Add more LLMs

Add "o3-2025-04-16" with cutoff knowledge
add "gemini-2.5-pro-preview-05-06"
add "gemini-2.5-flash-preview-04-17"

README.md

@@ -22,12 +22,12 @@ English / [简体中文](./README_CN.md)
 [![MacOS][MacOS-image]][download-url]
 [![Linux][Linux-image]][download-url]
 
-[NextChatAI](https://nextchat.club?utm_source=readme) / [iOS APP](https://apps.apple.com/us/app/nextchat-ai/id6743085599) / [Web App Demo](https://app.nextchat.club) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Enterprise Edition](#enterprise-edition) 
+[NextChatAI](https://nextchat.club?utm_source=readme) / [iOS APP](https://apps.apple.com/us/app/nextchat-ai/id6743085599) / [Web App Demo](https://app.nextchat.dev) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Enterprise Edition](#enterprise-edition) 
 
 
 [saas-url]: https://nextchat.club?utm_source=readme
 [saas-image]: https://img.shields.io/badge/NextChat-Saas-green?logo=microsoftedge
-[web-url]: https://app.nextchat.club/
+[web-url]: https://app.nextchat.dev/
 [download-url]: https://github.com/Yidadaa/ChatGPT-Next-Web/releases
 [Web-image]: https://img.shields.io/badge/Web-PWA-orange?logo=microsoftedge
 [Windows-image]: https://img.shields.io/badge/-Windows-blue?logo=windows

app/client/platforms/openai.ts

@@ -56,7 +56,7 @@ export interface OpenAIListModelResponse {
 
 export interface RequestPayload {
   messages: {
-    role: "developer" | "system" | "user" | "assistant";
+    role: "system" | "user" | "assistant";
     content: string | MultimodalContent[];
   }[];
   stream?: boolean;
@@ -238,16 +238,8 @@ export class ChatGPTApi implements LLMApi {
         // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore.
       };
 
+      // O1 使用 max_completion_tokens 控制token数 (https://platform.openai.com/docs/guides/reasoning#controlling-costs)
       if (isO1OrO3) {
-        // by default the o1/o3 models will not attempt to produce output that includes markdown formatting
-        // manually add "Formatting re-enabled" developer message to encourage markdown inclusion in model responses
-        // (https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/reasoning?tabs=python-secure#markdown-output)
-        requestPayload["messages"].unshift({
-          role: "developer",
-          content: "Formatting re-enabled",
-        });
-
-        // o1/o3 uses max_completion_tokens to control the number of tokens (https://platform.openai.com/docs/guides/reasoning#controlling-costs)
         requestPayload["max_completion_tokens"] = modelConfig.max_tokens;
       }
 

app/constant.ts

@@ -441,6 +441,7 @@ export const KnowledgeCutOffDate: Record<string, string> = {
   o1: "2023-10",
   "o3-mini-2025-01-31": "2023-10",
   "o3-mini": "2023-10",
+  "o3-2025-04-16": "2024-01-06", //https://platform.openai.com/docs/models/o3
   // After improvements,
   // it's now easier to add "KnowledgeCutOffDate" instead of stupid hardcoding it, as was done previously.
   "gemini-pro": "2023-12",
@@ -519,19 +520,25 @@ const openaiModels = [
   "o1-preview",
   "o3-mini",
   "o3",
+  "o3-2025-04-16",
   "o4-mini",
 ];
 
 const googleModels = [
+  "gemini-1.0-pro", // Deprecated on 2/15/2025
   "gemini-1.5-pro-latest",
   "gemini-1.5-pro",
   "gemini-1.5-pro-002",
+  "gemini-1.5-pro-exp-0827",
   "gemini-1.5-flash-latest",
   "gemini-1.5-flash-8b-latest",
   "gemini-1.5-flash",
   "gemini-1.5-flash-8b",
   "gemini-1.5-flash-002",
+  "gemini-1.5-flash-exp-0827",
   "learnlm-1.5-pro-experimental",
+  "gemini-exp-1114",
+  "gemini-exp-1121",
   "gemini-exp-1206",
   "gemini-2.0-flash",
   "gemini-2.0-flash-exp",
@@ -541,7 +548,9 @@ const googleModels = [
   "gemini-2.0-flash-thinking-exp-01-21",
   "gemini-2.0-pro-exp",
   "gemini-2.0-pro-exp-02-05",
-  "gemini-2.5-pro-preview-06-05",
+  "gemini-2.5-pro-exp-03-25",
+  "gemini-2.5-pro-preview-05-06",
+  "gemini-2.5-flash-preview-04-17"
 ];
 
 const anthropicModels = [
@@ -628,18 +637,6 @@ const xAIModes = [
   "grok-2-vision-1212",
   "grok-2-vision",
   "grok-2-vision-latest",
-  "grok-3-mini-fast-beta",
-  "grok-3-mini-fast",
-  "grok-3-mini-fast-latest",
-  "grok-3-mini-beta",
-  "grok-3-mini",
-  "grok-3-mini-latest",
-  "grok-3-fast-beta",
-  "grok-3-fast",
-  "grok-3-fast-latest",
-  "grok-3-beta",
-  "grok-3",
-  "grok-3-latest",
 ];
 
 const chatglmModels = [

package.json

@@ -83,7 +83,7 @@
     "jest": "^29.7.0",
     "jest-environment-jsdom": "^29.7.0",
     "lint-staged": "^13.2.2",
-    "prettier": "^3.6.2",
+    "prettier": "^3.0.2",
     "ts-node": "^10.9.2",
     "tsx": "^4.16.0",
     "typescript": "5.2.2",

yarn.lock

@@ -7076,10 +7076,10 @@ prettier-linter-helpers@^1.0.0:
   dependencies:
     fast-diff "^1.1.2"
 
-prettier@^3.6.2:
-  version "3.6.2"
-  resolved "https://registry.yarnpkg.com/prettier/-/prettier-3.6.2.tgz#ccda02a1003ebbb2bfda6f83a074978f608b9393"
-  integrity sha512-I7AIg5boAr5R0FFtJ6rCfD+LFsWHp81dolrFD8S79U9tb8Az2nGrJncnMSnys+bpQJfRUzqs9hnA81OAA3hCuQ==
+prettier@^3.0.2:
+  version "3.0.2"
+  resolved "https://registry.yarnpkg.com/prettier/-/prettier-3.0.2.tgz#78fcecd6d870551aa5547437cdae39d4701dca5b"
+  integrity sha512-o2YR9qtniXvwEZlOKbveKfDQVyqxbEIWn48Z8m3ZJjBjcCmUy3xZGIv+7AkaeuaTr6yPXJjwv07ZWlsWbEy1rQ==
 
 pretty-format@^27.0.2:
   version "27.5.1"