xinyin025/one-api
1
0
Fork 0
mirror of https://github.com/songquanpeng/one-api.git synced 2025-11-07 17:23:42 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'upstream/main'

Browse Source
This commit is contained in:
Laisky.Cai
2025-02-03 12:25:00 +00:00
parent 9dd86e8a15 33edcf604c
commit aa30c37e3c
70 changed files with 4032 additions and 2781 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
relay/adaptor/anthropic/constants.go
View File

@@ -4,6 +4,7 @@ var ModelList = []string{
"claude-instant-1.2", "claude-2.0", "claude-2.1",
"claude-3-haiku-20240307",
"claude-3-5-haiku-20241022",
"claude-3-5-haiku-latest",
"claude-3-sonnet-20240229",
"claude-3-opus-20240229",
"claude-3-5-sonnet-20240620",

1
relay/adaptor/groq/constants.go
View File

@@ -11,7 +11,6 @@ var ModelList = []string{
"llama-3.2-11b-vision-preview",
"llama-3.2-1b-preview",
"llama-3.2-3b-preview",
"llama-3.2-11b-vision-preview",
"llama-3.2-90b-text-preview",
"llama-3.2-90b-vision-preview",
"llama-guard-3-8b",

3
relay/adaptor/openai/token.go
View File

@@ -27,7 +27,8 @@ func InitTokenEncoders() {
logger.SysLog("initializing token encoders")
gpt35TokenEncoder, err := tiktoken.EncodingForModel("gpt-3.5-turbo")
if err != nil {
logger.FatalLog(fmt.Sprintf("failed to get gpt-3.5-turbo token encoder: %s", err.Error()))
logger.FatalLog(fmt.Sprintf("failed to get gpt-3.5-turbo token encoder: %s, "+
"if you are using in offline environment, please set TIKTOKEN_CACHE_DIR to use exsited files, check this link for more information: https://stackoverflow.com/questions/76106366/how-to-use-tiktoken-in-offline-mode-computer ", err.Error()))
}
defaultTokenEncoder = gpt35TokenEncoder
gpt4oTokenEncoder, err := tiktoken.EncodingForModel("gpt-4o")

13
relay/adaptor/zhipu/constants.go
View File

@@ -1,7 +1,14 @@
package zhipu
// https://open.bigmodel.cn/pricing
var ModelList = []string{
"chatglm_turbo", "chatglm_pro", "chatglm_std", "chatglm_lite",
"glm-4", "glm-4v", "glm-3-turbo", "embedding-2",
"cogview-3",
"glm-zero-preview", "glm-4-plus", "glm-4-0520", "glm-4-airx",
"glm-4-air", "glm-4-long", "glm-4-flashx", "glm-4-flash",
"glm-4", "glm-3-turbo",
"glm-4v-plus", "glm-4v", "glm-4v-flash",
"cogview-3-plus", "cogview-3", "cogview-3-flash",
"cogviewx", "cogviewx-flash",
"charglm-4", "emohaa", "codegeex-4",
"embedding-2", "embedding-3",
}

49
relay/billing/ratio/model.go
View File

@@ -98,6 +98,7 @@ var ModelRatio = map[string]float64{
"claude-2.1": 8.0 / 1000 * USD,
"claude-3-haiku-20240307": 0.25 / 1000 * USD,
"claude-3-5-haiku-20241022": 1.0 / 1000 * USD,
"claude-3-5-haiku-latest": 1.0 / 1000 * USD,
"claude-3-sonnet-20240229": 3.0 / 1000 * USD,
"claude-3-5-sonnet-20240620": 3.0 / 1000 * USD,
"claude-3-5-sonnet-20241022": 3.0 / 1000 * USD,
@@ -131,15 +132,29 @@ var ModelRatio = map[string]float64{
"gemini-2.0-flash-thinking-exp-01-21": 0.075 * MILLI_USD,
"aqa": 1,
// https://open.bigmodel.cn/pricing
"glm-4": 0.1 * RMB,
"glm-4v": 0.1 * RMB,
"glm-3-turbo": 0.005 * RMB,
"embedding-2": 0.0005 * 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
"chatglm_lite": 0.1429, // ￥0.002 / 1k tokens
"cogview-3": 0.25 * RMB,
"glm-zero-preview": 0.01 * RMB,
"glm-4-plus": 0.05 * RMB,
"glm-4-0520": 0.1 * RMB,
"glm-4-airx": 0.01 * RMB,
"glm-4-air": 0.0005 * RMB,
"glm-4-long": 0.001 * RMB,
"glm-4-flashx": 0.0001 * RMB,
"glm-4-flash": 0,
"glm-4": 0.1 * RMB, // deprecated model, available until 2025/06
"glm-3-turbo": 0.001 * RMB, // deprecated model, available until 2025/06
"glm-4v-plus": 0.004 * RMB,
"glm-4v": 0.05 * RMB,
"glm-4v-flash": 0,
"cogview-3-plus": 0.06 * RMB,
"cogview-3": 0.1 * RMB,
"cogview-3-flash": 0,
"cogviewx": 0.5 * RMB,
"cogviewx-flash": 0,
"charglm-4": 0.001 * RMB,
"emohaa": 0.015 * RMB,
"codegeex-4": 0.0001 * RMB,
"embedding-2": 0.0005 * RMB,
"embedding-3": 0.0005 * RMB,
// https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-thousand-questions-metering-and-billing
"qwen-turbo": 1.4286, // ￥0.02 / 1k tokens
"qwen-turbo-latest": 1.4286,
@@ -226,9 +241,19 @@ var ModelRatio = map[string]float64{
"embedding-bert-512-v1": 0.0715, // ¥0.001 / 1k tokens
"embedding_s1_v1": 0.0715, // ¥0.001 / 1k tokens
"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
"hunyuan": 7.143, // ¥0.1 / 1k tokens // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
"ChatStd": 0.01 * RMB,
"ChatPro": 0.1 * RMB,
// https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
"hunyuan-turbo": 0.015 * RMB,
"hunyuan-large": 0.004 * RMB,
"hunyuan-large-longcontext": 0.006 * RMB,
"hunyuan-standard": 0.0008 * RMB,
"hunyuan-standard-256K": 0.0005 * RMB,
"hunyuan-translation-lite": 0.005 * RMB,
"hunyuan-role": 0.004 * RMB,
"hunyuan-functioncall": 0.004 * RMB,
"hunyuan-code": 0.004 * RMB,
"hunyuan-turbo-vision": 0.08 * RMB,
"hunyuan-vision": 0.018 * RMB,
"hunyuan-embedding": 0.0007 * RMB,
// https://platform.moonshot.cn/pricing
"moonshot-v1-8k": 0.012 * RMB,
"moonshot-v1-32k": 0.024 * RMB,

2
relay/client/init.go
View File

@@ -5,7 +5,7 @@ import (
"os"
"time"
gutils "github.com/Laisky/go-utils/v4"
gutils "github.com/Laisky/go-utils/v5"
"github.com/songquanpeng/one-api/common/config"
)