diff --git a/middleware/utils.go b/middleware/utils.go index 4d2f8092ef..3ca51fa17c 100644 --- a/middleware/utils.go +++ b/middleware/utils.go @@ -2,11 +2,12 @@ package middleware import ( "fmt" + "strings" + "github.com/gin-gonic/gin" "github.com/songquanpeng/one-api/common" "github.com/songquanpeng/one-api/common/helper" "github.com/songquanpeng/one-api/common/logger" - "strings" ) func abortWithMessage(c *gin.Context, statusCode int, message string) { @@ -28,7 +29,7 @@ func getRequestModel(c *gin.Context) (string, error) { } if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") { if modelRequest.Model == "" { - modelRequest.Model = "text-moderation-stable" + modelRequest.Model = "omni-moderation-latest" } } if strings.HasSuffix(c.Request.URL.Path, "embeddings") { diff --git a/relay/adaptor/openai/constants.go b/relay/adaptor/openai/constants.go index 8a643bc6ad..0ef0e091a7 100644 --- a/relay/adaptor/openai/constants.go +++ b/relay/adaptor/openai/constants.go @@ -15,7 +15,7 @@ var ModelList = []string{ "gpt-4-vision-preview", "text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large", "text-curie-001", "text-babbage-001", "text-ada-001", "text-davinci-002", "text-davinci-003", - "text-moderation-latest", "text-moderation-stable", + "text-moderation-latest", "text-moderation-stable", "omni-moderation-latest", "omni-moderation-2024-09-26", "text-davinci-edit-001", "davinci-002", "babbage-002", "dall-e-2", "dall-e-3", diff --git a/relay/billing/ratio/model.go b/relay/billing/ratio/model.go index f83aa70c11..8b7aead6ef 100644 --- a/relay/billing/ratio/model.go +++ b/relay/billing/ratio/model.go @@ -22,65 +22,67 @@ const ( // 1 === ￥0.014 / 1k tokens var ModelRatio = map[string]float64{ // https://openai.com/pricing - "gpt-4": 15, - "gpt-4-0314": 15, - "gpt-4-0613": 15, - "gpt-4-32k": 30, - "gpt-4-32k-0314": 30, - "gpt-4-32k-0613": 30, - "gpt-4-1106-preview": 5, // $0.01 / 1K tokens - "gpt-4-0125-preview": 5, // $0.01 / 1K tokens - "gpt-4-turbo-preview": 5, // $0.01 / 1K tokens - "gpt-4-turbo": 5, // $0.01 / 1K tokens - "gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens - "gpt-4o": 2.5, // $0.005 / 1K tokens - "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 - "gpt-3.5-turbo": 0.25, // $0.0005 / 1K tokens - "gpt-3.5-turbo-0301": 0.75, - "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, // $0.0005 / 1K tokens - "o1": 7.5, // $15.00 / 1M input tokens - "o1-2024-12-17": 7.5, - "o1-preview": 7.5, // $15.00 / 1M input tokens - "o1-preview-2024-09-12": 7.5, - "o1-mini": 1.5, // $3.00 / 1M input tokens - "o1-mini-2024-09-12": 1.5, - "davinci-002": 1, // $0.002 / 1K tokens - "babbage-002": 0.2, // $0.0004 / 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, // $0.015 / 1K characters - "tts-1-1106": 7.5, - "tts-1-hd": 15, // $0.030 / 1K characters - "tts-1-hd-1106": 15, - "davinci": 10, - "curie": 10, - "babbage": 10, - "ada": 10, - "text-embedding-ada-002": 0.05, - "text-embedding-3-small": 0.01, - "text-embedding-3-large": 0.065, - "text-search-ada-doc-001": 10, - "text-moderation-stable": 0.1, - "text-moderation-latest": 0.1, - "dall-e-2": 0.02 * USD, // $0.016 - $0.020 / image - "dall-e-3": 0.04 * USD, // $0.040 - $0.120 / image + "gpt-4": 15, + "gpt-4-0314": 15, + "gpt-4-0613": 15, + "gpt-4-32k": 30, + "gpt-4-32k-0314": 30, + "gpt-4-32k-0613": 30, + "gpt-4-1106-preview": 5, // $0.01 / 1K tokens + "gpt-4-0125-preview": 5, // $0.01 / 1K tokens + "gpt-4-turbo-preview": 5, // $0.01 / 1K tokens + "gpt-4-turbo": 5, // $0.01 / 1K tokens + "gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens + "gpt-4o": 2.5, // $0.005 / 1K tokens + "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 + "gpt-3.5-turbo": 0.25, // $0.0005 / 1K tokens + "gpt-3.5-turbo-0301": 0.75, + "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, // $0.0005 / 1K tokens + "o1": 7.5, // $15.00 / 1M input tokens + "o1-2024-12-17": 7.5, + "o1-preview": 7.5, // $15.00 / 1M input tokens + "o1-preview-2024-09-12": 7.5, + "o1-mini": 1.5, // $3.00 / 1M input tokens + "o1-mini-2024-09-12": 1.5, + "davinci-002": 1, // $0.002 / 1K tokens + "babbage-002": 0.2, // $0.0004 / 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, // $0.015 / 1K characters + "tts-1-1106": 7.5, + "tts-1-hd": 15, // $0.030 / 1K characters + "tts-1-hd-1106": 15, + "davinci": 10, + "curie": 10, + "babbage": 10, + "ada": 10, + "text-embedding-ada-002": 0.05, + "text-embedding-3-small": 0.01, + "text-embedding-3-large": 0.065, + "text-search-ada-doc-001": 10, + "text-moderation-stable": 0.1, + "text-moderation-latest": 0.1, + "omni-moderation-latest": 0.1, + "omni-moderation-2024-09-26": 0.1, + "dall-e-2": 0.02 * USD, // $0.016 - $0.020 / image + "dall-e-3": 0.04 * USD, // $0.040 - $0.120 / image // https://www.anthropic.com/api#pricing "claude-instant-1.2": 0.8 / 1000 * USD, "claude-2.0": 8.0 / 1000 * USD, diff --git a/relay/controller/helper.go b/relay/controller/helper.go index 5f5fc90cb8..37a620495a 100644 --- a/relay/controller/helper.go +++ b/relay/controller/helper.go @@ -4,11 +4,12 @@ import ( "context" "errors" "fmt" - "github.com/songquanpeng/one-api/relay/constant/role" "math" "net/http" "strings" + "github.com/songquanpeng/one-api/relay/constant/role" + "github.com/gin-gonic/gin" "github.com/songquanpeng/one-api/common" "github.com/songquanpeng/one-api/common/config" @@ -30,7 +31,7 @@ func getAndValidateTextRequest(c *gin.Context, relayMode int) (*relaymodel.Gener return nil, err } if relayMode == relaymode.Moderations && textRequest.Model == "" { - textRequest.Model = "text-moderation-latest" + textRequest.Model = "omni-moderation-latest" } if relayMode == relaymode.Embeddings && textRequest.Model == "" { textRequest.Model = c.Param("model") diff --git a/web/air/src/helpers/render.js b/web/air/src/helpers/render.js index 62fb0dcde4..490d342fe7 100644 --- a/web/air/src/helpers/render.js +++ b/web/air/src/helpers/render.js @@ -150,6 +150,8 @@ export const modelColorMap = { 'text-embedding-v1': 'rgb(255,174,185)', // 浅粉红色（略有区别） 'text-moderation-latest': 'rgb(255,130,171)', // 强粉色 'text-moderation-stable': 'rgb(255,160,122)', // 浅珊瑚色（与Babbage相同，表示同一类功能） + 'omni-moderation-latest': 'rgb(255,130,171)', // 强粉色 + 'omni-moderation-2024-09-26': 'rgb(255,130,171)', // 强粉色 'tts-1': 'rgb(255,140,0)', // 深橙色 'tts-1-1106': 'rgb(255,165,0)', // 橙色 'tts-1-hd': 'rgb(255,215,0)', // 金色