Merge pull request #1020 from QuantumNous/v1responses

feat: support /v1/responses API

controller/relay.go

@@ -4,8 +4,6 @@ import (
 	"bytes"
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
-	"github.com/gorilla/websocket"
 	"io"
 	"log"
 	"net/http"
@@ -20,6 +18,9 @@ import (
 	"one-api/relay/helper"
 	"one-api/service"
 	"strings"
+
+	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 )
 
 func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
@@ -37,6 +38,8 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 		err = relay.RerankHelper(c, relayMode)
 	case relayconstant.RelayModeEmbeddings:
 		err = relay.EmbeddingHelper(c)
+	case relayconstant.RelayModeResponses:
+		err = relay.ResponsesHelper(c)
 	default:
 		err = relay.TextHelper(c)
 	}

dto/openai_request.go

@@ -370,3 +370,49 @@ func (m *Message) ParseContent() []MediaContent {
 	}
 	return contentList
 }
+
+type OpenAIResponsesRequest struct {
+	Model              string               `json:"model"`
+	Input              json.RawMessage      `json:"input,omitempty"`
+	Include            json.RawMessage      `json:"include,omitempty"`
+	Instructions       json.RawMessage      `json:"instructions,omitempty"`
+	MaxOutputTokens    uint                 `json:"max_output_tokens,omitempty"`
+	Metadata           json.RawMessage      `json:"metadata,omitempty"`
+	ParallelToolCalls  bool                 `json:"parallel_tool_calls,omitempty"`
+	PreviousResponseID string               `json:"previous_response_id,omitempty"`
+	Reasoning          *Reasoning           `json:"reasoning,omitempty"`
+	ServiceTier        string               `json:"service_tier,omitempty"`
+	Store              bool                 `json:"store,omitempty"`
+	Stream             bool                 `json:"stream,omitempty"`
+	Temperature        float64              `json:"temperature,omitempty"`
+	Text               json.RawMessage      `json:"text,omitempty"`
+	ToolChoice         json.RawMessage      `json:"tool_choice,omitempty"`
+	Tools              []ResponsesToolsCall `json:"tools,omitempty"`
+	TopP               float64              `json:"top_p,omitempty"`
+	Truncation         string               `json:"truncation,omitempty"`
+	User               string               `json:"user,omitempty"`
+}
+
+type Reasoning struct {
+	Effort  string `json:"effort,omitempty"`
+	Summary string `json:"summary,omitempty"`
+}
+
+type ResponsesToolsCall struct {
+	Type string `json:"type"`
+	// Web Search
+	UserLocation      json.RawMessage `json:"user_location,omitempty"`
+	SearchContextSize string          `json:"search_context_size,omitempty"`
+	// File Search
+	VectorStoreIds []string        `json:"vector_store_ids,omitempty"`
+	MaxNumResults  uint            `json:"max_num_results,omitempty"`
+	Filters        json.RawMessage `json:"filters,omitempty"`
+	// Computer Use
+	DisplayWidth  uint   `json:"display_width,omitempty"`
+	DisplayHeight uint   `json:"display_height,omitempty"`
+	Environment   string `json:"environment,omitempty"`
+	// Function
+	Name        string          `json:"name,omitempty"`
+	Description string          `json:"description,omitempty"`
+	Parameters  json.RawMessage `json:"parameters,omitempty"`
+}

dto/openai_response.go

 package dto
 
+import "encoding/json"
+
 type SimpleResponse struct {
 	Usage `json:"usage"`
 	Error *OpenAIError `json:"error"`
@@ -191,3 +193,63 @@ type OutputTokenDetails struct {
 	AudioTokens     int `json:"audio_tokens"`
 	ReasoningTokens int `json:"reasoning_tokens"`
 }
+
+type OpenAIResponsesResponse struct {
+	ID                 string             `json:"id"`
+	Object             string             `json:"object"`
+	CreatedAt          int                `json:"created_at"`
+	Status             string             `json:"status"`
+	Error              *OpenAIError       `json:"error,omitempty"`
+	IncompleteDetails  *IncompleteDetails `json:"incomplete_details,omitempty"`
+	Instructions       string             `json:"instructions"`
+	MaxOutputTokens    int                `json:"max_output_tokens"`
+	Model              string             `json:"model"`
+	Output             []ResponsesOutput  `json:"output"`
+	ParallelToolCalls  bool               `json:"parallel_tool_calls"`
+	PreviousResponseID string             `json:"previous_response_id"`
+	Reasoning          *Reasoning         `json:"reasoning"`
+	Store              bool               `json:"store"`
+	Temperature        float64            `json:"temperature"`
+	ToolChoice         string             `json:"tool_choice"`
+	Tools              []interface{}      `json:"tools"`
+	TopP               float64            `json:"top_p"`
+	Truncation         string             `json:"truncation"`
+	Usage              *Usage             `json:"usage"`
+	User               json.RawMessage    `json:"user"`
+	Metadata           json.RawMessage    `json:"metadata"`
+}
+
+type IncompleteDetails struct {
+	Reasoning string `json:"reasoning"`
+}
+
+type ResponsesOutput struct {
+	Type    string                   `json:"type"`
+	ID      string                   `json:"id"`
+	Status  string                   `json:"status"`
+	Role    string                   `json:"role"`
+	Content []ResponsesOutputContent `json:"content"`
+}
+
+type ResponsesOutputContent struct {
+	Type        string        `json:"type"`
+	Text        string        `json:"text"`
+	Annotations []interface{} `json:"annotations"`
+}
+
+const (
+	BuildInTools_WebSearch  = "web_search_preview"
+	BuildInTools_FileSearch = "file_search"
+)
+
+const (
+	ResponsesOutputTypeItemAdded = "response.output_item.added"
+	ResponsesOutputTypeItemDone  = "response.output_item.done"
+)
+
+// ResponsesStreamResponse 用于处理 /v1/responses 流式响应
+type ResponsesStreamResponse struct {
+	Type     string                   `json:"type"`
+	Response *OpenAIResponsesResponse `json:"response"`
+	Delta    string                   `json:"delta,omitempty"`
+}

relay/channel/adapter.go

 package channel
 
 import (
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	relaycommon "one-api/relay/common"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor interface {
@@ -18,6 +19,7 @@ type Adaptor interface {
 	ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error)
 	ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error)
 	ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error)
+	ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error)
 	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error)
 	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode)
 	GetModelList() []string

relay/channel/ali/adaptor.go

@@ -3,7 +3,6 @@ package ali
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -11,6 +10,8 @@ import (
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -79,6 +80,11 @@ func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInf
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/aws/adaptor.go

@@ -2,13 +2,14 @@ package aws
 
 import (
 	"errors"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel/claude"
 	relaycommon "one-api/relay/common"
 	"one-api/setting/model_setting"
+
+	"github.com/gin-gonic/gin"
 )
 
 const (
@@ -74,6 +75,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return nil, nil
 }

relay/channel/baidu/adaptor.go

@@ -3,7 +3,6 @@ package baidu
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -11,6 +10,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -130,6 +131,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return baiduEmbeddingRequest, nil
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/baidu_v2/adaptor.go

@@ -3,13 +3,14 @@ package baidu_v2
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -60,6 +61,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/claude/adaptor.go

@@ -3,7 +3,6 @@ package claude
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -11,6 +10,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/setting/model_setting"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 const (
@@ -84,6 +85,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/cloudflare/adaptor.go

@@ -55,6 +55,11 @@ func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayIn
 	}
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/cohere/adaptor.go

@@ -3,13 +3,14 @@ package cohere
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -52,6 +53,11 @@ func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayIn
 	return requestOpenAI2Cohere(*request), nil
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/deepseek/adaptor.go

@@ -3,7 +3,6 @@ package deepseek
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -12,6 +11,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -71,6 +72,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/dify/adaptor.go

@@ -3,12 +3,13 @@ package dify
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
+
+	"github.com/gin-gonic/gin"
 )
 
 const (
@@ -86,6 +87,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/gemini/adaptor.go

@@ -155,6 +155,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return geminiRequest, nil
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/jina/adaptor.go

@@ -3,7 +3,6 @@ package jina
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -12,6 +11,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/relay/common_handler"
 	"one-api/relay/constant"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -55,6 +56,11 @@ func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayIn
 	return request, nil
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/mistral/adaptor.go

@@ -2,13 +2,14 @@ package mistral
 
 import (
 	"errors"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -59,6 +60,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/mokaai/adaptor.go

@@ -3,7 +3,6 @@ package mokaai
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -11,6 +10,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -74,6 +75,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/ollama/adaptor.go

@@ -2,7 +2,6 @@ package ollama
 
 import (
 	"errors"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -10,6 +9,8 @@ import (
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -64,6 +65,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return requestOpenAI2Embeddings(request), nil
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/openai/adaptor.go

@@ -25,8 +25,9 @@ import (
 	"path/filepath"
 	"strings"
 
-	"github.com/gin-gonic/gin"
 	"net/textproto"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -67,6 +68,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	if info.RelayFormat == relaycommon.RelayFormatClaude {
 		return fmt.Sprintf("%s/v1/chat/completions", info.BaseUrl), nil
 	}
+	if info.RelayMode == constant.RelayModeResponses {
+		return fmt.Sprintf("%s/v1/responses", info.BaseUrl), nil
+	}
 	if info.RelayMode == constant.RelayModeRealtime {
 		if strings.HasPrefix(info.BaseUrl, "https://") {
 			baseUrl := strings.TrimPrefix(info.BaseUrl, "https://")
@@ -380,6 +384,21 @@ func detectImageMimeType(filename string) string {
 	}
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// 模型后缀转换 reasoning effort
+	if strings.HasSuffix(request.Model, "-high") {
+		request.Reasoning.Effort = "high"
+		request.Model = strings.TrimSuffix(request.Model, "-high")
+	} else if strings.HasSuffix(request.Model, "-low") {
+		request.Reasoning.Effort = "low"
+		request.Model = strings.TrimSuffix(request.Model, "-low")
+	} else if strings.HasSuffix(request.Model, "-medium") {
+		request.Reasoning.Effort = "medium"
+		request.Model = strings.TrimSuffix(request.Model, "-medium")
+	}
+	return request, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	if info.RelayMode == constant.RelayModeAudioTranscription ||
 		info.RelayMode == constant.RelayModeAudioTranslation ||
@@ -406,6 +425,12 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 		err, usage = OpenaiHandlerWithUsage(c, resp, info)
 	case constant.RelayModeRerank:
 		err, usage = common_handler.RerankHandler(c, info, resp)
+	case constant.RelayModeResponses:
+		if info.IsStream {
+			err, usage = OaiResponsesStreamHandler(c, resp, info)
+		} else {
+			err, usage = OpenaiResponsesHandler(c, resp, info)
+		}
 	default:
 		if info.IsStream {
 			err, usage = OaiStreamHandler(c, resp, info)

relay/channel/openai/relay-openai.go

@@ -644,3 +644,104 @@ func OpenaiHandlerWithUsage(c *gin.Context, resp *http.Response, info *relaycomm
 	}
 	return nil, &usageResp.Usage
 }
+
+func OpenaiResponsesHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	// read response body
+	var responsesResponse dto.OpenAIResponsesResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = common.DecodeJson(responseBody, &responsesResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if responsesResponse.Error != nil {
+		return &dto.OpenAIErrorWithStatusCode{
+			Error: dto.OpenAIError{
+				Message: responsesResponse.Error.Message,
+				Type:    "openai_error",
+				Code:    responsesResponse.Error.Code,
+			},
+			StatusCode: resp.StatusCode,
+		}, nil
+	}
+
+	// reset response body
+	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+	// We shouldn't set the header before we parse the response body, because the parse part may fail.
+	// And then we will have to send an error response, but in this case, the header has already been set.
+	// So the httpClient will be confused by the response.
+	// For example, Postman will report error, and we cannot check the response at all.
+	for k, v := range resp.Header {
+		c.Writer.Header().Set(k, v[0])
+	}
+	c.Writer.WriteHeader(resp.StatusCode)
+	// copy response body
+	_, err = io.Copy(c.Writer, resp.Body)
+	if err != nil {
+		common.SysError("error copying response body: " + err.Error())
+	}
+	resp.Body.Close()
+	// compute usage
+	usage := dto.Usage{}
+	usage.PromptTokens = responsesResponse.Usage.InputTokens
+	usage.CompletionTokens = responsesResponse.Usage.OutputTokens
+	usage.TotalTokens = responsesResponse.Usage.TotalTokens
+	return nil, &usage
+}
+
+func OaiResponsesStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	if resp == nil || resp.Body == nil {
+		common.LogError(c, "invalid response or response body")
+		return service.OpenAIErrorWrapper(fmt.Errorf("invalid response"), "invalid_response", http.StatusInternalServerError), nil
+	}
+
+	var usage = &dto.Usage{}
+	var responseTextBuilder strings.Builder
+
+	helper.StreamScannerHandler(c, resp, info, func(data string) bool {
+
+		// 检查当前数据是否包含 completed 状态和 usage 信息
+		var streamResponse dto.ResponsesStreamResponse
+		if err := common.DecodeJsonStr(data, &streamResponse); err == nil {
+			sendResponsesStreamData(c, streamResponse, data)
+			switch streamResponse.Type {
+			case "response.completed":
+				usage.PromptTokens = streamResponse.Response.Usage.InputTokens
+				usage.CompletionTokens = streamResponse.Response.Usage.OutputTokens
+				usage.TotalTokens = streamResponse.Response.Usage.TotalTokens
+			case "response.output_text.delta":
+				// 处理输出文本
+				responseTextBuilder.WriteString(streamResponse.Delta)
+
+			}
+		}
+		return true
+	})
+
+	helper.Done(c)
+
+	if usage.CompletionTokens == 0 {
+		// 计算输出文本的 token 数量
+		tempStr := responseTextBuilder.String()
+		if len(tempStr) > 0 {
+			// 非正常结束，使用输出文本的 token 数量
+			completionTokens, _ := service.CountTextToken(tempStr, info.UpstreamModelName)
+			usage.CompletionTokens = completionTokens
+		}
+	}
+
+	return nil, usage
+}
+
+func sendResponsesStreamData(c *gin.Context, streamResponse dto.ResponsesStreamResponse, data string) {
+	if data == "" {
+		return
+	}
+	helper.ResponseChunkData(c, streamResponse, data)
+}

relay/channel/palm/adaptor.go

@@ -3,13 +3,14 @@ package palm
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -60,6 +61,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/perplexity/adaptor.go

@@ -3,13 +3,14 @@ package perplexity
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -63,6 +64,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/siliconflow/adaptor.go

@@ -3,7 +3,6 @@ package siliconflow
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -11,6 +10,8 @@ import (
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -58,6 +59,11 @@ func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayIn
 	return request, nil
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/tencent/adaptor.go

@@ -3,7 +3,6 @@ package tencent
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
@@ -13,6 +12,8 @@ import (
 	"one-api/service"
 	"strconv"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -84,6 +85,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/vertex/adaptor.go

@@ -4,7 +4,6 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -15,6 +14,8 @@ import (
 	"one-api/setting/model_setting"
 	relaycommon "one-api/relay/common"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 const (
@@ -174,6 +175,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/volcengine/adaptor.go

@@ -3,7 +3,6 @@ package volcengine
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -12,6 +11,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -71,6 +72,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return request, nil
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/xai/adaptor.go

@@ -3,13 +3,14 @@ package xai
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -78,6 +79,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not available")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/xunfei/adaptor.go

@@ -2,7 +2,6 @@ package xunfei
 
 import (
 	"errors"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -10,6 +9,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -61,6 +62,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	// xunfei's request is not http request, so we don't need to do anything here
 	dummyResp := &http.Response{}

relay/channel/zhipu/adaptor.go

@@ -3,12 +3,13 @@ package zhipu
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -71,6 +72,11 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = zhipuStreamHandler(c, resp)

relay/channel/zhipu_4v/adaptor.go

@@ -3,7 +3,6 @@ package zhipu_4v
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
@@ -11,6 +10,8 @@ import (
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -70,6 +71,11 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return request, nil
 }
 
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	// TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/common/relay_info.go

@@ -200,6 +200,10 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 	if streamSupportedChannels[info.ChannelType] {
 		info.SupportStreamOptions = true
 	}
+	// responses 模式不支持 StreamOptions
+	if relayconstant.RelayModeResponses == info.RelayMode {
+		info.SupportStreamOptions = false
+	}
 	return info
 }
 

relay/constant/relay_mode.go

@@ -40,6 +40,8 @@ const (
 
 	RelayModeRerank
 
+	RelayModeResponses
+
 	RelayModeRealtime
 )
 
@@ -61,6 +63,8 @@ func Path2RelayMode(path string) int {
 		relayMode = RelayModeImagesEdits
 	} else if strings.HasPrefix(path, "/v1/edits") {
 		relayMode = RelayModeEdits
+	} else if strings.HasPrefix(path, "/v1/responses") {
+		relayMode = RelayModeResponses
 	} else if strings.HasPrefix(path, "/v1/audio/speech") {
 		relayMode = RelayModeAudioSpeech
 	} else if strings.HasPrefix(path, "/v1/audio/transcriptions") {

relay/helper/common.go

@@ -43,6 +43,14 @@ func ClaudeChunkData(c *gin.Context, resp dto.ClaudeResponse, data string) {
 	}
 }
 
+func ResponseChunkData(c *gin.Context, resp dto.ResponsesStreamResponse, data string) {
+	c.Render(-1, common.CustomEvent{Data: fmt.Sprintf("event: %s\n", resp.Type)})
+	c.Render(-1, common.CustomEvent{Data: fmt.Sprintf("data: %s\n", data)})
+	if flusher, ok := c.Writer.(http.Flusher); ok {
+		flusher.Flush()
+	}
+}
+
 func StringData(c *gin.Context, str string) error {
 	//str = strings.TrimPrefix(str, "data: ")
 	//str = strings.TrimSuffix(str, "\r")

relay/relay-responses.go

+package relay
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/helper"
+	"one-api/service"
+	"one-api/setting"
+	"one-api/setting/model_setting"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+)
+
+func getAndValidateResponsesRequest(c *gin.Context, relayInfo *relaycommon.RelayInfo) (*dto.OpenAIResponsesRequest, error) {
+	request := &dto.OpenAIResponsesRequest{}
+	err := common.UnmarshalBodyReusable(c, request)
+	if err != nil {
+		return nil, err
+	}
+	if request.Model == "" {
+		return nil, errors.New("model is required")
+	}
+	if len(request.Input) == 0 {
+		return nil, errors.New("input is required")
+	}
+	relayInfo.IsStream = request.Stream
+	return request, nil
+
+}
+
+func checkInputSensitive(textRequest *dto.OpenAIResponsesRequest, info *relaycommon.RelayInfo) ([]string, error) {
+
+	sensitiveWords, err := service.CheckSensitiveInput(textRequest.Input)
+	return sensitiveWords, err
+}
+
+func getInputTokens(req *dto.OpenAIResponsesRequest, info *relaycommon.RelayInfo) (int, error) {
+	inputTokens, err := service.CountTokenInput(req.Input, req.Model)
+	info.PromptTokens = inputTokens
+	return inputTokens, err
+}
+
+func ResponsesHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
+	relayInfo := relaycommon.GenRelayInfo(c)
+	req, err := getAndValidateResponsesRequest(c, relayInfo)
+	if err != nil {
+		common.LogError(c, fmt.Sprintf("getAndValidateResponsesRequest error: %s", err.Error()))
+		return service.OpenAIErrorWrapperLocal(err, "invalid_responses_request", http.StatusBadRequest)
+	}
+	if setting.ShouldCheckPromptSensitive() {
+		sensitiveWords, err := checkInputSensitive(req, relayInfo)
+		if err != nil {
+			common.LogWarn(c, fmt.Sprintf("user sensitive words detected: %s", strings.Join(sensitiveWords, ", ")))
+			return service.OpenAIErrorWrapperLocal(err, "check_request_sensitive_error", http.StatusBadRequest)
+		}
+	}
+
+	err = helper.ModelMappedHelper(c, relayInfo)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "model_mapped_error", http.StatusBadRequest)
+	}
+	req.Model = relayInfo.UpstreamModelName
+	if value, exists := c.Get("prompt_tokens"); exists {
+		promptTokens := value.(int)
+		relayInfo.SetPromptTokens(promptTokens)
+	} else {
+		promptTokens, err := getInputTokens(req, relayInfo)
+		if err != nil {
+			return service.OpenAIErrorWrapperLocal(err, "count_input_tokens_error", http.StatusBadRequest)
+		}
+		c.Set("prompt_tokens", promptTokens)
+	}
+
+	priceData, err := helper.ModelPriceHelper(c, relayInfo, relayInfo.PromptTokens, int(req.MaxOutputTokens))
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "model_price_error", http.StatusInternalServerError)
+	}
+	// pre consume quota
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, priceData.ShouldPreConsumedQuota, relayInfo)
+	if openaiErr != nil {
+		return openaiErr
+	}
+	defer func() {
+		if openaiErr != nil {
+			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
+		}
+	}()
+	adaptor := GetAdaptor(relayInfo.ApiType)
+	if adaptor == nil {
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
+	}
+	adaptor.Init(relayInfo)
+	var requestBody io.Reader
+	if model_setting.GetGlobalSettings().PassThroughRequestEnabled {
+		body, err := common.GetRequestBody(c)
+		if err != nil {
+			return service.OpenAIErrorWrapperLocal(err, "get_request_body_error", http.StatusInternalServerError)
+		}
+		requestBody = bytes.NewBuffer(body)
+	} else {
+		convertedRequest, err := adaptor.ConvertOpenAIResponsesRequest(c, relayInfo, *req)
+		if err != nil {
+			return service.OpenAIErrorWrapperLocal(err, "convert_request_error", http.StatusBadRequest)
+		}
+		jsonData, err := json.Marshal(convertedRequest)
+		if err != nil {
+			return service.OpenAIErrorWrapperLocal(err, "marshal_request_error", http.StatusInternalServerError)
+		}
+		// apply param override
+		if len(relayInfo.ParamOverride) > 0 {
+			reqMap := make(map[string]interface{})
+			err = json.Unmarshal(jsonData, &reqMap)
+			if err != nil {
+				return service.OpenAIErrorWrapperLocal(err, "param_override_unmarshal_failed", http.StatusInternalServerError)
+			}
+			for key, value := range relayInfo.ParamOverride {
+				reqMap[key] = value
+			}
+			jsonData, err = json.Marshal(reqMap)
+			if err != nil {
+				return service.OpenAIErrorWrapperLocal(err, "param_override_marshal_failed", http.StatusInternalServerError)
+			}
+		}
+
+		if common.DebugEnabled {
+			println("requestBody: ", string(jsonData))
+		}
+		requestBody = bytes.NewBuffer(jsonData)
+	}
+
+	var httpResp *http.Response
+	resp, err := adaptor.DoRequest(c, relayInfo, requestBody)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
+	}
+
+	statusCodeMappingStr := c.GetString("status_code_mapping")
+
+	if resp != nil {
+		httpResp = resp.(*http.Response)
+
+		if httpResp.StatusCode != http.StatusOK {
+			openaiErr = service.RelayErrorHandler(httpResp, false)
+			// reset status code 重置状态码
+			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+			return openaiErr
+		}
+	}
+
+	usage, openaiErr := adaptor.DoResponse(c, httpResp, relayInfo)
+	if openaiErr != nil {
+		// reset status code 重置状态码
+		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+		return openaiErr
+	}
+
+	if strings.HasPrefix(relayInfo.OriginModelName, "gpt-4o-audio") {
+		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, priceData, "")
+	} else {
+		postConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, priceData, "")
+	}
+	return nil
+}

router/relay-router.go

 package router
 
 import (
-	"github.com/gin-gonic/gin"
 	"one-api/controller"
 	"one-api/middleware"
 	"one-api/relay"
+
+	"github.com/gin-gonic/gin"
 )
 
 func SetRelayRouter(router *gin.Engine) {
@@ -47,6 +48,7 @@ func SetRelayRouter(router *gin.Engine) {
 		httpRouter.POST("/audio/transcriptions", controller.Relay)
 		httpRouter.POST("/audio/translations", controller.Relay)
 		httpRouter.POST("/audio/speech", controller.Relay)
+		httpRouter.POST("/responses", controller.Relay)
 		httpRouter.GET("/files", controller.RelayNotImplemented)
 		httpRouter.POST("/files", controller.RelayNotImplemented)
 		httpRouter.DELETE("/files/:id", controller.RelayNotImplemented)