diff --git a/common/model-ratio.go b/common/model-ratio.go
index 4e7bc11..8bb78ea 100644
--- a/common/model-ratio.go
+++ b/common/model-ratio.go
@@ -5,7 +5,7 @@ import (
"strings"
)
-//from songquanpeng/one-api
+// from songquanpeng/one-api
const (
USD2RMB = 7.3 // 暂定 1 USD = 7.3 RMB
USD = 500 // $0.002 = 1 -> $1 = 500
@@ -40,86 +40,86 @@ var DefaultModelRatio = map[string]float64{
"gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens
"gpt-3.5-turbo": 0.25, // $0.0015 / 1K tokens
//"gpt-3.5-turbo-0301": 0.75, //deprecated
- "gpt-3.5-turbo-0613": 0.75,
- "gpt-3.5-turbo-16k": 1.5, // $0.003 / 1K tokens
- "gpt-3.5-turbo-16k-0613": 1.5,
- "gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens
- "gpt-3.5-turbo-1106": 0.5, // $0.001 / 1K tokens
- "gpt-3.5-turbo-0125": 0.25,
- "babbage-002": 0.2, // $0.0004 / 1K tokens
- "davinci-002": 1, // $0.002 / 1K tokens
- "text-ada-001": 0.2,
- "text-babbage-001": 0.25,
- "text-curie-001": 1,
- "text-davinci-002": 10,
- "text-davinci-003": 10,
- "text-davinci-edit-001": 10,
- "code-davinci-edit-001": 10,
- "whisper-1": 15, // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
- "tts-1": 7.5, // 1k characters -> $0.015
- "tts-1-1106": 7.5, // 1k characters -> $0.015
- "tts-1-hd": 15, // 1k characters -> $0.03
- "tts-1-hd-1106": 15, // 1k characters -> $0.03
- "davinci": 10,
- "curie": 10,
- "babbage": 10,
- "ada": 10,
- "text-embedding-3-small": 0.01,
- "text-embedding-3-large": 0.065,
- "text-embedding-ada-002": 0.05,
- "text-search-ada-doc-001": 10,
- "text-moderation-stable": 0.1,
- "text-moderation-latest": 0.1,
- "claude-instant-1": 0.4, // $0.8 / 1M tokens
- "claude-2.0": 4, // $8 / 1M tokens
- "claude-2.1": 4, // $8 / 1M tokens
- "claude-3-haiku-20240307": 0.125, // $0.25 / 1M tokens
- "claude-3-sonnet-20240229": 1.5, // $3 / 1M tokens
- "claude-3-opus-20240229": 7.5, // $15 / 1M tokens
- "ERNIE-Bot": 0.8572, // ￥0.012 / 1k tokens //renamed to ERNIE-3.5-8K
- "ERNIE-Bot-turbo": 0.5715, // ￥0.008 / 1k tokens //renamed to ERNIE-Lite-8K
- "ERNIE-Bot-4": 8.572, // ￥0.12 / 1k tokens //renamed to ERNIE-4.0-8K
- "ERNIE-4.0-8K": 8.572, // ￥0.12 / 1k tokens
- "ERNIE-3.5-8K": 0.8572, // ￥0.012 / 1k tokens
- "ERNIE-Speed-8K": 0.2858, // ￥0.004 / 1k tokens
- "ERNIE-Speed-128K": 0.2858, // ￥0.004 / 1k tokens
- "ERNIE-Lite-8K": 0.2143, // ￥0.003 / 1k tokens
- "ERNIE-Tiny-8K": 0.0715, // ￥0.001 / 1k tokens
- "ERNIE-Character-8K": 0.2858, // ￥0.004 / 1k tokens
- "ERNIE-Functions-8K": 0.2858, // ￥0.004 / 1k tokens
- "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
- "gemini-1.0-pro-vision-001": 1,
- "gemini-1.0-pro-001": 1,
- "gemini-1.5-pro-latest": 1,
- "gemini-1.5-flash-latest": 1,
- "gemini-1.0-pro-latest": 1,
- "gemini-1.0-pro-vision-latest": 1,
- "gemini-ultra": 1,
- "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
- "glm-4": 7.143, // ￥0.1 / 1k tokens
- "glm-4v": 7.143, // ￥0.1 / 1k tokens
- "glm-3-turbo": 0.3572,
- "qwen-turbo": 0.8572, // ￥0.012 / 1k tokens
- "qwen-plus": 10, // ￥0.14 / 1k tokens
- "text-embedding-v1": 0.05, // ￥0.0007 / 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-v3.5": 1.2858, // ￥0.018 / 1k tokens
- "360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens
- "360gpt-turbo": 0.0858, // ¥0.0012 / 1k tokens
+ "gpt-3.5-turbo-0613": 0.75,
+ "gpt-3.5-turbo-16k": 1.5, // $0.003 / 1K tokens
+ "gpt-3.5-turbo-16k-0613": 1.5,
+ "gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens
+ "gpt-3.5-turbo-1106": 0.5, // $0.001 / 1K tokens
+ "gpt-3.5-turbo-0125": 0.25,
+ "babbage-002": 0.2, // $0.0004 / 1K tokens
+ "davinci-002": 1, // $0.002 / 1K tokens
+ "text-ada-001": 0.2,
+ "text-babbage-001": 0.25,
+ "text-curie-001": 1,
+ "text-davinci-002": 10,
+ "text-davinci-003": 10,
+ "text-davinci-edit-001": 10,
+ "code-davinci-edit-001": 10,
+ "whisper-1": 15, // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
+ "tts-1": 7.5, // 1k characters -> $0.015
+ "tts-1-1106": 7.5, // 1k characters -> $0.015
+ "tts-1-hd": 15, // 1k characters -> $0.03
+ "tts-1-hd-1106": 15, // 1k characters -> $0.03
+ "davinci": 10,
+ "curie": 10,
+ "babbage": 10,
+ "ada": 10,
+ "text-embedding-3-small": 0.01,
+ "text-embedding-3-large": 0.065,
+ "text-embedding-ada-002": 0.05,
+ "text-search-ada-doc-001": 10,
+ "text-moderation-stable": 0.1,
+ "text-moderation-latest": 0.1,
+ "claude-instant-1": 0.4, // $0.8 / 1M tokens
+ "claude-2.0": 4, // $8 / 1M tokens
+ "claude-2.1": 4, // $8 / 1M tokens
+ "claude-3-haiku-20240307": 0.125, // $0.25 / 1M tokens
+ "claude-3-sonnet-20240229": 1.5, // $3 / 1M tokens
+ "claude-3-opus-20240229": 7.5, // $15 / 1M tokens
+ "ERNIE-Bot": 0.8572, // ￥0.012 / 1k tokens //renamed to ERNIE-3.5-8K
+ "ERNIE-Bot-turbo": 0.5715, // ￥0.008 / 1k tokens //renamed to ERNIE-Lite-8K
+ "ERNIE-Bot-4": 8.572, // ￥0.12 / 1k tokens //renamed to ERNIE-4.0-8K
+ "ERNIE-4.0-8K": 8.572, // ￥0.12 / 1k tokens
+ "ERNIE-3.5-8K": 0.8572, // ￥0.012 / 1k tokens
+ "ERNIE-Speed-8K": 0.2858, // ￥0.004 / 1k tokens
+ "ERNIE-Speed-128K": 0.2858, // ￥0.004 / 1k tokens
+ "ERNIE-Lite-8K": 0.2143, // ￥0.003 / 1k tokens
+ "ERNIE-Tiny-8K": 0.0715, // ￥0.001 / 1k tokens
+ "ERNIE-Character-8K": 0.2858, // ￥0.004 / 1k tokens
+ "ERNIE-Functions-8K": 0.2858, // ￥0.004 / 1k tokens
+ "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
+ "gemini-1.0-pro-vision-001": 1,
+ "gemini-1.0-pro-001": 1,
+ "gemini-1.5-pro-latest": 1,
+ "gemini-1.5-flash-latest": 1,
+ "gemini-1.0-pro-latest": 1,
+ "gemini-1.0-pro-vision-latest": 1,
+ "gemini-ultra": 1,
+ "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
+ "glm-4": 7.143, // ￥0.1 / 1k tokens
+ "glm-4v": 7.143, // ￥0.1 / 1k tokens
+ "glm-3-turbo": 0.3572,
+ "qwen-turbo": 0.8572, // ￥0.012 / 1k tokens
+ "qwen-plus": 10, // ￥0.14 / 1k tokens
+ "text-embedding-v1": 0.05, // ￥0.0007 / 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-v3.5": 1.2858, // ￥0.018 / 1k tokens
+ "360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens
+ "360gpt-turbo": 0.0858, // ¥0.0012 / 1k tokens
"360gpt-turbo-responsibility-8k": 0.8572, // ¥0.012 / 1k tokens
- "360gpt-pro": 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
+ "360gpt-pro": 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
// https://platform.lingyiwanwu.com/docs#-计费单元
// 已经按照 7.2 来换算美元价格
"yi-34b-chat-0205": 0.18,
@@ -143,10 +143,10 @@ var DefaultModelRatio = map[string]float64{
"deepseek-chat": 0.07,
"deepseek-coder": 0.07,
// Perplexity online 模型对搜索额外收费，有需要应自行调整，此处不计入搜索费用
- "llama-3-sonar-small-32k-chat": 0.2 / 1000 * USD,
- "llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
- "llama-3-sonar-large-32k-chat": 1 / 1000 * USD,
- "llama-3-sonar-large-32k-online": 1 / 1000 * USD,
+ "llama-3-sonar-small-32k-chat": 0.2 / 1000 * USD,
+ "llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
+ "llama-3-sonar-large-32k-chat": 1 / 1000 * USD,
+ "llama-3-sonar-large-32k-online": 1 / 1000 * USD,
}
var DefaultModelPrice = map[string]float64{
@@ -289,7 +289,7 @@ func GetCompletionRatio(name string) float64 {
}
return 4.0 / 3.0
}
- if strings.HasPrefix(name, "gpt-4") && name != "gpt-4-all" && name != "gpt-4-gizmo-*" {
+ if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.HasSuffix(name, "-gizmo-*") {
if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") || strings.HasPrefix(name, "gpt-4o") {
return 3
}
diff --git a/relay/channel/openai/adaptor.go b/relay/channel/openai/adaptor.go
index 46d827a..a0a5b07 100644
--- a/relay/channel/openai/adaptor.go
+++ b/relay/channel/openai/adaptor.go
@@ -41,10 +41,10 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
case common.ChannelTypeMiniMax:
return minimax.GetRequestURL(info)
- //case common.ChannelTypeCustom:
- // url := info.BaseUrl
- // url = strings.Replace(url, "{model}", info.UpstreamModelName, -1)
- // return url, nil
+ case common.ChannelTypeCustom:
+ url := info.BaseUrl
+ url = strings.Replace(url, "{model}", info.UpstreamModelName, -1)
+ return url, nil
default:
return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
}
diff --git a/web/src/components/ChannelsTable.js b/web/src/components/ChannelsTable.js
index ad53999..c49d85b 100644
--- a/web/src/components/ChannelsTable.js
+++ b/web/src/components/ChannelsTable.js
@@ -310,12 +310,12 @@ const ChannelsTable = () => {
const setChannelFormat = (channels) => {
for (let i = 0; i < channels.length; i++) {
- if (channels[i].type === 8) {
- showWarning(
- '检测到您使用了“自定义渠道”类型，请更换为“OpenAI”渠道类型！',
- );
- showWarning('下个版本将不再支持“自定义渠道”类型！');
- }
+ // if (channels[i].type === 8) {
+ // showWarning(
+ // '检测到您使用了“自定义渠道”类型，请更换为“OpenAI”渠道类型！',
+ // );
+ // showWarning('下个版本将不再支持“自定义渠道”类型！');
+ // }
channels[i].key = '' + channels[i].id;
let test_models = [];
channels[i].models.split(',').forEach((item, index) => {
diff --git a/web/src/components/LogsTable.js b/web/src/components/LogsTable.js
index f8436ad..d94eb60 100644
--- a/web/src/components/LogsTable.js
+++ b/web/src/components/LogsTable.js
@@ -302,6 +302,9 @@ const LogsTable = () => {
let content = '渠道：' + record.channel;
if (record.other !== '') {
let other = JSON.parse(record.other);
+ if (other === null) {
+ return <>
+ }
if (other.admin_info !== undefined) {
if (
other.admin_info.use_channel !== null &&
@@ -322,7 +325,8 @@ const LogsTable = () => {
title: '详情',
dataIndex: 'content',
render: (text, record, index) => {
- if (record.other === '') {
+ let other = JSON.parse(record.other);
+ if (other == null) {
return (
{
);
}
- let other = JSON.parse(record.other);
let content = renderModelPrice(
record.prompt_tokens,
record.completion_tokens,
diff --git a/web/src/components/ModelPricing.js b/web/src/components/ModelPricing.js
index c7a45d7..f5bb01c 100644
--- a/web/src/components/ModelPricing.js
+++ b/web/src/components/ModelPricing.js
@@ -146,11 +146,11 @@ const ModelPricing = () => {
render: (text, record, index) => {
let content = text;
if (record.quota_type === 0) {
- let inputRatioPrice = record.model_ratio * 2.0 * record.group_ratio;
+ // 这里的 *2 是因为 1倍率=0.002刀，请勿删除
+ let inputRatioPrice = record.model_ratio * 2 * record.group_ratio;
let completionRatioPrice =
record.model_ratio *
- record.completion_ratio *
- 2.0 *
+ record.completion_ratio * 2 *
record.group_ratio;
content = (
<>
diff --git a/web/src/helpers/render.js b/web/src/helpers/render.js
index d84b2eb..971b1d8 100644
--- a/web/src/helpers/render.js
+++ b/web/src/helpers/render.js
@@ -149,8 +149,9 @@ export function renderModelPrice(
if (completionRatio === undefined) {
completionRatio = 0;
}
+ // 这里的 *2 是因为 1倍率=0.002刀，请勿删除
let inputRatioPrice = modelRatio * 2.0 * groupRatio;
- let completionRatioPrice = modelRatio * completionRatio * 2.0 * groupRatio;
+ let completionRatioPrice = modelRatio * 2.0 * completionRatio * groupRatio;
let price =
(inputTokens / 1000000) * inputRatioPrice +
(completionTokens / 1000000) * completionRatioPrice;
diff --git a/web/src/pages/Channel/EditChannel.js b/web/src/pages/Channel/EditChannel.js
index 2c39093..14f15db 100644
--- a/web/src/pages/Channel/EditChannel.js
+++ b/web/src/pages/Channel/EditChannel.js
@@ -37,8 +37,6 @@ const STATUS_CODE_MAPPING_EXAMPLE = {
400: '500',
};
-const fetchButtonTips = "1. 新建渠道时，请求通过当前浏览器发出；2. 编辑已有渠道，请求通过后端服务器发出"
-
function type2secretPrompt(type) {
// inputs.type === 15 ? '按照如下格式输入：APIKey|SecretKey' : (inputs.type === 18 ? '按照如下格式输入：APPID|APISecret|APIKey' : '请输入渠道对应的鉴权密钥')
switch (type) {
@@ -90,55 +88,6 @@ const EditChannel = (props) => {
const [basicModels, setBasicModels] = useState([]);
const [fullModels, setFullModels] = useState([]);
const [customModel, setCustomModel] = useState('');
-
- const fetchUpstreamModelList = async (name) => {
- if (inputs["type"] !== 1) {
- showError("仅支持 OpenAI 接口格式")
- return;
- }
- const models = inputs["models"] || []
- let err = false;
- if (isEdit) {
- const res = await API.get("/api/channel/fetch_models/" + channelId)
- if (res.data && res.data?.success) {
- models.push(...res.data.data)
- } else {
- err = true
- }
- } else {
- if (!inputs?.["key"]) {
- showError("请填写密钥")
- return;
- }
- try {
- const host = new URL((inputs["base_url"] || "https://api.openai.com"))
-
- const url = `https://${host.hostname}/v1/models`;
- const key = inputs["key"];
- const res = await axios.get(url, {
- headers: {
- 'Authorization': `Bearer ${key}`
- }
- })
- if (res.data && res.data?.success) {
- models.push(...es.data.data.map((model) => model.id))
- } else {
- err = true
- }
- }
- catch (error) {
- err = true
- }
- }
- if (!err) {
- handleInputChange(name, Array.from(new Set(models)));
- showSuccess("获取模型列表成功");
- } else {
- showError('获取模型列表失败');
- }
- }
-
-
const handleInputChange = (name, value) => {
setInputs((inputs) => ({ ...inputs, [name]: value }));
if (name === 'type') {
@@ -284,7 +233,7 @@ const EditChannel = (props) => {
fetchModels().then();
fetchGroups().then();
if (isEdit) {
- loadChannel().then(() => { });
+ loadChannel().then(() => {});
} else {
setInputs(originInputs);
let localModels = getChannelModels(inputs.type);
@@ -354,17 +303,18 @@ const EditChannel = (props) => {
const addCustomModels = () => {
if (customModel.trim() === '') return;
// 使用逗号分隔字符串，然后去除每个模型名称前后的空格
- const modelArray = customModel.split(',').map(model => model.trim());
+ const modelArray = customModel.split(',').map((model) => model.trim());
let localModels = [...inputs.models];
let localModelOptions = [...modelOptions];
let hasError = false;
- modelArray.forEach(model => {
+ modelArray.forEach((model) => {
// 检查模型是否已存在，且模型名称非空
if (model && !localModels.includes(model)) {
localModels.push(model); // 添加到模型列表
- localModelOptions.push({ // 添加到下拉选项
+ localModelOptions.push({
+ // 添加到下拉选项
key: model,
text: model,
value: model,
@@ -486,11 +436,15 @@ const EditChannel = (props) => {
{inputs.type === 8 && (
<>
- Base URL：
+
+ 完整的 Base URL，支持变量{'{model}'}：
+
{
handleInputChange('base_url', value);
}}
@@ -723,7 +677,7 @@ const EditChannel = (props) => {
onChange={() => {
setAutoBan(!autoBan);
}}
- // onChange={handleInputChange}
+ // onChange={handleInputChange}
/>
是否自动禁用（仅当自动禁用开启时有效），关闭后不会自动禁用该渠道：