xinyin025/one-api
1
0
Fork 0
mirror of https://github.com/songquanpeng/one-api.git synced 2026-04-05 09:54:26 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge 33af45d4a9 into 36c8f4f15c

Browse Source
This commit is contained in:
longkeyy
2024-12-21 03:21:41 +08:00
committed by GitHub
parent 36c8f4f15c 33af45d4a9
commit 061a8d77ad
3 changed files with 114 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
relay/adaptor/ali/constants.go
View File

@@ -1,7 +1,23 @@
package ali
var ModelList = []string{
"qwen-turbo", "qwen-plus", "qwen-max", "qwen-max-longcontext",
"text-embedding-v1",
"qwen-turbo", "qwen-turbo-latest",
"qwen-plus", "qwen-plus-latest",
"qwen-max", "qwen-max-latest",
"qwen-max-longcontext",
"qwen-vl-max", "qwen-vl-max-latest", "qwen-vl-plus", "qwen-vl-plus-latest",
"qwen-vl-ocr", "qwen-vl-ocr-latest",
"qwen-audio-turbo",
"qwen-math-plus", "qwen-math-plus-latest", "qwen-math-turbo", "qwen-math-turbo-latest",
"qwen-coder-plus", "qwen-coder-plus-latest", "qwen-coder-turbo", "qwen-coder-turbo-latest",
"qwq-32b-preview", "qwen2.5-72b-instruct", "qwen2.5-32b-instruct", "qwen2.5-14b-instruct", "qwen2.5-7b-instruct", "qwen2.5-3b-instruct", "qwen2.5-1.5b-instruct", "qwen2.5-0.5b-instruct",
"qwen2-72b-instruct", "qwen2-57b-a14b-instruct", "qwen2-7b-instruct", "qwen2-1.5b-instruct", "qwen2-0.5b-instruct",
"qwen1.5-110b-chat", "qwen1.5-72b-chat", "qwen1.5-32b-chat", "qwen1.5-14b-chat", "qwen1.5-7b-chat", "qwen1.5-1.8b-chat", "qwen1.5-0.5b-chat",
"qwen-72b-chat", "qwen-14b-chat", "qwen-7b-chat", "qwen-1.8b-chat", "qwen-1.8b-longcontext-chat",
"qwen2-vl-7b-instruct", "qwen2-vl-2b-instruct", "qwen-vl-v1", "qwen-vl-chat-v1",
"qwen2-audio-instruct", "qwen-audio-chat",
"qwen2.5-math-72b-instruct", "qwen2.5-math-7b-instruct", "qwen2.5-math-1.5b-instruct", "qwen2-math-72b-instruct", "qwen2-math-7b-instruct", "qwen2-math-1.5b-instruct",
"qwen2.5-coder-32b-instruct", "qwen2.5-coder-14b-instruct", "qwen2.5-coder-7b-instruct", "qwen2.5-coder-3b-instruct", "qwen2.5-coder-1.5b-instruct", "qwen2.5-coder-0.5b-instruct",
"text-embedding-v1", "text-embedding-v3", "text-embedding-v2", "text-embedding-async-v2", "text-embedding-async-v1",
"ali-stable-diffusion-xl", "ali-stable-diffusion-v1.5", "wanx-v1",
}

4
relay/adaptor/openai/constants.go
View File

@@ -7,7 +7,9 @@ var ModelList = []string{
"gpt-4", "gpt-4-0314", "gpt-4-0613", "gpt-4-1106-preview", "gpt-4-0125-preview",
"gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613",
"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
"gpt-4o", "gpt-4o-2024-05-13",
"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06", "gpt-4o-2024-11-20",
"o1-preview", "o1-preview-2024-09-12",
"o1-mini", "o1-mini-2024-09-12",
"gpt-4o-2024-08-06",
"chatgpt-4o-latest",
"gpt-4o-mini", "gpt-4o-mini-2024-07-18",

116
relay/billing/ratio/model.go
View File

@@ -22,6 +22,10 @@ const (
// 1 === ￥0.014 / 1k tokens
var ModelRatio = map[string]float64{
// https://openai.com/pricing
"o1-preview": 15,
"o1-preview-2024-09-12": 15,
"o1-mini": 3,
"o1-mini-2024-09-12": 3,
"gpt-4": 15,
"gpt-4-0314": 15,
"gpt-4-0613": 15,
@@ -37,6 +41,7 @@ var ModelRatio = map[string]float64{
"chatgpt-4o-latest": 2.5, // $0.005 / 1K tokens
"gpt-4o-2024-05-13": 2.5, // $0.005 / 1K tokens
"gpt-4o-2024-08-06": 1.25, // $0.0025 / 1K tokens
"gpt-4o-2024-11-20": 1.25, // $0.0025 / 1K tokens
"gpt-4o-mini": 0.075, // $0.00015 / 1K tokens
"gpt-4o-mini-2024-07-18": 0.075, // $0.00015 / 1K tokens
"gpt-4-vision-preview": 5, // $0.01 / 1K tokens
@@ -118,29 +123,94 @@ var ModelRatio = map[string]float64{
"chatglm_lite": 0.1429, // ￥0.002 / 1k tokens
"cogview-3": 0.25 * RMB,
// https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-thousand-questions-metering-and-billing
"qwen-turbo": 0.5715, // ￥0.008 / 1k tokens
"qwen-plus": 1.4286, // ￥0.02 / 1k tokens
"qwen-max": 1.4286, // ￥0.02 / 1k tokens
"qwen-max-longcontext": 1.4286, // ￥0.02 / 1k tokens
"text-embedding-v1": 0.05, // ￥0.0007 / 1k tokens
"ali-stable-diffusion-xl": 8,
"ali-stable-diffusion-v1.5": 8,
"wanx-v1": 8,
"SparkDesk": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v1.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v2.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.1-128K": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.5": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.5-32K": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v4.0": 1.2858, // ￥0.018 / 1k tokens
"360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens
"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,
"qwen-turbo": 1.4286, // ￥0.02 / 1k tokens
"qwen-turbo-latest": 1.4286,
"qwen-plus": 1.4286,
"qwen-plus-latest": 1.4286,
"qwen-max": 1.4286,
"qwen-max-latest": 1.4286,
"qwen-max-longcontext": 1.4286,
"qwen-vl-max": 1.4286,
"qwen-vl-max-latest": 1.4286,
"qwen-vl-plus": 1.4286,
"qwen-vl-plus-latest": 1.4286,
"qwen-vl-ocr": 1.4286,
"qwen-vl-ocr-latest": 1.4286,
"qwen-audio-turbo": 1.4286,
"qwen-math-plus": 1.4286,
"qwen-math-plus-latest": 1.4286,
"qwen-math-turbo": 1.4286,
"qwen-math-turbo-latest": 1.4286,
"qwen-coder-plus": 1.4286,
"qwen-coder-plus-latest": 1.4286,
"qwen-coder-turbo": 1.4286,
"qwen-coder-turbo-latest": 1.4286,
"qwq-32b-preview": 1.4286,
"qwen2.5-72b-instruct": 1.4286,
"qwen2.5-32b-instruct": 1.4286,
"qwen2.5-14b-instruct": 1.4286,
"qwen2.5-7b-instruct": 1.4286,
"qwen2.5-3b-instruct": 1.4286,
"qwen2.5-1.5b-instruct": 1.4286,
"qwen2.5-0.5b-instruct": 1.4286,
"qwen2-72b-instruct": 1.4286,
"qwen2-57b-a14b-instruct": 1.4286,
"qwen2-7b-instruct": 1.4286,
"qwen2-1.5b-instruct": 1.4286,
"qwen2-0.5b-instruct": 1.4286,
"qwen1.5-110b-chat": 1.4286,
"qwen1.5-72b-chat": 1.4286,
"qwen1.5-32b-chat": 1.4286,
"qwen1.5-14b-chat": 1.4286,
"qwen1.5-7b-chat": 1.4286,
"qwen1.5-1.8b-chat": 1.4286,
"qwen1.5-0.5b-chat": 1.4286,
"qwen-72b-chat": 1.4286,
"qwen-14b-chat": 1.4286,
"qwen-7b-chat": 1.4286,
"qwen-1.8b-chat": 1.4286,
"qwen-1.8b-longcontext-chat": 1.4286,
"qwen2-vl-7b-instruct": 1.4286,
"qwen2-vl-2b-instruct": 1.4286,
"qwen-vl-v1": 1.4286,
"qwen-vl-chat-v1": 1.4286,
"qwen2-audio-instruct": 1.4286,
"qwen-audio-chat": 1.4286,
"qwen2.5-math-72b-instruct": 1.4286,
"qwen2.5-math-7b-instruct": 1.4286,
"qwen2.5-math-1.5b-instruct": 1.4286,
"qwen2-math-72b-instruct": 1.4286,
"qwen2-math-7b-instruct": 1.4286,
"qwen2-math-1.5b-instruct": 1.4286,
"qwen2.5-coder-32b-instruct": 1.4286,
"qwen2.5-coder-14b-instruct": 1.4286,
"qwen2.5-coder-7b-instruct": 1.4286,
"qwen2.5-coder-3b-instruct": 1.4286,
"qwen2.5-coder-1.5b-instruct": 1.4286,
"qwen2.5-coder-0.5b-instruct": 1.4286,
"text-embedding-v1": 0.05, // ￥0.0007 / 1k tokens
"text-embedding-v3": 0.05,
"text-embedding-v2": 0.05,
"text-embedding-async-v2": 0.05,
"text-embedding-async-v1": 0.05,
"ali-stable-diffusion-xl": 8.00,
"ali-stable-diffusion-v1.5": 8.00,
"wanx-v1": 8.00,
"SparkDesk": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v1.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v2.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.1": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.1-128K": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.5": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v3.5-32K": 1.2858, // ￥0.018 / 1k tokens
"SparkDesk-v4.0": 1.2858, // ￥0.018 / 1k tokens
"360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens
"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://platform.moonshot.cn/pricing
"moonshot-v1-8k": 0.012 * RMB,
"moonshot-v1-32k": 0.024 * RMB,