Ecosystem/ai-gateway
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: update ali constants and model ratio

Browse Source
This commit is contained in:
JustSong 2024-04-05 18:06:08 +08:00
parent b125358464
commit dfe79fa489
4 changed files with 19 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
common/model-ratio.go
View File

@ -88,20 +88,22 @@ var ModelRatio = map[string]float64{
"gemini-1.0-pro-001": 1,
"gemini-1.5-pro": 1,
// https://open.bigmodel.cn/pricing
"glm-4": 0.1 * RMB,
"glm-4v": 0.1 * RMB,
"glm-3-turbo": 0.005 * 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
"qwen-turbo": 0.5715, // ￥0.008 / 1k tokens // https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-thousand-questions-metering-and-billing
"glm-4": 0.1 * RMB,
"glm-4v": 0.1 * RMB,
"glm-3-turbo": 0.005 * 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
// 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
"stable-diffusion-xl": 0, // todo
"wanx-v1": 0, // todo
"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

1
relay/channel/ali/constants.go
View File

@ -3,4 +3,5 @@ package ali
var ModelList = []string{
"qwen-turbo", "qwen-plus", "qwen-max", "qwen-max-longcontext",
"text-embedding-v1",
"ali-stable-diffusion-xl", "ali-stable-diffusion-v1.5", "wanx-v1",
}

1
relay/channel/openai/adaptor.go
View File

@ -94,7 +94,6 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *util.Rel
default:
err, usage = Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
}
}
return
}

12
relay/channel/openai/main.go
View File

@ -154,15 +154,15 @@ func ImageHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCo
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), &imageResponse.Usage
return ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
}
err = resp.Body.Close()
if err != nil {
return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), &imageResponse.Usage
return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
}
err = json.Unmarshal(responseBody, &imageResponse)
if err != nil {
return ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), &imageResponse.Usage
return ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
}
resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
@ -174,11 +174,11 @@ func ImageHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCo
_, err = io.Copy(c.Writer, resp.Body)
if err != nil {
return ErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), &imageResponse.Usage
return ErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
}
err = resp.Body.Close()
if err != nil {
return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), &imageResponse.Usage
return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
}
return nil, nil
return nil, &imageResponse.Usage
}