xinyin025/new-api
1
0
Fork 0
mirror of https://github.com/linux-do/new-api.git synced 2025-11-04 13:23:42 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: add claude-3.7-sonnet model support

Browse Source
This commit is contained in:
wozulong
2025-02-25 19:54:30 +08:00
parent b648816add
commit 7c0b93c38c
6 changed files with 195 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

257
common/model-ratio.go
View File

@@ -23,133 +23,136 @@ const (
var defaultModelRatio = map[string]float64{
//"midjourney": 50,
"gpt-4-gizmo-*": 15,
"g-*": 15,
"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-4o-mini": 0.075, // $0.00015 / 1K tokens
"gpt-4o-mini-2024-07-18": 0.075,
"chatgpt-4o-latest": 2.5, // $0.01 / 1K tokens
"gpt-4o": 1.25, // $0.005 / 1K tokens
"gpt-4o-2024-05-13": 2.5, // $0.005 / 1K tokens
"gpt-4o-2024-08-06": 1.25, // $0.01 / 1K tokens
"gpt-4o-2024-11-20": 1.25, // $0.01 / 1K tokens
"o1-preview": 7.5,
"o1-preview-2024-09-12": 7.5,
"o1-mini": 0.55, // $0.0011 / 1K tokens
"o1-mini-2024-09-12": 0.55,
"o3-mini": 0.55,
"o3-mini-2025-01-31": 0.55,
"gpt-4-turbo": 5, // $0.01 / 1K tokens
"gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens
"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-vision-preview": 5, // $0.01 / 1K tokens
"gpt-4-1106-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,
"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-3-5-sonnet-20240620": 1.5, // $3 / 1M tokens
"claude-3-5-sonnet-20241022": 1.5, // $3 / 1M tokens
"claude-3-sonnet-20240229": 1.5, // $3 / 1M tokens
"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
"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
"gpt-4-gizmo-*": 15,
"g-*": 15,
"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-4o-mini": 0.075, // $0.00015 / 1K tokens
"gpt-4o-mini-2024-07-18": 0.075,
"chatgpt-4o-latest": 2.5, // $0.01 / 1K tokens
"gpt-4o": 1.25, // $0.005 / 1K tokens
"gpt-4o-2024-05-13": 2.5, // $0.005 / 1K tokens
"gpt-4o-2024-08-06": 1.25, // $0.01 / 1K tokens
"gpt-4o-2024-11-20": 1.25, // $0.01 / 1K tokens
"o1-preview": 7.5,
"o1-preview-2024-09-12": 7.5,
"o1-mini": 0.55, // $0.0011 / 1K tokens
"o1-mini-2024-09-12": 0.55,
"o3-mini": 0.55,
"o3-mini-2025-01-31": 0.55,
"gpt-4-turbo": 5, // $0.01 / 1K tokens
"gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens
"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-vision-preview": 5, // $0.01 / 1K tokens
"gpt-4-1106-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,
"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-3-7-sonnet-20250219": 1.5,
"claude-3-7-sonnet-20250219-thinking": 1.5,
"claude-3-5-haiku-20241022": 0.4,
"claude-3-haiku-20240307": 0.125, // $0.25 / 1M tokens
"claude-3-5-sonnet-20240620": 1.5, // $3 / 1M tokens
"claude-3-5-sonnet-20241022": 1.5, // $3 / 1M tokens
"claude-3-sonnet-20240229": 1.5, // $3 / 1M tokens
"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
"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,

18
dto/text_request.go
View File

@@ -36,6 +36,13 @@ type GeneralOpenAIRequest struct {
Dimensions int `json:"dimensions,omitempty"`
ParallelToolCalls bool `json:"parallel_tool_calls,omitempty"`
EncodingFormat any `json:"encoding_format,omitempty"`
Thinking *Thinking `json:"thinking,omitempty"`
}
type Thinking struct {
Type string `json:"type"`
BudgetTokens int `json:"budget_tokens"`
}
type OpenAITools struct {
@@ -77,11 +84,12 @@ func (r GeneralOpenAIRequest) ParseInput() []string {
}
type Message struct {
Role string `json:"role"`
Content json.RawMessage `json:"content"`
Name *string `json:"name,omitempty"`
ToolCalls any `json:"tool_calls,omitempty"`
ToolCallId string `json:"tool_call_id,omitempty"`
Role string `json:"role"`
Content json.RawMessage `json:"content"`
ReasoningContent *string `json:"reasoning_content,omitempty"`
Name *string `json:"name,omitempty"`
ToolCalls any `json:"tool_calls,omitempty"`
ToolCallId string `json:"tool_call_id,omitempty"`
}
type MediaMessage struct {

7
dto/text_response.go
View File

@@ -62,9 +62,10 @@ type ChatCompletionsStreamResponseChoice struct {
}
type ChatCompletionsStreamResponseChoiceDelta struct {
Content *string `json:"content,omitempty"`
Role string `json:"role,omitempty"`
ToolCalls []ToolCall `json:"tool_calls,omitempty"`
Content *string `json:"content,omitempty"`
ReasoningContent *string `json:"reasoning_content,omitempty"`
Role string `json:"role,omitempty"`
ToolCalls []ToolCall `json:"tool_calls,omitempty"`
}
func (c *ChatCompletionsStreamResponseChoiceDelta) SetContentString(s string) {

3
relay/channel/claude/constants.go
View File

@@ -8,8 +8,11 @@ var ModelList = []string{
"claude-3-sonnet-20240229",
"claude-3-opus-20240229",
"claude-3-haiku-20240307",
"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"

12
relay/channel/claude/dto.go
View File

@@ -1,5 +1,7 @@
package claude
import "one-api/dto"
type ClaudeMetadata struct {
UserId string `json:"user_id"`
}
@@ -11,6 +13,9 @@ 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"`
@@ -58,9 +63,10 @@ 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 *dto.Thinking `json:"thinking,omitempty"`
}
type ClaudeError struct {

38
relay/channel/claude/relay-claude.go
View File

@@ -62,6 +62,24 @@ func RequestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *ClaudeR
func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeRequest, error) {
claudeTools := make([]Tool, 0, len(textRequest.Tools))
if strings.HasSuffix(textRequest.Model, "-thinking") {
textRequest.Model = strings.TrimSuffix(textRequest.Model, "-thinking")
if textRequest.MaxTokens == 0 {
textRequest.MaxTokens = 4096
} else if textRequest.MaxTokens < 1280 {
textRequest.MaxTokens = 1280
}
textRequest.TopP = 0
textRequest.TopK = 0
textRequest.Temperature = 0
textRequest.Thinking = &dto.Thinking{
Type: "enabled",
BudgetTokens: int(float64(textRequest.MaxTokens) * 0.8),
}
}
for _, tool := range textRequest.Tools {
claudeTool := Tool{
Name: tool.Function.Name,
@@ -113,6 +131,7 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
Stream: textRequest.Stream,
Tools: claudeTools,
ToolChoice: textRequest.ToolChoice,
Thinking: textRequest.Thinking,
}
if claudeRequest.MaxTokens == 0 {
claudeRequest.MaxTokens = 4096
@@ -334,12 +353,19 @@ 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":
reasoningContent := "\n"
choice.Delta.ReasoningContent = &reasoningContent
case "thinking_delta":
reasoningContent := claudeResponse.Delta.Thinking
choice.Delta.ReasoningContent = &reasoningContent
}
}
} else if claudeResponse.Type == "message_delta" {
@@ -377,6 +403,8 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
if len(claudeResponse.Content) > 0 {
responseText = claudeResponse.Content[0].Text
}
reasoningContent := ""
tools := make([]dto.ToolCall, 0)
if reqMode == RequestModeCompletion {
content, _ := json.Marshal(strings.TrimPrefix(claudeResponse.Completion, " "))
@@ -393,7 +421,8 @@ 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,
@@ -403,6 +432,10 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
Arguments: string(args),
},
})
case "thinking":
reasoningContent = message.Thinking
case "text":
responseText = message.Text
}
}
}
@@ -417,6 +450,7 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
if len(tools) > 0 {
choice.Message.ToolCalls = tools
}
choice.Message.ReasoningContent = &reasoningContent
fullTextResponse.Model = claudeResponse.Model
choices = append(choices, choice)
fullTextResponse.Choices = choices