * RMB,
|
||||
"chatglm_turbo": 0.3572, // ¥0.005 / 1k tokens
|
||||
"chatglm_pro": 0.7143, // ¥0.01 / 1k tokens
|
||||
"chatglm_std": 0.3572, // ¥0.005 / 1k tokens
|
||||
@@ -127,6 +107,37 @@ var ModelRatio = map[string]float64{
|
||||
"moonshot-v1-8k": 0.012 * RMB,
|
||||
"moonshot-v1-32k": 0.024 * RMB,
|
||||
"moonshot-v1-128k": 0.06 * RMB,
|
||||
// https://platform.baichuan-ai.com/price
|
||||
"Baichuan2-Turbo": 0.008 * RMB,
|
||||
"Baichuan2-Turbo-192k": 0.016 * RMB,
|
||||
"Baichuan2-53B": 0.02 * RMB,
|
||||
// https://api.minimax.chat/document/price
|
||||
"abab6-chat": 0.1 * RMB,
|
||||
"abab5.5-chat": 0.015 * RMB,
|
||||
"abab5.5s-chat": 0.005 * RMB,
|
||||
// https://docs.mistral.ai/platform/pricing/
|
||||
"open-mistral-7b": 0.25 / 1000 * USD,
|
||||
"open-mixtral-8x7b": 0.7 / 1000 * USD,
|
||||
"mistral-small-latest": 2.0 / 1000 * USD,
|
||||
"mistral-medium-latest": 2.7 / 1000 * USD,
|
||||
"mistral-large-latest": 8.0 / 1000 * USD,
|
||||
"mistral-embed": 0.1 / 1000 * USD,
|
||||
}
|
||||
|
||||
var CompletionRatio = map[string]float64{}
|
||||
|
||||
var DefaultModelRatio map[string]float64
|
||||
var DefaultCompletionRatio map[string]float64
|
||||
|
||||
func init() {
|
||||
DefaultModelRatio = make(map[string]float64)
|
||||
for k, v := range ModelRatio {
|
||||
DefaultModelRatio[k] = v
|
||||
}
|
||||
DefaultCompletionRatio = make(map[string]float64)
|
||||
for k, v := range CompletionRatio {
|
||||
DefaultCompletionRatio[k] = v
|
||||
}
|
||||
}
|
||||
|
||||
func ModelRatio2JSONString() string {
|
||||
@@ -147,6 +158,9 @@ func GetModelRatio(name string) float64 {
|
||||
name = strings.TrimSuffix(name, "-internet")
|
||||
}
|
||||
ratio, ok := ModelRatio[name]
|
||||
if !ok {
|
||||
ratio, ok = DefaultModelRatio[name]
|
||||
}
|
||||
if !ok {
|
||||
logger.SysError("model ratio not found: " + name)
|
||||
return 30
|
||||
@@ -154,8 +168,6 @@ func GetModelRatio(name string) float64 {
|
||||
return ratio
|
||||
}
|
||||
|
||||
var CompletionRatio = map[string]float64{}
|
||||
|
||||
func CompletionRatio2JSONString() string {
|
||||
jsonBytes, err := json.Marshal(CompletionRatio)
|
||||
if err != nil {
|
||||
@@ -176,6 +188,9 @@ func GetCompletionRatio(name string) float64 {
|
||||
if ratio, ok := CompletionRatio[name]; ok {
|
||||
return ratio
|
||||
}
|
||||
if ratio, ok := DefaultCompletionRatio[name]; ok {
|
||||
return ratio
|
||||
}
|
||||
if strings.HasPrefix(name, "gpt-3.5") {
|
||||
if strings.HasSuffix(name, "0125") {
|
||||
// https://openai.com/blog/new-embedding-models-and-api-updates
|
||||
@@ -208,5 +223,8 @@ func GetCompletionRatio(name string) float64 {
|
||||
if strings.HasPrefix(name, "claude-2") {
|
||||
return 2.965517
|
||||
}
|
||||
if strings.HasPrefix(name, "mistral-") {
|
||||
return 3
|
||||
}
|
||||
return 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user