diff --git a/common/model-ratio.go b/common/model-ratio.go index d8356dc2..94607c92 100644 --- a/common/model-ratio.go +++ b/common/model-ratio.go @@ -72,14 +72,22 @@ var ModelRatio = map[string]float64{ "claude-3-sonnet-20240229": 3.0 / 1000 * USD, "claude-3-opus-20240229": 15.0 / 1000 * USD, // 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 - "bge-large-zh": 0.002 * RMB, - "bge-large-en": 0.002 * RMB, - "bge-large-8k": 0.002 * RMB, + "ERNIE-4.0-8K": 0.120 * RMB, + "ERNIE-Bot-8K-0922": 0.024 * RMB, + "ERNIE-3.5-8K": 0.012 * RMB, + "ERNIE-Lite-8K-0922": 0.008 * RMB, + "ERNIE-Speed-8K": 0.004 * RMB, + "ERNIE-3.5-4K-0205": 0.012 * RMB, + "ERNIE-3.5-8K-0205": 0.024 * RMB, + "ERNIE-3.5-8K-1222": 0.012 * RMB, + "ERNIE-Lite-8K": 0.003 * RMB, + "ERNIE-Speed-128K": 0.004 * RMB, + "ERNIE-Tiny-8K": 0.001 * RMB, + "BLOOMZ-7B": 0.004 * RMB, + "Embedding-V1": 0.002 * RMB, + "bge-large-zh": 0.002 * RMB, + "bge-large-en": 0.002 * RMB, + "tao-8k": 0.002 * RMB, // https://ai.google.dev/pricing "PaLM-2": 1, "gemini-pro": 1, // $0.00025 / 1k characters -> $0.001 / 1k tokens diff --git a/relay/channel/baidu/adaptor.go b/relay/channel/baidu/adaptor.go index 2d2e24f6..72302fdf 100644 --- a/relay/channel/baidu/adaptor.go +++ b/relay/channel/baidu/adaptor.go @@ -38,16 +38,26 @@ func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) { suffix += "completions_pro" case "ERNIE-Bot-4": suffix += "completions_pro" - case "ERNIE-3.5-8K": - suffix += "completions" - case "ERNIE-Bot-8K": - suffix += "ernie_bot_8k" case "ERNIE-Bot": suffix += "completions" - case "ERNIE-Speed": - suffix += "ernie_speed" case "ERNIE-Bot-turbo": suffix += "eb-instant" + case "ERNIE-Speed": + suffix += "ernie_speed" + case "ERNIE-Bot-8K": + suffix += "ernie_bot_8k" + case "ERNIE-4.0-8K": + suffix += "completions_pro" + case "ERNIE-3.5-8K": + suffix += "completions" + case "ERNIE-Speed-8K": + suffix += "ernie_speed" + case "ERNIE-Speed-128K": + suffix += "ernie-speed-128k" + case "ERNIE-Lite-8K": + suffix += "ernie-lite-8k" + case "ERNIE-Tiny-8K": + suffix += "ernie-tiny-8k" case "BLOOMZ-7B": suffix += "bloomz_7b1" case "Embedding-V1": @@ -59,7 +69,7 @@ func (a *Adaptor) GetRequestURL(meta *util.RelayMeta) (string, error) { case "tao-8k": suffix += "tao_8k" default: - suffix += meta.ActualModelName + suffix += strings.ToLower(meta.ActualModelName) } fullRequestURL := fmt.Sprintf("%s/rpc/2.0/ai_custom/v1/wenxinworkshop/%s", meta.BaseURL, suffix) var accessToken string diff --git a/relay/channel/baidu/constants.go b/relay/channel/baidu/constants.go index 45a4e901..ccdc25c3 100644 --- a/relay/channel/baidu/constants.go +++ b/relay/channel/baidu/constants.go @@ -1,11 +1,18 @@ package baidu var ModelList = []string{ - "ERNIE-Bot-4", - "ERNIE-Bot-8K", - "ERNIE-Bot", - "ERNIE-Speed", - "ERNIE-Bot-turbo", + "ERNIE-4.0-8K", + "ERNIE-Bot-8K-0922", + "ERNIE-3.5-8K", + "ERNIE-Lite-8K-0922", + "ERNIE-Speed-8K", + "ERNIE-3.5-4K-0205", + "ERNIE-3.5-8K-0205", + "ERNIE-3.5-8K-1222", + "ERNIE-Lite-8K", + "ERNIE-Speed-128K", + "ERNIE-Tiny-8K", + "BLOOMZ-7B", "Embedding-V1", "bge-large-zh", "bge-large-en",