Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Calcium-Ion
|
f5cbab77cf | ||
|
1808837298@qq.com
|
d4706d6b8e | ||
|
1808837298@qq.com
|
6c8016e5f8 | ||
|
MartialBE
|
7160012fe2 | ||
|
1808837298@qq.com
|
c62276fcc4 | ||
|
1808837298@qq.com
|
15a3b44689 | ||
|
1808837298@qq.com
|
8f3c7280cf |
+88
-86
@@ -83,92 +83,94 @@ var defaultModelRatio = map[string]float64{
|
||||
"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-3-5-haiku-20241022": 0.5, // $1 / 1M tokens
|
||||
"claude-3-sonnet-20240229": 1.5, // $3 / 1M tokens
|
||||
"claude-3-5-sonnet-20240620": 1.5,
|
||||
"claude-3-5-sonnet-20241022": 1.5,
|
||||
"claude-3-opus-20240229": 7.5, // $15 / 1M tokens
|
||||
"ERNIE-4.0-8K": 0.120 * RMB,
|
||||
"ERNIE-3.5-8K": 0.012 * RMB,
|
||||
"ERNIE-3.5-8K-0205": 0.024 * RMB,
|
||||
"ERNIE-3.5-8K-1222": 0.012 * RMB,
|
||||
"ERNIE-Bot-8K": 0.024 * RMB,
|
||||
"ERNIE-3.5-4K-0205": 0.012 * RMB,
|
||||
"ERNIE-Speed-8K": 0.004 * RMB,
|
||||
"ERNIE-Speed-128K": 0.004 * RMB,
|
||||
"ERNIE-Lite-8K-0922": 0.008 * RMB,
|
||||
"ERNIE-Lite-8K-0308": 0.003 * 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,
|
||||
"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": 1.75, // $3.5 / 1M tokens
|
||||
"gemini-1.5-pro-exp-0827": 1.75, // $3.5 / 1M tokens
|
||||
"gemini-1.5-flash-latest": 1,
|
||||
"gemini-1.5-flash-exp-0827": 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": 0.05 * RMB, // ￥0.05 / 1k tokens
|
||||
"glm-4-alltools": 0.1 * RMB, // ￥0.1 / 1k tokens
|
||||
"glm-3-turbo": 0.3572,
|
||||
"glm-4-plus": 0.05 * RMB,
|
||||
"glm-4-0520": 0.1 * RMB,
|
||||
"glm-4-air": 0.001 * RMB,
|
||||
"glm-4-airx": 0.01 * RMB,
|
||||
"glm-4-long": 0.001 * RMB,
|
||||
"glm-4-flash": 0,
|
||||
"glm-4v-plus": 0.01 * RMB,
|
||||
"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
|
||||
"SparkDesk-v4.0": 1.2858,
|
||||
"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
|
||||
"360gpt2-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
|
||||
"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-3-5-haiku-20241022": 0.5, // $1 / 1M tokens
|
||||
"claude-3-sonnet-20240229": 1.5, // $3 / 1M tokens
|
||||
"claude-3-5-sonnet-20240620": 1.5,
|
||||
"claude-3-5-sonnet-20241022": 1.5,
|
||||
"claude-3-7-sonnet-20250219": 1.5,
|
||||
"claude-3-7-sonnet-20250219-thinking": 1.5,
|
||||
"claude-3-opus-20240229": 7.5, // $15 / 1M tokens
|
||||
"ERNIE-4.0-8K": 0.120 * RMB,
|
||||
"ERNIE-3.5-8K": 0.012 * RMB,
|
||||
"ERNIE-3.5-8K-0205": 0.024 * RMB,
|
||||
"ERNIE-3.5-8K-1222": 0.012 * RMB,
|
||||
"ERNIE-Bot-8K": 0.024 * RMB,
|
||||
"ERNIE-3.5-4K-0205": 0.012 * RMB,
|
||||
"ERNIE-Speed-8K": 0.004 * RMB,
|
||||
"ERNIE-Speed-128K": 0.004 * RMB,
|
||||
"ERNIE-Lite-8K-0922": 0.008 * RMB,
|
||||
"ERNIE-Lite-8K-0308": 0.003 * 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,
|
||||
"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": 1.75, // $3.5 / 1M tokens
|
||||
"gemini-1.5-pro-exp-0827": 1.75, // $3.5 / 1M tokens
|
||||
"gemini-1.5-flash-latest": 1,
|
||||
"gemini-1.5-flash-exp-0827": 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": 0.05 * RMB, // ￥0.05 / 1k tokens
|
||||
"glm-4-alltools": 0.1 * RMB, // ￥0.1 / 1k tokens
|
||||
"glm-3-turbo": 0.3572,
|
||||
"glm-4-plus": 0.05 * RMB,
|
||||
"glm-4-0520": 0.1 * RMB,
|
||||
"glm-4-air": 0.001 * RMB,
|
||||
"glm-4-airx": 0.01 * RMB,
|
||||
"glm-4-long": 0.001 * RMB,
|
||||
"glm-4-flash": 0,
|
||||
"glm-4v-plus": 0.01 * RMB,
|
||||
"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
|
||||
"SparkDesk-v4.0": 1.2858,
|
||||
"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
|
||||
"360gpt2-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,
|
||||
|
||||
@@ -9,7 +9,8 @@ var awsModelIDMap = map[string]string{
|
||||
"claude-3-haiku-20240307": "anthropic.claude-3-haiku-20240307-v1:0",
|
||||
"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
|
||||
"claude-3-5-sonnet-20241022": "anthropic.claude-3-5-sonnet-20241022-v2:0",
|
||||
"claude-3-5-haiku-20241022": "anthropic.claude-3-5-haiku-20241022-v1:0",
|
||||
"claude-3-5-haiku-20241022": "anthropic.claude-3-5-haiku-20241022-v1:0",
|
||||
"claude-3-7-sonnet-20250219": "anthropic.claude-3-7-sonnet-20250219-v1:0",
|
||||
}
|
||||
|
||||
var ChannelName = "aws"
|
||||
|
||||
@@ -16,6 +16,7 @@ type AwsClaudeRequest struct {
|
||||
StopSequences []string `json:"stop_sequences,omitempty"`
|
||||
Tools []claude.Tool `json:"tools,omitempty"`
|
||||
ToolChoice any `json:"tool_choice,omitempty"`
|
||||
Thinking *claude.Thinking `json:"thinking,omitempty"`
|
||||
}
|
||||
|
||||
func copyRequest(req *claude.ClaudeRequest) *AwsClaudeRequest {
|
||||
@@ -30,5 +31,6 @@ func copyRequest(req *claude.ClaudeRequest) *AwsClaudeRequest {
|
||||
StopSequences: req.StopSequences,
|
||||
Tools: req.Tools,
|
||||
ToolChoice: req.ToolChoice,
|
||||
Thinking: req.Thinking,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,6 +11,8 @@ var ModelList = []string{
|
||||
"claude-3-5-haiku-20241022",
|
||||
"claude-3-5-sonnet-20240620",
|
||||
"claude-3-5-sonnet-20241022",
|
||||
"claude-3-7-sonnet-20250219",
|
||||
"claude-3-7-sonnet-20250219-thinking",
|
||||
}
|
||||
|
||||
var ChannelName = "claude"
|
||||
|
||||
@@ -11,6 +11,9 @@ type ClaudeMediaMessage struct {
|
||||
Usage *ClaudeUsage `json:"usage,omitempty"`
|
||||
StopReason *string `json:"stop_reason,omitempty"`
|
||||
PartialJson string `json:"partial_json,omitempty"`
|
||||
Thinking string `json:"thinking,omitempty"`
|
||||
Signature string `json:"signature,omitempty"`
|
||||
Delta string `json:"delta,omitempty"`
|
||||
// tool_calls
|
||||
Id string `json:"id,omitempty"`
|
||||
Name string `json:"name,omitempty"`
|
||||
@@ -54,9 +57,15 @@ type ClaudeRequest struct {
|
||||
TopP float64 `json:"top_p,omitempty"`
|
||||
TopK int `json:"top_k,omitempty"`
|
||||
//ClaudeMetadata `json:"metadata,omitempty"`
|
||||
Stream bool `json:"stream,omitempty"`
|
||||
Tools []Tool `json:"tools,omitempty"`
|
||||
ToolChoice any `json:"tool_choice,omitempty"`
|
||||
Stream bool `json:"stream,omitempty"`
|
||||
Tools []Tool `json:"tools,omitempty"`
|
||||
ToolChoice any `json:"tool_choice,omitempty"`
|
||||
Thinking *Thinking `json:"thinking,omitempty"`
|
||||
}
|
||||
|
||||
type Thinking struct {
|
||||
Type string `json:"type"`
|
||||
BudgetTokens int `json:"budget_tokens"`
|
||||
}
|
||||
|
||||
type ClaudeError struct {
|
||||
|
||||
@@ -92,6 +92,25 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
|
||||
Stream: textRequest.Stream,
|
||||
Tools: claudeTools,
|
||||
}
|
||||
|
||||
if strings.HasSuffix(textRequest.Model, "-thinking") {
|
||||
if claudeRequest.MaxTokens == 0 {
|
||||
claudeRequest.MaxTokens = 8192
|
||||
}
|
||||
|
||||
// 因为BudgetTokens 必须大于1024
|
||||
if claudeRequest.MaxTokens < 1280 {
|
||||
claudeRequest.MaxTokens = 1280
|
||||
}
|
||||
|
||||
// BudgetTokens 为 max_tokens 的 80%
|
||||
claudeRequest.Thinking = &Thinking{
|
||||
Type: "enabled",
|
||||
BudgetTokens: int(float64(claudeRequest.MaxTokens) * 0.8),
|
||||
}
|
||||
claudeRequest.Model = strings.TrimSuffix(textRequest.Model, "-thinking")
|
||||
}
|
||||
|
||||
if claudeRequest.MaxTokens == 0 {
|
||||
claudeRequest.MaxTokens = 4096
|
||||
}
|
||||
@@ -308,12 +327,20 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
|
||||
if claudeResponse.Delta != nil {
|
||||
choice.Index = claudeResponse.Index
|
||||
choice.Delta.SetContentString(claudeResponse.Delta.Text)
|
||||
if claudeResponse.Delta.Type == "input_json_delta" {
|
||||
switch claudeResponse.Delta.Type {
|
||||
case "input_json_delta":
|
||||
tools = append(tools, dto.ToolCall{
|
||||
Function: dto.FunctionCall{
|
||||
Arguments: claudeResponse.Delta.PartialJson,
|
||||
},
|
||||
})
|
||||
case "signature_delta":
|
||||
// 加密的不处理
|
||||
signatureContent := "\n"
|
||||
choice.Delta.ReasoningContent = &signatureContent
|
||||
case "thinking_delta":
|
||||
thinkingContent := claudeResponse.Delta.Thinking
|
||||
choice.Delta.ReasoningContent = &thinkingContent
|
||||
}
|
||||
}
|
||||
} else if claudeResponse.Type == "message_delta" {
|
||||
@@ -352,6 +379,8 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
|
||||
responseText = claudeResponse.Content[0].Text
|
||||
}
|
||||
tools := make([]dto.ToolCall, 0)
|
||||
thinkingContent := ""
|
||||
|
||||
if reqMode == RequestModeCompletion {
|
||||
content, _ := json.Marshal(strings.TrimPrefix(claudeResponse.Completion, " "))
|
||||
choice := dto.OpenAITextResponseChoice{
|
||||
@@ -367,7 +396,8 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
|
||||
} else {
|
||||
fullTextResponse.Id = claudeResponse.Id
|
||||
for _, message := range claudeResponse.Content {
|
||||
if message.Type == "tool_use" {
|
||||
switch message.Type {
|
||||
case "tool_use":
|
||||
args, _ := json.Marshal(message.Input)
|
||||
tools = append(tools, dto.ToolCall{
|
||||
ID: message.Id,
|
||||
@@ -377,6 +407,11 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
|
||||
Arguments: string(args),
|
||||
},
|
||||
})
|
||||
case "thinking":
|
||||
// 加密的不管， 只输出明文的推理过程
|
||||
thinkingContent = message.Thinking
|
||||
case "text":
|
||||
responseText = message.Text
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -391,6 +426,7 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
|
||||
if len(tools) > 0 {
|
||||
choice.Message.SetToolCalls(tools)
|
||||
}
|
||||
choice.Message.ReasoningContent = thinkingContent
|
||||
fullTextResponse.Model = claudeResponse.Model
|
||||
choices = append(choices, choice)
|
||||
fullTextResponse.Choices = choices
|
||||
|
||||
@@ -11,6 +11,7 @@ type OllamaRequest struct {
|
||||
Topp float64 `json:"top_p,omitempty"`
|
||||
TopK int `json:"top_k,omitempty"`
|
||||
Stop any `json:"stop,omitempty"`
|
||||
MaxTokens uint `json:"max_tokens,omitempty"`
|
||||
Tools []dto.ToolCall `json:"tools,omitempty"`
|
||||
ResponseFormat any `json:"response_format,omitempty"`
|
||||
FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
|
||||
|
||||
@@ -58,6 +58,7 @@ func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) (*OllamaRequest, err
|
||||
TopK: request.TopK,
|
||||
Stop: Stop,
|
||||
Tools: request.Tools,
|
||||
MaxTokens: request.MaxTokens,
|
||||
ResponseFormat: request.ResponseFormat,
|
||||
FrequencyPenalty: request.FrequencyPenalty,
|
||||
PresencePenalty: request.PresencePenalty,
|
||||
|
||||
Reference in New Issue
Block a user