diff --git a/go.mod b/go.mod
index 842cb74f..91e344da 100644
--- a/go.mod
+++ b/go.mod
@@ -10,6 +10,7 @@ require (
 	github.com/skratchdot/open-golang v0.0.0-20200116055534-eef842397966
 	github.com/tidwall/gjson v1.18.0
 	github.com/tidwall/sjson v1.2.5
+	golang.org/x/crypto v0.36.0
 	golang.org/x/net v0.37.1-0.20250305215238-2914f4677317
 	golang.org/x/oauth2 v0.30.0
 	gopkg.in/yaml.v3 v3.0.1
@@ -39,7 +40,6 @@ require (
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.12 // indirect
 	golang.org/x/arch v0.8.0 // indirect
-	golang.org/x/crypto v0.36.0 // indirect
 	golang.org/x/sys v0.31.0 // indirect
 	golang.org/x/text v0.23.0 // indirect
 	google.golang.org/protobuf v1.34.1 // indirect
diff --git a/internal/api/handlers/openai/openai_responses_handlers.go b/internal/api/handlers/openai/openai_responses_handlers.go
new file mode 100644
index 00000000..bc92e4da
--- /dev/null
+++ b/internal/api/handlers/openai/openai_responses_handlers.go
@@ -0,0 +1,474 @@
+// Package openai provides HTTP handlers for OpenAIResponses API endpoints.
+// This package implements the OpenAIResponses-compatible API interface, including model listing
+// and chat completion functionality. It supports both streaming and non-streaming responses,
+// and manages a pool of clients to interact with backend services.
+// The handlers translate OpenAIResponses API requests to the appropriate backend format and
+// convert responses back to OpenAIResponses-compatible format.
+package openai
+
+import (
+	"context"
+	"fmt"
+	"net/http"
+	"time"
+
+	"github.com/gin-gonic/gin"
+	"github.com/luispater/CLIProxyAPI/internal/api/handlers"
+	. "github.com/luispater/CLIProxyAPI/internal/constant"
+	"github.com/luispater/CLIProxyAPI/internal/interfaces"
+	"github.com/luispater/CLIProxyAPI/internal/registry"
+	"github.com/luispater/CLIProxyAPI/internal/util"
+	log "github.com/sirupsen/logrus"
+	"github.com/tidwall/gjson"
+)
+
+// OpenAIResponsesAPIHandler contains the handlers for OpenAIResponses API endpoints.
+// It holds a pool of clients to interact with the backend service.
+type OpenAIResponsesAPIHandler struct {
+	*handlers.BaseAPIHandler
+}
+
+// NewOpenAIResponsesAPIHandler creates a new OpenAIResponses API handlers instance.
+// It takes an BaseAPIHandler instance as input and returns an OpenAIResponsesAPIHandler.
+//
+// Parameters:
+//   - apiHandlers: The base API handlers instance
+//
+// Returns:
+//   - *OpenAIResponsesAPIHandler: A new OpenAIResponses API handlers instance
+func NewOpenAIResponsesAPIHandler(apiHandlers *handlers.BaseAPIHandler) *OpenAIResponsesAPIHandler {
+	return &OpenAIResponsesAPIHandler{
+		BaseAPIHandler: apiHandlers,
+	}
+}
+
+// HandlerType returns the identifier for this handler implementation.
+func (h *OpenAIResponsesAPIHandler) HandlerType() string {
+	return OPENAI_RESPONSE
+}
+
+// Models returns the OpenAIResponses-compatible model metadata supported by this handler.
+func (h *OpenAIResponsesAPIHandler) Models() []map[string]any {
+	// Get dynamic models from the global registry
+	modelRegistry := registry.GetGlobalRegistry()
+	return modelRegistry.GetAvailableModels("openai")
+}
+
+// OpenAIResponsesModels handles the /v1/models endpoint.
+// It returns a list of available AI models with their capabilities
+// and specifications in OpenAIResponses-compatible format.
+func (h *OpenAIResponsesAPIHandler) OpenAIResponsesModels(c *gin.Context) {
+	c.JSON(http.StatusOK, gin.H{
+		"object": "list",
+		"data":   h.Models(),
+	})
+}
+
+// ChatCompletions handles the /v1/chat/completions endpoint.
+// It determines whether the request is for a streaming or non-streaming response
+// and calls the appropriate handler based on the model provider.
+//
+// Parameters:
+//   - c: The Gin context containing the HTTP request and response
+func (h *OpenAIResponsesAPIHandler) ChatCompletions(c *gin.Context) {
+	rawJSON, err := c.GetRawData()
+	// If data retrieval fails, return a 400 Bad Request error.
+	if err != nil {
+		c.JSON(http.StatusBadRequest, handlers.ErrorResponse{
+			Error: handlers.ErrorDetail{
+				Message: fmt.Sprintf("Invalid request: %v", err),
+				Type:    "invalid_request_error",
+			},
+		})
+		return
+	}
+
+	// Check if the client requested a streaming response.
+	streamResult := gjson.GetBytes(rawJSON, "stream")
+	if streamResult.Type == gjson.True {
+		h.handleStreamingResponse(c, rawJSON)
+	} else {
+		h.handleNonStreamingResponse(c, rawJSON)
+	}
+
+}
+
+// Completions handles the /v1/completions endpoint.
+// It determines whether the request is for a streaming or non-streaming response
+// and calls the appropriate handler based on the model provider.
+// This endpoint follows the OpenAIResponses completions API specification.
+//
+// Parameters:
+//   - c: The Gin context containing the HTTP request and response
+func (h *OpenAIResponsesAPIHandler) Completions(c *gin.Context) {
+	rawJSON, err := c.GetRawData()
+	// If data retrieval fails, return a 400 Bad Request error.
+	if err != nil {
+		c.JSON(http.StatusBadRequest, handlers.ErrorResponse{
+			Error: handlers.ErrorDetail{
+				Message: fmt.Sprintf("Invalid request: %v", err),
+				Type:    "invalid_request_error",
+			},
+		})
+		return
+	}
+
+	// Check if the client requested a streaming response.
+	streamResult := gjson.GetBytes(rawJSON, "stream")
+	if streamResult.Type == gjson.True {
+		h.handleCompletionsStreamingResponse(c, rawJSON)
+	} else {
+		h.handleCompletionsNonStreamingResponse(c, rawJSON)
+	}
+
+}
+
+// handleNonStreamingResponse handles non-streaming chat completion responses
+// for Gemini models. It selects a client from the pool, sends the request, and
+// aggregates the response before sending it back to the client in OpenAIResponses format.
+//
+// Parameters:
+//   - c: The Gin context containing the HTTP request and response
+//   - rawJSON: The raw JSON bytes of the OpenAIResponses-compatible request
+func (h *OpenAIResponsesAPIHandler) handleNonStreamingResponse(c *gin.Context, rawJSON []byte) {
+	c.Header("Content-Type", "application/json")
+
+	modelName := gjson.GetBytes(rawJSON, "model").String()
+	cliCtx, cliCancel := h.GetContextWithCancel(h, c, context.Background())
+
+	var cliClient interfaces.Client
+	defer func() {
+		if cliClient != nil {
+			if mutex := cliClient.GetRequestMutex(); mutex != nil {
+				mutex.Unlock()
+			}
+		}
+	}()
+
+	retryCount := 0
+	for retryCount <= h.Cfg.RequestRetry {
+		var errorResponse *interfaces.ErrorMessage
+		cliClient, errorResponse = h.GetClient(modelName)
+		if errorResponse != nil {
+			c.Status(errorResponse.StatusCode)
+			_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+			cliCancel()
+			return
+		}
+
+		resp, err := cliClient.SendRawMessage(cliCtx, modelName, rawJSON, "")
+		if err != nil {
+			switch err.StatusCode {
+			case 429:
+				if h.Cfg.QuotaExceeded.SwitchProject {
+					log.Debugf("quota exceeded, switch client")
+					continue // Restart the client selection process
+				}
+			case 403, 408, 500, 502, 503, 504:
+				log.Debugf("http status code %d, switch client", err.StatusCode)
+				retryCount++
+				continue
+			case 401:
+				log.Debugf("unauthorized request, try to refresh token, %s", util.HideAPIKey(cliClient.GetEmail()))
+				errRefreshTokens := cliClient.RefreshTokens(cliCtx)
+				if errRefreshTokens != nil {
+					log.Debugf("refresh token failed, switch client, %s", util.HideAPIKey(cliClient.GetEmail()))
+				}
+				retryCount++
+				continue
+			default:
+				// Forward other errors directly to the client
+				c.Status(err.StatusCode)
+				_, _ = c.Writer.Write([]byte(err.Error.Error()))
+				cliCancel(err.Error)
+			}
+			break
+		} else {
+			_, _ = c.Writer.Write(resp)
+			cliCancel(resp)
+			break
+		}
+	}
+}
+
+// handleStreamingResponse handles streaming responses for Gemini models.
+// It establishes a streaming connection with the backend service and forwards
+// the response chunks to the client in real-time using Server-Sent Events.
+//
+// Parameters:
+//   - c: The Gin context containing the HTTP request and response
+//   - rawJSON: The raw JSON bytes of the OpenAIResponses-compatible request
+func (h *OpenAIResponsesAPIHandler) handleStreamingResponse(c *gin.Context, rawJSON []byte) {
+	c.Header("Content-Type", "text/event-stream")
+	c.Header("Cache-Control", "no-cache")
+	c.Header("Connection", "keep-alive")
+	c.Header("Access-Control-Allow-Origin", "*")
+
+	// Get the http.Flusher interface to manually flush the response.
+	flusher, ok := c.Writer.(http.Flusher)
+	if !ok {
+		c.JSON(http.StatusInternalServerError, handlers.ErrorResponse{
+			Error: handlers.ErrorDetail{
+				Message: "Streaming not supported",
+				Type:    "server_error",
+			},
+		})
+		return
+	}
+
+	modelName := gjson.GetBytes(rawJSON, "model").String()
+	cliCtx, cliCancel := h.GetContextWithCancel(h, c, context.Background())
+
+	var cliClient interfaces.Client
+	defer func() {
+		// Ensure the client's mutex is unlocked on function exit.
+		if cliClient != nil {
+			if mutex := cliClient.GetRequestMutex(); mutex != nil {
+				mutex.Unlock()
+			}
+		}
+	}()
+
+	retryCount := 0
+outLoop:
+	for retryCount <= h.Cfg.RequestRetry {
+		var errorResponse *interfaces.ErrorMessage
+		cliClient, errorResponse = h.GetClient(modelName)
+		if errorResponse != nil {
+			c.Status(errorResponse.StatusCode)
+			_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+			flusher.Flush()
+			cliCancel()
+			return
+		}
+
+		// Send the message and receive response chunks and errors via channels.
+		respChan, errChan := cliClient.SendRawMessageStream(cliCtx, modelName, rawJSON, "")
+
+		for {
+			select {
+			// Handle client disconnection.
+			case <-c.Request.Context().Done():
+				if c.Request.Context().Err().Error() == "context canceled" {
+					log.Debugf("openai client disconnected: %v", c.Request.Context().Err())
+					cliCancel() // Cancel the backend request.
+					return
+				}
+			// Process incoming response chunks.
+			case chunk, okStream := <-respChan:
+				if !okStream {
+					// Stream is closed, send the final [DONE] message.
+					_, _ = fmt.Fprintf(c.Writer, "data: [DONE]\n\n")
+					flusher.Flush()
+					cliCancel()
+					return
+				}
+
+				_, _ = fmt.Fprintf(c.Writer, "data: %s\n\n", string(chunk))
+				flusher.Flush()
+			// Handle errors from the backend.
+			case err, okError := <-errChan:
+				if okError {
+					switch err.StatusCode {
+					case 429:
+						if h.Cfg.QuotaExceeded.SwitchProject {
+							log.Debugf("quota exceeded, switch client")
+							continue outLoop // Restart the client selection process
+						}
+					case 403, 408, 500, 502, 503, 504:
+						log.Debugf("http status code %d, switch client", err.StatusCode)
+						retryCount++
+						continue outLoop
+					default:
+						// Forward other errors directly to the client
+						c.Status(err.StatusCode)
+						_, _ = fmt.Fprint(c.Writer, err.Error.Error())
+						flusher.Flush()
+						cliCancel(err.Error)
+					}
+					return
+				}
+			// Send a keep-alive signal to the client.
+			case <-time.After(500 * time.Millisecond):
+			}
+		}
+	}
+}
+
+// handleCompletionsNonStreamingResponse handles non-streaming completions responses.
+// It converts completions request to chat completions format, sends to backend,
+// then converts the response back to completions format before sending to client.
+//
+// Parameters:
+//   - c: The Gin context containing the HTTP request and response
+//   - rawJSON: The raw JSON bytes of the OpenAIResponses-compatible completions request
+func (h *OpenAIResponsesAPIHandler) handleCompletionsNonStreamingResponse(c *gin.Context, rawJSON []byte) {
+	c.Header("Content-Type", "application/json")
+
+	// Convert completions request to chat completions format
+	chatCompletionsJSON := convertCompletionsRequestToChatCompletions(rawJSON)
+
+	modelName := gjson.GetBytes(chatCompletionsJSON, "model").String()
+	cliCtx, cliCancel := h.GetContextWithCancel(h, c, context.Background())
+
+	var cliClient interfaces.Client
+	defer func() {
+		if cliClient != nil {
+			if mutex := cliClient.GetRequestMutex(); mutex != nil {
+				mutex.Unlock()
+			}
+		}
+	}()
+
+	retryCount := 0
+	for retryCount <= h.Cfg.RequestRetry {
+		var errorResponse *interfaces.ErrorMessage
+		cliClient, errorResponse = h.GetClient(modelName)
+		if errorResponse != nil {
+			c.Status(errorResponse.StatusCode)
+			_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+			cliCancel()
+			return
+		}
+
+		// Send the converted chat completions request
+		resp, err := cliClient.SendRawMessage(cliCtx, modelName, chatCompletionsJSON, "")
+		if err != nil {
+			switch err.StatusCode {
+			case 429:
+				if h.Cfg.QuotaExceeded.SwitchProject {
+					log.Debugf("quota exceeded, switch client")
+					continue // Restart the client selection process
+				}
+			case 403, 408, 500, 502, 503, 504:
+				log.Debugf("http status code %d, switch client", err.StatusCode)
+				retryCount++
+				continue
+			default:
+				// Forward other errors directly to the client
+				c.Status(err.StatusCode)
+				_, _ = c.Writer.Write([]byte(err.Error.Error()))
+				cliCancel(err.Error)
+			}
+			break
+		} else {
+			// Convert chat completions response back to completions format
+			completionsResp := convertChatCompletionsResponseToCompletions(resp)
+			_, _ = c.Writer.Write(completionsResp)
+			cliCancel(completionsResp)
+			break
+		}
+	}
+}
+
+// handleCompletionsStreamingResponse handles streaming completions responses.
+// It converts completions request to chat completions format, streams from backend,
+// then converts each response chunk back to completions format before sending to client.
+//
+// Parameters:
+//   - c: The Gin context containing the HTTP request and response
+//   - rawJSON: The raw JSON bytes of the OpenAIResponses-compatible completions request
+func (h *OpenAIResponsesAPIHandler) handleCompletionsStreamingResponse(c *gin.Context, rawJSON []byte) {
+	c.Header("Content-Type", "text/event-stream")
+	c.Header("Cache-Control", "no-cache")
+	c.Header("Connection", "keep-alive")
+	c.Header("Access-Control-Allow-Origin", "*")
+
+	// Get the http.Flusher interface to manually flush the response.
+	flusher, ok := c.Writer.(http.Flusher)
+	if !ok {
+		c.JSON(http.StatusInternalServerError, handlers.ErrorResponse{
+			Error: handlers.ErrorDetail{
+				Message: "Streaming not supported",
+				Type:    "server_error",
+			},
+		})
+		return
+	}
+
+	// Convert completions request to chat completions format
+	chatCompletionsJSON := convertCompletionsRequestToChatCompletions(rawJSON)
+
+	modelName := gjson.GetBytes(chatCompletionsJSON, "model").String()
+	cliCtx, cliCancel := h.GetContextWithCancel(h, c, context.Background())
+
+	var cliClient interfaces.Client
+	defer func() {
+		// Ensure the client's mutex is unlocked on function exit.
+		if cliClient != nil {
+			if mutex := cliClient.GetRequestMutex(); mutex != nil {
+				mutex.Unlock()
+			}
+		}
+	}()
+
+	retryCount := 0
+outLoop:
+	for retryCount <= h.Cfg.RequestRetry {
+		var errorResponse *interfaces.ErrorMessage
+		cliClient, errorResponse = h.GetClient(modelName)
+		if errorResponse != nil {
+			c.Status(errorResponse.StatusCode)
+			_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+			flusher.Flush()
+			cliCancel()
+			return
+		}
+
+		// Send the converted chat completions request and receive response chunks
+		respChan, errChan := cliClient.SendRawMessageStream(cliCtx, modelName, chatCompletionsJSON, "")
+
+		for {
+			select {
+			// Handle client disconnection.
+			case <-c.Request.Context().Done():
+				if c.Request.Context().Err().Error() == "context canceled" {
+					log.Debugf("client disconnected: %v", c.Request.Context().Err())
+					cliCancel() // Cancel the backend request.
+					return
+				}
+			// Process incoming response chunks.
+			case chunk, okStream := <-respChan:
+				if !okStream {
+					// Stream is closed, send the final [DONE] message.
+					_, _ = fmt.Fprintf(c.Writer, "data: [DONE]\n\n")
+					flusher.Flush()
+					cliCancel()
+					return
+				}
+
+				// Convert chat completions chunk to completions chunk format
+				completionsChunk := convertChatCompletionsStreamChunkToCompletions(chunk)
+				// Skip this chunk if it has no meaningful content (empty text)
+				if completionsChunk != nil {
+					_, _ = fmt.Fprintf(c.Writer, "data: %s\n\n", string(completionsChunk))
+					flusher.Flush()
+				}
+			// Handle errors from the backend.
+			case err, okError := <-errChan:
+				if okError {
+					switch err.StatusCode {
+					case 429:
+						if h.Cfg.QuotaExceeded.SwitchProject {
+							log.Debugf("quota exceeded, switch client")
+							continue outLoop // Restart the client selection process
+						}
+					case 403, 408, 500, 502, 503, 504:
+						log.Debugf("http status code %d, switch client", err.StatusCode)
+						retryCount++
+						continue outLoop
+					default:
+						// Forward other errors directly to the client
+						c.Status(err.StatusCode)
+						_, _ = fmt.Fprint(c.Writer, err.Error.Error())
+						flusher.Flush()
+						cliCancel(err.Error)
+					}
+					return
+				}
+			// Send a keep-alive signal to the client.
+			case <-time.After(500 * time.Millisecond):
+			}
+		}
+	}
+}
diff --git a/internal/constant/constant.go b/internal/constant/constant.go
index 30e3644e..4e39d93f 100644
--- a/internal/constant/constant.go
+++ b/internal/constant/constant.go
@@ -1,10 +1,10 @@
 package constant
 
 const (
-	GEMINI               = "gemini"
-	GEMINICLI            = "gemini-cli"
-	CODEX                = "codex"
-	CLAUDE               = "claude"
-	OPENAI               = "openai"
-	OPENAI_COMPATIBILITY = "openai-compatibility"
+	GEMINI          = "gemini"
+	GEMINICLI       = "gemini-cli"
+	CODEX           = "codex"
+	CLAUDE          = "claude"
+	OPENAI          = "openai"
+	OPENAI_RESPONSE = "openai-response"
 )
diff --git a/internal/translator/claude/openai/claude_openai_request.go b/internal/translator/claude/openai/chat-completions/claude_openai_request.go
similarity index 99%
rename from internal/translator/claude/openai/claude_openai_request.go
rename to internal/translator/claude/openai/chat-completions/claude_openai_request.go
index b65334bf..dce6f248 100644
--- a/internal/translator/claude/openai/claude_openai_request.go
+++ b/internal/translator/claude/openai/chat-completions/claude_openai_request.go
@@ -3,7 +3,7 @@
 // extracting model information, system instructions, message contents, and tool declarations.
 // The package performs JSON data transformation to ensure compatibility
 // between OpenAI API format and Claude Code API's expected format.
-package openai
+package chat_completions
 
 import (
 	"crypto/rand"
diff --git a/internal/translator/claude/openai/claude_openai_response.go b/internal/translator/claude/openai/chat-completions/claude_openai_response.go
similarity index 99%
rename from internal/translator/claude/openai/claude_openai_response.go
rename to internal/translator/claude/openai/chat-completions/claude_openai_response.go
index 9b4fd8c9..f6b6b3da 100644
--- a/internal/translator/claude/openai/claude_openai_response.go
+++ b/internal/translator/claude/openai/chat-completions/claude_openai_response.go
@@ -3,7 +3,7 @@
 // JSON format, transforming streaming events and non-streaming responses into the format
 // expected by OpenAI API clients. It supports both streaming and non-streaming modes,
 // handling text content, tool calls, reasoning content, and usage metadata appropriately.
-package openai
+package chat_completions
 
 import (
 	"bufio"
diff --git a/internal/translator/claude/openai/init.go b/internal/translator/claude/openai/chat-completions/init.go
similarity index 94%
rename from internal/translator/claude/openai/init.go
rename to internal/translator/claude/openai/chat-completions/init.go
index b8ea73d3..e4c53a42 100644
--- a/internal/translator/claude/openai/init.go
+++ b/internal/translator/claude/openai/chat-completions/init.go
@@ -1,4 +1,4 @@
-package openai
+package chat_completions
 
 import (
 	. "github.com/luispater/CLIProxyAPI/internal/constant"
diff --git a/internal/translator/codex/openai/codex_openai_request.go b/internal/translator/codex/openai/chat-completions/codex_openai_request.go
similarity index 99%
rename from internal/translator/codex/openai/codex_openai_request.go
rename to internal/translator/codex/openai/chat-completions/codex_openai_request.go
index 842cb7e3..60f71b41 100644
--- a/internal/translator/codex/openai/codex_openai_request.go
+++ b/internal/translator/codex/openai/chat-completions/codex_openai_request.go
@@ -4,7 +4,7 @@
 // The package handles the conversion of OpenAI API requests into the format
 // expected by the OpenAI Responses API, including proper mapping of messages,
 // tools, and generation parameters.
-package openai
+package chat_completions
 
 import (
 	"github.com/luispater/CLIProxyAPI/internal/misc"
diff --git a/internal/translator/codex/openai/codex_openai_response.go b/internal/translator/codex/openai/chat-completions/codex_openai_response.go
similarity index 99%
rename from internal/translator/codex/openai/codex_openai_response.go
rename to internal/translator/codex/openai/chat-completions/codex_openai_response.go
index 51ab5d09..1ba78601 100644
--- a/internal/translator/codex/openai/codex_openai_response.go
+++ b/internal/translator/codex/openai/chat-completions/codex_openai_response.go
@@ -3,7 +3,7 @@
 // JSON format, transforming streaming events and non-streaming responses into the format
 // expected by OpenAI API clients. It supports both streaming and non-streaming modes,
 // handling text content, tool calls, reasoning content, and usage metadata appropriately.
-package openai
+package chat_completions
 
 import (
 	"bufio"
diff --git a/internal/translator/codex/openai/init.go b/internal/translator/codex/openai/chat-completions/init.go
similarity index 94%
rename from internal/translator/codex/openai/init.go
rename to internal/translator/codex/openai/chat-completions/init.go
index 7c734cd9..062b413f 100644
--- a/internal/translator/codex/openai/init.go
+++ b/internal/translator/codex/openai/chat-completions/init.go
@@ -1,4 +1,4 @@
-package openai
+package chat_completions
 
 import (
 	. "github.com/luispater/CLIProxyAPI/internal/constant"
diff --git a/internal/translator/gemini-cli/openai/cli_openai_request.go b/internal/translator/gemini-cli/openai/chat-completions/cli_openai_request.go
similarity index 99%
rename from internal/translator/gemini-cli/openai/cli_openai_request.go
rename to internal/translator/gemini-cli/openai/chat-completions/cli_openai_request.go
index b21a0f8f..9dc080ed 100644
--- a/internal/translator/gemini-cli/openai/cli_openai_request.go
+++ b/internal/translator/gemini-cli/openai/chat-completions/cli_openai_request.go
@@ -1,6 +1,6 @@
 // Package openai provides request translation functionality for OpenAI to Gemini CLI API compatibility.
 // It converts OpenAI Chat Completions requests into Gemini CLI compatible JSON using gjson/sjson only.
-package openai
+package chat_completions
 
 import (
 	"fmt"
diff --git a/internal/translator/gemini-cli/openai/cli_openai_response.go b/internal/translator/gemini-cli/openai/chat-completions/cli_openai_response.go
similarity index 99%
rename from internal/translator/gemini-cli/openai/cli_openai_response.go
rename to internal/translator/gemini-cli/openai/chat-completions/cli_openai_response.go
index 0bbbed5a..06d68651 100644
--- a/internal/translator/gemini-cli/openai/cli_openai_response.go
+++ b/internal/translator/gemini-cli/openai/chat-completions/cli_openai_response.go
@@ -3,7 +3,7 @@
 // JSON format, transforming streaming events and non-streaming responses into the format
 // expected by OpenAI API clients. It supports both streaming and non-streaming modes,
 // handling text content, tool calls, reasoning content, and usage metadata appropriately.
-package openai
+package chat_completions
 
 import (
 	"bytes"
@@ -11,7 +11,7 @@ import (
 	"fmt"
 	"time"
 
-	. "github.com/luispater/CLIProxyAPI/internal/translator/gemini/openai"
+	. "github.com/luispater/CLIProxyAPI/internal/translator/gemini/openai/chat-completions"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
diff --git a/internal/translator/gemini-cli/openai/init.go b/internal/translator/gemini-cli/openai/chat-completions/init.go
similarity index 94%
rename from internal/translator/gemini-cli/openai/init.go
rename to internal/translator/gemini-cli/openai/chat-completions/init.go
index 2203eb57..5ee21657 100644
--- a/internal/translator/gemini-cli/openai/init.go
+++ b/internal/translator/gemini-cli/openai/chat-completions/init.go
@@ -1,4 +1,4 @@
-package openai
+package chat_completions
 
 import (
 	. "github.com/luispater/CLIProxyAPI/internal/constant"
diff --git a/internal/translator/gemini/openai/gemini_openai_request.go b/internal/translator/gemini/openai/chat-completions/gemini_openai_request.go
similarity index 99%
rename from internal/translator/gemini/openai/gemini_openai_request.go
rename to internal/translator/gemini/openai/chat-completions/gemini_openai_request.go
index 71590fdd..5b207240 100644
--- a/internal/translator/gemini/openai/gemini_openai_request.go
+++ b/internal/translator/gemini/openai/chat-completions/gemini_openai_request.go
@@ -1,6 +1,6 @@
 // Package openai provides request translation functionality for OpenAI to Gemini API compatibility.
 // It converts OpenAI Chat Completions requests into Gemini compatible JSON using gjson/sjson only.
-package openai
+package chat_completions
 
 import (
 	"fmt"
diff --git a/internal/translator/gemini/openai/gemini_openai_response.go b/internal/translator/gemini/openai/chat-completions/gemini_openai_response.go
similarity index 99%
rename from internal/translator/gemini/openai/gemini_openai_response.go
rename to internal/translator/gemini/openai/chat-completions/gemini_openai_response.go
index 4fd11d0c..28782135 100644
--- a/internal/translator/gemini/openai/gemini_openai_response.go
+++ b/internal/translator/gemini/openai/chat-completions/gemini_openai_response.go
@@ -3,7 +3,7 @@
 // JSON format, transforming streaming events and non-streaming responses into the format
 // expected by OpenAI API clients. It supports both streaming and non-streaming modes,
 // handling text content, tool calls, reasoning content, and usage metadata appropriately.
-package openai
+package chat_completions
 
 import (
 	"bytes"
diff --git a/internal/translator/gemini/openai/init.go b/internal/translator/gemini/openai/chat-completions/init.go
similarity index 94%
rename from internal/translator/gemini/openai/init.go
rename to internal/translator/gemini/openai/chat-completions/init.go
index 376b485c..53a4c131 100644
--- a/internal/translator/gemini/openai/init.go
+++ b/internal/translator/gemini/openai/chat-completions/init.go
@@ -1,4 +1,4 @@
-package openai
+package chat_completions
 
 import (
 	. "github.com/luispater/CLIProxyAPI/internal/constant"
diff --git a/internal/translator/init.go b/internal/translator/init.go
index 7e3f2b60..f74e70a4 100644
--- a/internal/translator/init.go
+++ b/internal/translator/init.go
@@ -3,18 +3,18 @@ package translator
 import (
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/claude/gemini"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/claude/gemini-cli"
-	_ "github.com/luispater/CLIProxyAPI/internal/translator/claude/openai"
+	_ "github.com/luispater/CLIProxyAPI/internal/translator/claude/openai/chat-completions"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/codex/claude"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/codex/gemini"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/codex/gemini-cli"
-	_ "github.com/luispater/CLIProxyAPI/internal/translator/codex/openai"
+	_ "github.com/luispater/CLIProxyAPI/internal/translator/codex/openai/chat-completions"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/gemini-cli/claude"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/gemini-cli/gemini"
-	_ "github.com/luispater/CLIProxyAPI/internal/translator/gemini-cli/openai"
+	_ "github.com/luispater/CLIProxyAPI/internal/translator/gemini-cli/openai/chat-completions"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/gemini/claude"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/gemini/gemini"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/gemini/gemini-cli"
-	_ "github.com/luispater/CLIProxyAPI/internal/translator/gemini/openai"
+	_ "github.com/luispater/CLIProxyAPI/internal/translator/gemini/openai/chat-completions"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/openai/claude"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/openai/gemini"
 	_ "github.com/luispater/CLIProxyAPI/internal/translator/openai/gemini-cli"