add model catalogs

* fix(image generation): model recognize

* fix(grok): disable off option

.github/dependabot.yml

@@ -1,86 +1,17 @@
 version: 2
 updates:
-  - package-ecosystem: "npm"
-    directory: "/"
+  - package-ecosystem: 'github-actions'
+    directory: '/'
     schedule:
-      interval: "monthly"
-    open-pull-requests-limit: 7
-    target-branch: "main"
-    commit-message:
-      prefix: "chore"
-      include: "scope"
-    groups:
-      # 核心框架
-      core-framework:
-        patterns:
-          - "react"
-          - "react-dom"
-          - "electron"
-          - "typescript"
-          - "@types/react*"
-          - "@types/node"
-        update-types:
-          - "minor"
-          - "patch"
-
-      # Electron 生态和构建工具
-      electron-build:
-        patterns:
-          - "electron-*"
-          - "@electron*"
-          - "vite"
-          - "@vitejs/*"
-          - "dotenv-cli"
-          - "rollup-plugin-*"
-          - "@swc/*"
-        update-types:
-          - "minor"
-          - "patch"
-
-      # 测试工具
-      testing-tools:
-        patterns:
-          - "vitest"
-          - "@vitest/*"
-          - "playwright"
-          - "@playwright/*"
-          - "eslint*"
-          - "@eslint*"
-          - "prettier"
-          - "husky"
-          - "lint-staged"
-        update-types:
-          - "minor"
-          - "patch"
-
-      # CherryStudio 自定义包
-      cherrystudio-packages:
-        patterns:
-          - "@cherrystudio/*"
-        update-types:
-          - "minor"
-          - "patch"
-
-      # 兜底其他 dependencies
-      other-dependencies:
-        dependency-type: "production"
-
-      # 兜底其他 devDependencies
-      other-dev-dependencies:
-        dependency-type: "development"
-
-  - package-ecosystem: "github-actions"
-    directory: "/"
-    schedule:
-      interval: "weekly"
+      interval: 'monthly'
     open-pull-requests-limit: 3
     commit-message:
-      prefix: "ci"
-      include: "scope"
+      prefix: 'ci'
+      include: 'scope'
     groups:
       github-actions:
         patterns:
-          - "*"
+          - '*'
         update-types:
-          - "minor"
-          - "patch"
+          - 'minor'
+          - 'patch'

.github/workflows/dispatch-docs-update.yml

@@ -0,0 +1,27 @@
+name: Dispatch Docs Update on Release
+
+on:
+  release:
+    types: [released]
+
+permissions:
+  contents: write
+
+jobs:
+  dispatch-docs-update:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Get Release Tag from Event
+        id: get-event-tag
+        shell: bash
+        run: |
+          # 从当前 Release 事件中获取 tag_name
+          echo "tag=${{ github.event.release.tag_name }}" >> $GITHUB_OUTPUT
+
+      - name: Dispatch update-download-version workflow to cherry-studio-docs
+        uses: peter-evans/repository-dispatch@v3
+        with:
+          token: ${{ secrets.REPO_DISPATCH_TOKEN }}
+          repository: CherryHQ/cherry-studio-docs
+          event-type: update-download-version
+          client-payload: '{"version": "${{ steps.get-event-tag.outputs.tag }}"}'

.github/workflows/release.yml

@@ -79,6 +79,7 @@ jobs:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           RENDERER_VITE_AIHUBMIX_SECRET: ${{ vars.RENDERER_VITE_AIHUBMIX_SECRET }}
           NODE_OPTIONS: --max-old-space-size=8192
+          MAIN_VITE_MINERU_API_KEY: ${{ vars.MAIN_VITE_MINERU_API_KEY }}
 
       - name: Build Mac
         if: matrix.os == 'macos-latest'
@@ -95,6 +96,7 @@ jobs:
           RENDERER_VITE_AIHUBMIX_SECRET: ${{ vars.RENDERER_VITE_AIHUBMIX_SECRET }}
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           NODE_OPTIONS: --max-old-space-size=8192
+          MAIN_VITE_MINERU_API_KEY: ${{ vars.MAIN_VITE_MINERU_API_KEY }}
 
       - name: Build Windows
         if: matrix.os == 'windows-latest'
@@ -105,6 +107,7 @@ jobs:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           RENDERER_VITE_AIHUBMIX_SECRET: ${{ vars.RENDERER_VITE_AIHUBMIX_SECRET }}
           NODE_OPTIONS: --max-old-space-size=8192
+          MAIN_VITE_MINERU_API_KEY: ${{ vars.MAIN_VITE_MINERU_API_KEY }}
 
       - name: Release
         uses: ncipollo/release-action@v1
@@ -114,39 +117,4 @@ jobs:
           makeLatest: false
           tag: ${{ steps.get-tag.outputs.tag }}
           artifacts: 'dist/*.exe,dist/*.zip,dist/*.dmg,dist/*.AppImage,dist/*.snap,dist/*.deb,dist/*.rpm,dist/*.tar.gz,dist/latest*.yml,dist/rc*.yml,dist/*.blockmap'
-          token: ${{ secrets.GITHUB_TOKEN }}
-
-  dispatch-docs-update:
-    needs: release
-    if: success() && github.repository == 'CherryHQ/cherry-studio' # 确保所有构建成功且在主仓库中运行
-    runs-on: ubuntu-latest
-    steps:
-      - name: Get release tag
-        id: get-tag
-        shell: bash
-        run: |
-          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
-            echo "tag=${{ github.event.inputs.tag }}" >> $GITHUB_OUTPUT
-          else
-            echo "tag=${GITHUB_REF#refs/tags/}" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Check if tag is pre-release
-        id: check-tag
-        shell: bash
-        run: |
-          TAG="${{ steps.get-tag.outputs.tag }}"
-          if [[ "$TAG" == *"rc"* || "$TAG" == *"pre-release"* ]]; then
-            echo "is_pre_release=true" >> $GITHUB_OUTPUT
-          else
-            echo "is_pre_release=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Dispatch update-download-version workflow to cherry-studio-docs
-        if: steps.check-tag.outputs.is_pre_release == 'false'
-        uses: peter-evans/repository-dispatch@v3
-        with:
-          token: ${{ secrets.REPO_DISPATCH_TOKEN }}
-          repository: CherryHQ/cherry-studio-docs
-          event-type: update-download-version
-          client-payload: '{"version": "${{ steps.get-tag.outputs.tag }}"}'
+          token: ${{ secrets.GITHUB_TOKEN }}

.vscode/settings.json

@@ -1,7 +1,8 @@
 {
   "editor.formatOnSave": true,
   "editor.codeActionsOnSave": {
-    "source.fixAll.eslint": "explicit"
+    "source.fixAll.eslint": "explicit",
+    "source.organizeImports": "never"
   },
   "search.exclude": {
     "**/dist/**": true,

.yarn/patches/antd-npm-5.24.7-356a553ae5.patch

@@ -0,0 +1,69 @@
+diff --git a/es/dropdown/dropdown.js b/es/dropdown/dropdown.js
+index 986877a762b9ad0aca596a8552732cd12d2eaabb..1f18aa2ea745e68950e4cee16d4d655f5c835fd5 100644
+--- a/es/dropdown/dropdown.js
++++ b/es/dropdown/dropdown.js
+@@ -2,7 +2,7 @@
+ 
+ import * as React from 'react';
+ import LeftOutlined from "@ant-design/icons/es/icons/LeftOutlined";
+-import RightOutlined from "@ant-design/icons/es/icons/RightOutlined";
++import { ChevronRight } from 'lucide-react';
+ import classNames from 'classnames';
+ import RcDropdown from 'rc-dropdown';
+ import useEvent from "rc-util/es/hooks/useEvent";
+@@ -158,8 +158,10 @@ const Dropdown = props => {
+         className: `${prefixCls}-menu-submenu-arrow`
+       }, direction === 'rtl' ? (/*#__PURE__*/React.createElement(LeftOutlined, {
+         className: `${prefixCls}-menu-submenu-arrow-icon`
+-      })) : (/*#__PURE__*/React.createElement(RightOutlined, {
+-        className: `${prefixCls}-menu-submenu-arrow-icon`
++      })) : (/*#__PURE__*/React.createElement(ChevronRight, {
++        size: 16,
++        strokeWidth: 1.8,
++        className: `${prefixCls}-menu-submenu-arrow-icon lucide-custom`
+       }))),
+       mode: "vertical",
+       selectable: false,
+diff --git a/es/dropdown/style/index.js b/es/dropdown/style/index.js
+index 768c01783002c6901c85a73061ff6b3e776a60ce..39b1b95a56cdc9fb586a193c3adad5141f5cf213 100644
+--- a/es/dropdown/style/index.js
++++ b/es/dropdown/style/index.js
+@@ -240,7 +240,8 @@ const genBaseStyle = token => {
+               marginInlineEnd: '0 !important',
+               color: token.colorTextDescription,
+               fontSize: fontSizeIcon,
+-              fontStyle: 'normal'
++              fontStyle: 'normal',
++              marginTop: 3,
+             }
+           }
+         }),
+diff --git a/es/select/useIcons.js b/es/select/useIcons.js
+index 959115be936ef8901548af2658c5dcfdc5852723..c812edd52123eb0faf4638b1154fcfa1b05b513b 100644
+--- a/es/select/useIcons.js
++++ b/es/select/useIcons.js
+@@ -4,10 +4,10 @@ import * as React from 'react';
+ import CheckOutlined from "@ant-design/icons/es/icons/CheckOutlined";
+ import CloseCircleFilled from "@ant-design/icons/es/icons/CloseCircleFilled";
+ import CloseOutlined from "@ant-design/icons/es/icons/CloseOutlined";
+-import DownOutlined from "@ant-design/icons/es/icons/DownOutlined";
+ import LoadingOutlined from "@ant-design/icons/es/icons/LoadingOutlined";
+ import SearchOutlined from "@ant-design/icons/es/icons/SearchOutlined";
+ import { devUseWarning } from '../_util/warning';
++import { ChevronDown } from 'lucide-react';
+ export default function useIcons(_ref) {
+   let {
+     suffixIcon,
+@@ -56,8 +56,10 @@ export default function useIcons(_ref) {
+           className: iconCls
+         }));
+       }
+-      return getSuffixIconNode(/*#__PURE__*/React.createElement(DownOutlined, {
+-        className: iconCls
++      return getSuffixIconNode(/*#__PURE__*/React.createElement(ChevronDown, {
++        size: 16,
++        strokeWidth: 1.8,
++        className: `${iconCls} lucide-custom`
+       }));
+     };
+   }

CONTRIBUTING.md

@@ -1,4 +1,4 @@
-[中文](./docs/CONTRIBUTING.zh.md) | [English](./CONTRIBUTING.md)
+[中文](docs/CONTRIBUTING.zh.md) | [English](CONTRIBUTING.md)
 
 # Cherry Studio Contributor Guide
 
@@ -58,6 +58,10 @@ git commit --signoff -m "Your commit message"
 
 Maintainers are here to help you implement your use case within a reasonable timeframe. They will do their best to review your code and provide constructive feedback promptly. However, if you get stuck during the review process or feel your Pull Request is not receiving the attention it deserves, please contact us via comments in the Issue or through the [Community](README.md#-community).
 
+### Participating in the Test Plan
+
+The Test Plan aims to provide users with a more stable application experience and faster iteration speed. For details, please refer to the [Test Plan](docs/testplan-en.md).
+
 ### Other Suggestions
 
 - **Contact Developers**: Before submitting a PR, you can contact the developers first to discuss or get help.

README.md

@@ -1,34 +1,54 @@
+<div align="right" >
+  <details>
+    <summary >🌐 Language</summary>
+    <div>
+      <div align="right">
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=en">English</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=zh-CN">简体中文</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=zh-TW">繁體中文</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=ja">日本語</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=ko">한국어</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=hi">हिन्दी</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=th">ไทย</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=fr">Français</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=de">Deutsch</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=es">Español</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=it">Itapano</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=ru">Русский</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=pt">Português</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=nl">Nederlands</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=pl">Polski</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=ar">العربية</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=fa">فارسی</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=tr">Türkçe</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=vi">Tiếng Việt</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=id">Bahasa Indonesia</a></p>
+      </div>
+    </div>
+  </details>
+</div>
+
 <h1 align="center">
   <a href="https://github.com/CherryHQ/cherry-studio/releases">
     <img src="https://github.com/CherryHQ/cherry-studio/blob/main/build/icon.png?raw=true" width="150" height="150" alt="banner" /><br>
   </a>
 </h1>
-  <p align="center">English | <a href="./docs/README.zh.md">中文</a> | <a href="./docs/README.ja.md">日本語</a> | <a href="https://cherry-ai.com">Official Site</a> | <a href="https://docs.cherry-ai.com/cherry-studio-wen-dang/en-us">Documents</a> | <a href="./docs/dev.md">Development</a> | <a href="https://github.com/CherryHQ/cherry-studio/issues">Feedback</a><br></p>
 
-<!-- 题头徽章组合 -->
+<p align="center">English | <a href="./docs/README.zh.md">中文</a> | <a href="https://cherry-ai.com">Official Site</a> | <a href="https://docs.cherry-ai.com/cherry-studio-wen-dang/en-us">Documents</a> | <a href="./docs/dev.md">Development</a> | <a href="https://github.com/CherryHQ/cherry-studio/issues">Feedback</a><br></p>
 
 <div align="center">
-
+  
 [![][deepwiki-shield]][deepwiki-link]
 [![][twitter-shield]][twitter-link]
 [![][discord-shield]][discord-link]
 [![][telegram-shield]][telegram-link]
 
 </div>
-
-<!-- 项目统计徽章 -->
-
 <div align="center">
-
-[![][github-stars-shield]][github-stars-link]
-[![][github-forks-shield]][github-forks-link]
+  
 [![][github-release-shield]][github-release-link]
+[![][github-nightly-shield]][github-nightly-link]
 [![][github-contributors-shield]][github-contributors-link]
-
-</div>
-
-<div align="center">
-
 [![][license-shield]][license-link]
 [![][commercial-shield]][commercial-link]
 [![][sponsor-shield]][sponsor-link]
@@ -36,9 +56,9 @@
 </div>
 
 <div align="center">
- <a href="https://hellogithub.com/repository/1605492e1e2a4df3be07abfa4578dd37" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=1605492e1e2a4df3be07abfa4578dd37" alt="Featured｜HelloGitHub" style="width: 200px; height: 43px;" width="200" height="43" /></a>
- <a href="https://trendshift.io/repositories/11772" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11772" alt="kangfenmao%2Fcherry-studio | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
- <a href="https://www.producthunt.com/posts/cherry-studio?embed=true&utm_source=badge-featured&utm_medium=badge&utm_souce=badge-cherry&#0045;studio" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=496640&theme=light" alt="Cherry&#0032;Studio - AI&#0032;Chatbots&#0044;&#0032;AI&#0032;Desktop&#0032;Client | Product Hunt" style="width: 200px; height: 43px;" width="200" height="43" /></a>
+ <a href="https://hellogithub.com/repository/1605492e1e2a4df3be07abfa4578dd37" target="_blank" style="text-decoration: none"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=1605492e1e2a4df3be07abfa4578dd37" alt="Featured｜HelloGitHub"  width="220" height="55" /></a>
+ <a href="https://trendshift.io/repositories/11772" target="_blank" style="text-decoration: none"><img src="https://trendshift.io/api/badge/repositories/11772" alt="kangfenmao%2Fcherry-studio | Trendshift" width="220" height="55" /></a>
+ <a href="https://www.producthunt.com/posts/cherry-studio?embed=true&utm_source=badge-featured&utm_medium=badge&utm_souce=badge-cherry&#0045;studio" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=496640&theme=light" alt="Cherry&#0032;Studio - AI&#0032;Chatbots&#0044;&#0032;AI&#0032;Desktop&#0032;Client | Product Hunt" width="220" height="55" /></a>
 </div>
 
 # 🍒 Cherry Studio
@@ -163,10 +183,82 @@ Refer to the [Branching Strategy](docs/branching-strategy-en.md) for contributio
 3. **Submit Changes**: Commit and push your changes.
 4. **Open a Pull Request**: Describe your changes and reasons.
 
-For more detailed guidelines, please refer to our [Contributing Guide](./CONTRIBUTING.md).
+For more detailed guidelines, please refer to our [Contributing Guide](CONTRIBUTING.md).
 
 Thank you for your support and contributions!
 
+# 🔧 Developer Co-creation Program
+
+We are launching the Cherry Studio Developer Co-creation Program to foster a healthy and positive-feedback loop within the open-source ecosystem. We believe that great software is built collaboratively, and every merged pull request breathes new life into the project.
+
+We sincerely invite you to join our ranks of contributors and shape the future of Cherry Studio with us.
+
+## Contributor Rewards Program
+
+To give back to our core contributors and create a virtuous cycle, we have established the following long-term incentive plan.
+
+**The inaugural tracking period for this program will be Q3 2025 (July, August, September). Rewards for this cycle will be distributed on October 1st.**
+
+Within any tracking period (e.g., July 1st to September 30th for the first cycle), any developer who contributes more than **30 meaningful commits** to any of Cherry Studio's open-source projects on GitHub is eligible for the following benefits:
+
+- **Cursor Subscription Sponsorship**: Receive a **$70 USD** credit or reimbursement for your [Cursor](https://cursor.sh/) subscription, making AI your most efficient coding partner.
+- **Unlimited Model Access**: Get **unlimited** API calls for the **DeepSeek** and **Qwen** models.
+- **Cutting-Edge Tech Access**: Enjoy occasional perks, including API access to models like **Claude**, **Gemini**, and **OpenAI**, keeping you at the forefront of technology.
+
+## Growing Together & Future Plans
+
+A vibrant community is the driving force behind any sustainable open-source project. As Cherry Studio grows, so will our rewards program. We are committed to continuously aligning our benefits with the best-in-class tools and resources in the industry. This ensures our core contributors receive meaningful support, creating a positive cycle where developers, the community, and the project grow together.
+
+**Moving forward, the project will also embrace an increasingly open stance to give back to the entire open-source community.**
+
+## How to Get Started?
+
+We look forward to your first Pull Request!
+
+You can start by exploring our repositories, picking up a `good first issue`, or proposing your own enhancements. Every commit is a testament to the spirit of open source.
+
+Thank you for your interest and contributions.
+
+Let's build together.
+
+# 🏢 Enterprise Edition
+
+Building on the Community Edition, we are proud to introduce **Cherry Studio Enterprise Edition**—a privately deployable AI productivity and management platform designed for modern teams and enterprises.
+
+The Enterprise Edition addresses core challenges in team collaboration by centralizing the management of AI resources, knowledge, and data. It empowers organizations to enhance efficiency, foster innovation, and ensure compliance, all while maintaining 100% control over their data in a secure environment.
+
+## Core Advantages
+
+- **Unified Model Management**: Centrally integrate and manage various cloud-based LLMs (e.g., OpenAI, Anthropic, Google Gemini) and locally deployed private models. Employees can use them out-of-the-box without individual configuration.
+- **Enterprise-Grade Knowledge Base**: Build, manage, and share team-wide knowledge bases. Ensure knowledge is retained and consistent, enabling team members to interact with AI based on unified and accurate information.
+- **Fine-Grained Access Control**: Easily manage employee accounts and assign role-based permissions for different models, knowledge bases, and features through a unified admin backend.
+- **Fully Private Deployment**: Deploy the entire backend service on your on-premises servers or private cloud, ensuring your data remains 100% private and under your control to meet the strictest security and compliance standards.
+- **Reliable Backend Services**: Provides stable API services, enterprise-grade data backup and recovery mechanisms to ensure business continuity.
+
+## ✨ Online Demo
+
+> 🚧 **Public Beta Notice**
+>
+> The Enterprise Edition is currently in its early public beta stage, and we are actively iterating and optimizing its features. We are aware that it may not be perfectly stable yet. If you encounter any issues or have valuable suggestions during your trial, we would be very grateful if you could contact us via email to provide feedback.
+
+**🔗 [Cherry Studio Enterprise](https://www.cherry-ai.com/enterprise)**
+
+## Version Comparison
+
+| Feature           | Community Edition                          | Enterprise Edition                                                                                                                      |
+| :---------------- | :----------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------- |
+| **Open Source**   | ✅ Yes                                     | ⭕️ part. released to cust.                                                                                                              |
+| **Cost**          | Free for Personal Use / Commercial License | Buyout / Subscription Fee                                                                                                               |
+| **Admin Backend** | —                                          | ● Centralized **Model** Access<br>● **Employee** Management<br>● Shared **Knowledge Base**<br>● **Access** Control<br>● **Data** Backup |
+| **Server**        | —                                          | ✅ Dedicated Private Deployment                                                                                                         |
+
+## Get the Enterprise Edition
+
+We believe the Enterprise Edition will become your team's AI productivity engine. If you are interested in Cherry Studio Enterprise Edition and would like to learn more, request a quote, or schedule a demo, please contact us.
+
+- **For Business Inquiries & Purchasing**:
+  **📧 [bd@cherry-ai.com](mailto:bd@cherry-ai.com)**
+
 # 🔗 Related Projects
 
 - [one-api](https://github.com/songquanpeng/one-api):LLM API management and distribution system, supporting mainstream models like OpenAI, Azure, and Anthropic. Features unified API interface, suitable for key management and secondary distribution.
@@ -180,34 +272,45 @@ Thank you for your support and contributions!
 </a>
 <br /><br />
 
+# 📊 GitHub Stats
+
+![Stats](https://repobeats.axiom.co/api/embed/a693f2e5f773eed620f70031e974552156c7f397.svg 'Repobeats analytics image')
+
 # ⭐️ Star History
 
-[![Star History Chart](https://api.star-history.com/svg?repos=CherryHQ/cherry-studio&type=Timeline)](https://star-history.com/#CherryHQ/cherry-studio&Timeline)
+<a href="https://www.star-history.com/#CherryHQ/cherry-studio&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=CherryHQ/cherry-studio&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=CherryHQ/cherry-studio&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=CherryHQ/cherry-studio&type=Date" />
+ </picture>
+</a>
 
 <!-- Links & Images -->
-[deepwiki-shield]: https://img.shields.io/badge/Deepwiki-CherryHQ-0088CC?style=plastic
+
+[deepwiki-shield]: https://img.shields.io/badge/Deepwiki-CherryHQ-0088CC?logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNy45MyAzMiI+PHBhdGggZD0iTTE5LjMzIDE0LjEyYy42Ny0uMzkgMS41LS4zOSAyLjE4IDBsMS43NCAxYy4wNi4wMy4xMS4wNi4xOC4wN2guMDRjLjA2LjAzLjEyLjAzLjE4LjAzaC4wMmMuMDYgMCAuMTEgMCAuMTctLjAyaC4wM2MuMDYtLjAyLjEyLS4wNS4xNy0uMDhoLjAybDMuNDgtMi4wMWMuMjUtLjE0LjQtLjQxLjQtLjdWOC40YS44MS44MSAwIDAgMC0uNC0uN2wtMy40OC0yLjAxYS44My44MyAwIDAgMC0uODEgMEwxOS43NyA3LjdoLS4wMWwtLjE1LjEyLS4wMi4wMnMtLjA3LjA5LS4xLjE0VjhhLjQuNCAwIDAgMC0uMDguMTd2LjA0Yy0uMDMuMDYtLjAzLjEyLS4wMy4xOXYyLjAxYzAgLjc4LS40MSAxLjQ5LTEuMDkgMS44OC0uNjcuMzktMS41LjM5LTIuMTggMGwtMS43NC0xYS42LjYgMCAwIDAtLjIxLS4wOGMtLjA2LS4wMS0uMTItLjAyLS4xOC0uMDJoLS4wM2MtLjA2IDAtLjExLjAxLS4xNy4wMmgtLjAzYy0uMDYuMDItLjEyLjA0LS4xNy4wN2gtLjAybC0zLjQ3IDIuMDFjLS4yNS4xNC0uNC40MS0uNC43VjE4YzAgLjI5LjE1LjU1LjQuN2wzLjQ4IDIuMDFoLjAyYy4wNi4wNC4xMS4wNi4xNy4wOGguMDNjLjA1LjAyLjExLjAzLjE3LjAzaC4wMmMuMDYgMCAuMTIgMCAuMTgtLjAyaC4wNGMuMDYtLjAzLjEyLS4wNS4xOC0uMDhsMS43NC0xYy42Ny0uMzkgMS41LS4zOSAyLjE3IDBzMS4wOSAxLjExIDEuMDkgMS44OHYyLjAxYzAgLjA3IDAgLjEzLjAyLjE5di4wNGMuMDMuMDYuMDUuMTIuMDguMTd2LjAycy4wOC4wOS4xMi4xM2wuMDIuMDJzLjA5LjA4LjE1LjExYzAgMCAuMDEgMCAuMDEuMDFsMy40OCAyLjAxYy4yNS4xNC41Ni4xNC44MSAwbDMuNDgtMi4wMWMuMjUtLjE0LjQtLjQxLjQtLjd2LTQuMDFhLjgxLjgxIDAgMCAwLS40LS43bC0zLjQ4LTIuMDFoLS4wMmMtLjA1LS4wNC0uMTEtLjA2LS4xNy0uMDhoLS4wM2EuNS41IDAgMCAwLS4xNy0uMDNoLS4wM2MtLjA2IDAtLjEyIDAtLjE4LjAyLS4wNy4wMi0uMTUuMDUtLjIxLjA4bC0xLjc0IDFjLS42Ny4zOS0xLjUuMzktMi4xNyAwYTIuMTkgMi4xOSAwIDAgMS0xLjA5LTEuODhjMC0uNzguNDItMS40OSAxLjA5LTEuODhaIiBzdHlsZT0iZmlsbDojNWRiZjlkIi8+PHBhdGggZD0ibS40IDEzLjExIDMuNDcgMi4wMWMuMjUuMTQuNTYuMTQuOCAwbDMuNDctMi4wMWguMDFsLjE1LS4xMi4wMi0uMDJzLjA3LS4wOS4xLS4xNGwuMDItLjAyYy4wMy0uMDUuMDUtLjExLjA3LS4xN3YtLjA0Yy4wMy0uMDYuMDMtLjEyLjAzLS4xOVYxMC40YzAtLjc4LjQyLTEuNDkgMS4wOS0xLjg4czEuNS0uMzkgMi4xOCAwbDEuNzQgMWMuMDcuMDQuMTQuMDcuMjEuMDguMDYuMDEuMTIuMDIuMTguMDJoLjAzYy4wNiAwIC4xMS0uMDEuMTctLjAyaC4wM2MuMDYtLjAyLjEyLS4wNC4xNy0uMDdoLjAybDMuNDctMi4wMmMuMjUtLjE0LjQtLjQxLjQtLjd2LTRhLjgxLjgxIDAgMCAwLS40LS43bC0zLjQ2LTJhLjgzLjgzIDAgMCAwLS44MSAwbC0zLjQ4IDIuMDFoLS4wMWwtLjE1LjEyLS4wMi4wMi0uMS4xMy0uMDIuMDJjLS4wMy4wNS0uMDUuMTEtLjA3LjE3di4wNGMtLjAzLjA2LS4wMy4xMi0uMDMuMTl2Mi4wMWMwIC43OC0uNDIgMS40OS0xLjA5IDEuODhzLTEuNS4zOS0yLjE4IDBsLTEuNzQtMWEuNi42IDAgMCAwLS4yMS0uMDhjLS4wNi0uMDEtLjEyLS4wMi0uMTgtLjAyaC0uMDNjLS4wNiAwLS4xMS4wMS0uMTcuMDJoLS4wM2MtLjA2LjAyLS4xMi4wNS0uMTcuMDhoLS4wMkwuNCA3LjcxYy0uMjUuMTQtLjQuNDEtLjQuNjl2NC4wMWMwIC4yOS4xNS41Ni40LjciIHN0eWxlPSJmaWxsOiM0NDY4YzQiLz48cGF0aCBkPSJtMTcuODQgMjQuNDgtMy40OC0yLjAxaC0uMDJjLS4wNS0uMDQtLjExLS4wNi0uMTctLjA4aC0uMDNhLjUuNSAwIDAgMC0uMTctLjAzaC0uMDNjLS4wNiAwLS4xMiAwLS4xOC4wMmgtLjA0Yy0uMDYuMDMtLjEyLjA1LS4xOC4wOGwtMS43NCAxYy0uNjcuMzktMS41LjM5LTIuMTggMGEyLjE5IDIuMTkgMCAwIDEtMS4wOS0xLjg4di0yLjAxYzAtLjA2IDAtLjEzLS4wMi0uMTl2LS4wNGMtLjAzLS4wNi0uMDUtLjExLS4wOC0uMTdsLS4wMi0uMDJzLS4wNi0uMDktLjEtLjEzTDguMjkgMTlzLS4wOS0uMDgtLjE1LS4xMWgtLjAxbC0zLjQ3LTIuMDJhLjgzLjgzIDAgMCAwLS44MSAwTC4zNyAxOC44OGEuODcuODcgMCAwIDAtLjM3LjcxdjQuMDFjMCAuMjkuMTUuNTUuNC43bDMuNDcgMi4wMWguMDJjLjA1LjA0LjExLjA2LjE3LjA4aC4wM2MuMDUuMDIuMTEuMDMuMTYuMDNoLjAzYy4wNiAwIC4xMiAwIC4xOC0uMDJoLjA0Yy4wNi0uMDMuMTItLjA1LjE4LS4wOGwxLjc0LTFjLjY3LS4zOSAxLjUtLjM5IDIuMTcgMHMxLjA5IDEuMTEgMS4wOSAxLjg4djIuMDFjMCAuMDcgMCAuMTMuMDIuMTl2LjA0Yy4wMy4wNi4wNS4xMS4wOC4xN2wuMDIuMDJzLjA2LjA5LjEuMTRsLjAyLjAycy4wOS4wOC4xNS4xMWguMDFsMy40OCAyLjAyYy4yNS4xNC41Ni4xNC44MSAwbDMuNDgtMi4wMWMuMjUtLjE0LjQtLjQxLjQtLjdWMjUuMmEuODEuODEgMCAwIDAtLjQtLjdaIiBzdHlsZT0iZmlsbDojNDI5M2Q5Ii8+PC9zdmc+
 [deepwiki-link]: https://deepwiki.com/CherryHQ/cherry-studio
-[twitter-shield]: https://img.shields.io/badge/Twitter-CherryStudioApp-0088CC?style=plastic&logo=x
+[twitter-shield]: https://img.shields.io/badge/Twitter-CherryStudioApp-0088CC?logo=x
 [twitter-link]: https://twitter.com/CherryStudioHQ
-[discord-shield]: https://img.shields.io/badge/Discord-@CherryStudio-0088CC?style=plastic&logo=discord
+[discord-shield]: https://img.shields.io/badge/Discord-@CherryStudio-0088CC?logo=discord
 [discord-link]: https://discord.gg/wez8HtpxqQ
-[telegram-shield]: https://img.shields.io/badge/Telegram-@CherryStudioAI-0088CC?style=plastic&logo=telegram
+[telegram-shield]: https://img.shields.io/badge/Telegram-@CherryStudioAI-0088CC?logo=telegram
 [telegram-link]: https://t.me/CherryStudioAI
 
 <!-- Links & Images -->
-[github-stars-shield]: https://img.shields.io/github/stars/CherryHQ/cherry-studio?style=social
-[github-stars-link]: https://github.com/CherryHQ/cherry-studio/stargazers
-[github-forks-shield]: https://img.shields.io/github/forks/CherryHQ/cherry-studio?style=social
-[github-forks-link]: https://github.com/CherryHQ/cherry-studio/network
-[github-release-shield]: https://img.shields.io/github/v/release/CherryHQ/cherry-studio
+
+[github-release-shield]: https://img.shields.io/github/v/release/CherryHQ/cherry-studio?logo=github
 [github-release-link]: https://github.com/CherryHQ/cherry-studio/releases
-[github-contributors-shield]: https://img.shields.io/github/contributors/CherryHQ/cherry-studio
+[github-nightly-shield]: https://img.shields.io/github/actions/workflow/status/CherryHQ/cherry-studio/nightly-build.yml?label=nightly%20build&logo=github
+[github-nightly-link]: https://github.com/CherryHQ/cherry-studio/actions/workflows/nightly-build.yml
+[github-contributors-shield]: https://img.shields.io/github/contributors/CherryHQ/cherry-studio?logo=github
 [github-contributors-link]: https://github.com/CherryHQ/cherry-studio/graphs/contributors
 
 <!-- Links & Images -->
-[license-shield]: https://img.shields.io/badge/License-AGPLv3-important.svg?style=plastic&logo=gnu
+
+[license-shield]: https://img.shields.io/badge/License-AGPLv3-important.svg?logo=gnu
 [license-link]: https://www.gnu.org/licenses/agpl-3.0
-[commercial-shield]: https://img.shields.io/badge/License-Contact-white.svg?style=plastic&logoColor=white&logo=telegram&color=blue
+[commercial-shield]: https://img.shields.io/badge/License-Contact-white.svg?logoColor=white&logo=telegram&color=blue
 [commercial-link]: mailto:license@cherry-ai.com?subject=Commercial%20License%20Inquiry
-[sponsor-shield]: https://img.shields.io/badge/Sponsor-FF6699.svg?style=plastic&logo=githubsponsors&logoColor=white
+[sponsor-shield]: https://img.shields.io/badge/Sponsor-FF6699.svg?logo=githubsponsors&logoColor=white
 [sponsor-link]: https://github.com/CherryHQ/cherry-studio/blob/main/docs/sponsor.md

docs/CONTRIBUTING.zh.md

@@ -1,6 +1,6 @@
 # Cherry Studio 贡献者指南
 
-[**English**](../CONTRIBUTING.md) | [**中文**](./CONTRIBUTING.zh.md)
+[**English**](../CONTRIBUTING.md) | [**中文**](CONTRIBUTING.zh.md)
 
 欢迎来到 Cherry Studio 的贡献者社区！我们致力于将 Cherry Studio 打造成一个长期提供价值的项目，并希望邀请更多的开发者加入我们的行列。无论您是经验丰富的开发者还是刚刚起步的初学者，您的贡献都将帮助我们更好地服务用户，提升软件质量。
 
@@ -24,7 +24,7 @@
 
 ## 开始之前
 
-请确保阅读了[行为准则](CODE_OF_CONDUCT.md)和[LICENSE](LICENSE)。
+请确保阅读了[行为准则](../CODE_OF_CONDUCT.md)和[LICENSE](../LICENSE)。
 
 ## 开始贡献
 
@@ -32,7 +32,7 @@
 
 ### 测试
 
-未经测试的功能等同于不存在。为确保代码真正有效，应通过单元测试和功能测试覆盖相关流程。因此，在考虑贡献时，也请考虑可测试性。所有测试均可本地运行，无需依赖 CI。请参阅[开发者指南](docs/dev.md#test)中的“Test”部分。
+未经测试的功能等同于不存在。为确保代码真正有效，应通过单元测试和功能测试覆盖相关流程。因此，在考虑贡献时，也请考虑可测试性。所有测试均可本地运行，无需依赖 CI。请参阅[开发者指南](dev.md#test)中的“Test”部分。
 
 ### 拉取请求的自动化测试
 
@@ -60,7 +60,11 @@ git commit --signoff -m "Your commit message"
 
 ### 获取代码审查/合并
 
-维护者在此帮助您在合理时间内实现您的用例。他们会尽力在合理时间内审查您的代码并提供建设性反馈。但如果您在审查过程中受阻，或认为您的 Pull Request 未得到应有的关注，请通过 Issue 中的评论或者[社群](README.md#-community)联系我们
+维护者在此帮助您在合理时间内实现您的用例。他们会尽力在合理时间内审查您的代码并提供建设性反馈。但如果您在审查过程中受阻，或认为您的 Pull Request 未得到应有的关注，请通过 Issue 中的评论或者[社群](README.zh.md#-community)联系我们
+
+### 参与测试计划
+
+测试计划旨在为用户提供更稳定的应用体验和更快的迭代速度，详细情况请参阅[测试计划](testplan-zh.md)。
 
 ### 其他建议
 

docs/README.ja.md

@@ -1,215 +0,0 @@
-<h1 align="center">
-  <a href="https://github.com/CherryHQ/cherry-studio/releases">
-    <img src="https://github.com/CherryHQ/cherry-studio/blob/main/build/icon.png?raw=true" width="150" height="150" alt="banner" /><br>
-  </a>
-</h1>
-<p align="center">
-  <a href="https://github.com/CherryHQ/cherry-studio">English</a> | <a href="./README.zh.md">中文</a> | 日本語 | <a href="https://cherry-ai.com">公式サイト</a> | <a href="https://docs.cherry-ai.com/cherry-studio-wen-dang/ja">ドキュメント</a> | <a href="./dev.md">開発</a> | <a href="https://github.com/CherryHQ/cherry-studio/issues">フィードバック</a><br>
-</p>
-
-<!-- バッジコレクション -->
-
-<div align="center">
-
-[![][deepwiki-shield]][deepwiki-link]
-[![][twitter-shield]][twitter-link]
-[![][discord-shield]][discord-link]
-[![][telegram-shield]][telegram-link]
-
-</div>
-
-<!-- プロジェクト統計 -->
-
-<div align="center">
-
-[![][github-stars-shield]][github-stars-link]
-[![][github-forks-shield]][github-forks-link]
-[![][github-release-shield]][github-release-link]
-[![][github-contributors-shield]][github-contributors-link]
-
-</div>
-
-<div align="center">
-
-[![][license-shield]][license-link]
-[![][commercial-shield]][commercial-link]
-[![][sponsor-shield]][sponsor-link]
-
-</div>
-
-<div align="center">
- <a href="https://hellogithub.com/repository/1605492e1e2a4df3be07abfa4578dd37" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=1605492e1e2a4df3be07abfa4578dd37" alt="Featured｜HelloGitHub" style="width: 200px; height: 43px;" width="200" height="43" /></a>
- <a href="https://trendshift.io/repositories/11772" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11772" alt="kangfenmao%2Fcherry-studio | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
- <a href="https://www.producthunt.com/posts/cherry-studio?embed=true&utm_source=badge-featured&utm_medium=badge&utm_souce=badge-cherry&#0045;studio" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=496640&theme=light" alt="Cherry&#0032;Studio - AI&#0032;Chatbots&#0044;&#0032;AI&#0032;Desktop&#0032;Client | Product Hunt" style="width: 200px; height: 43px;" width="200" height="43" /></a>
-</div>
-
-# 🍒 Cherry Studio
-
-Cherry Studio は、複数の LLM プロバイダーをサポートするデスクトップクライアントで、Windows、Mac、Linux で利用可能です。
-
-👏 [Telegram](https://t.me/CherryStudioAI)｜[Discord](https://discord.gg/wez8HtpxqQ) | [QQグループ(575014769)](https://qm.qq.com/q/lo0D4qVZKi)
-
-❤️ Cherry Studio をお気に入りにしましたか？小さな星をつけてください 🌟 または [スポンサー](sponsor.md) をして開発をサポートしてください！
-
-# 🌠 スクリーンショット
-
-![](https://github.com/user-attachments/assets/36dddb2c-e0fb-4a5f-9411-91447bab6e18)
-
-![](https://github.com/user-attachments/assets/f549e8a0-2385-40b4-b52b-2039e39f2930)
-
-![](https://github.com/user-attachments/assets/58e0237c-4d36-40de-b428-53051d982026)
-
-# 🌟 主な機能
-
-1. **多様な LLM サービス対応**：
-
-- ☁️ 主要な LLM クラウドサービス対応：OpenAI、Gemini、Anthropic など
-- 🔗 AI Web サービス統合：Claude、Peplexity、Poe など
-- 💻 Ollama、LM Studio によるローカルモデル実行対応
-
-2. **AI アシスタントと対話**：
-
-- 📚 300+ の事前設定済み AI アシスタント
-- 🤖 カスタム AI アシスタントの作成
-- 💬 複数モデルでの同時対話機能
-
-3. **文書とデータ処理**：
-
-- 📄 テキスト、画像、Office、PDF など多様な形式対応
-- ☁️ WebDAV によるファイル管理とバックアップ
-- 📊 Mermaid による図表作成
-- 💻 コードハイライト機能
-
-4. **実用的なツール統合**：
-
-- 🔍 グローバル検索機能
-- 📝 トピック管理システム
-- 🔤 AI による翻訳機能
-- 🎯 ドラッグ＆ドロップによる整理
-- 🔌 ミニプログラム対応
-- ⚙️ MCP（モデルコンテキストプロトコル）サービス
-
-5. **優れたユーザー体験**：
-
-- 🖥️ Windows、Mac、Linux のクロスプラットフォーム対応
-- 📦 環境構築不要ですぐに使用可能
-- 🎨 ライト/ダークテーマと透明ウィンドウ対応
-- 📝 完全な Markdown レンダリング
-- 🤲 簡単な共有機能
-
-# 📝 開発計画
-
-以下の機能と改善に積極的に取り組んでいます：
-
-1. 🎯 **コア機能**
-
-- 選択アシスタント - スマートな内容選択の強化
-- ディープリサーチ - 高度な研究能力
-- メモリーシステム - グローバルコンテキスト認識
-- ドキュメント前処理 - 文書処理の改善
-- MCP マーケットプレイス - モデルコンテキストプロトコルエコシステム
-
-2. 🗂 **ナレッジ管理**
-
-- ノートとコレクション
-- ダイナミックキャンバス可視化
-- OCR 機能
-- TTS（テキスト読み上げ）サポート
-
-3. 📱 **プラットフォーム対応**
-
-- HarmonyOS エディション
-- Android アプリ（フェーズ1）
-- iOS アプリ（フェーズ1）
-- マルチウィンドウ対応
-- ウィンドウピン留め機能
-
-4. 🔌 **高度な機能**
-
-- プラグインシステム
-- ASR（音声認識）
-- アシスタントとトピックの対話機能リファクタリング
-
-[プロジェクトボード](https://github.com/orgs/CherryHQ/projects/7)で進捗を確認し、貢献することができます。
-
-開発計画に影響を与えたいですか？[GitHub ディスカッション](https://github.com/CherryHQ/cherry-studio/discussions)に参加して、アイデアやフィードバックを共有してください！
-
-# 🌈 テーマ
-
-- テーマギャラリー：https://cherrycss.com
-- Aero テーマ：https://github.com/hakadao/CherryStudio-Aero
-- PaperMaterial テーマ：https://github.com/rainoffallingstar/CherryStudio-PaperMaterial
-- Claude テーマ：https://github.com/bjl101501/CherryStudio-Claudestyle-dynamic
-- メープルネオンテーマ：https://github.com/BoningtonChen/CherryStudio_themes
-
-より多くのテーマの PR を歓迎します
-
-# 🤝 貢献
-
-Cherry Studio への貢献を歓迎します！以下の方法で貢献できます：
-
-1. **コードの貢献**：新機能を開発するか、既存のコードを最適化します
-2. **バグの修正**：見つけたバグを修正します
-3. **問題の管理**：GitHub の問題を管理するのを手伝います
-4. **製品デザイン**：デザインの議論に参加します
-5. **ドキュメントの作成**：ユーザーマニュアルやガイドを改善します
-6. **コミュニティの参加**：ディスカッションに参加し、ユーザーを支援します
-7. **使用の促進**：Cherry Studio を広めます
-
-[ブランチ戦略](branching-strategy-en.md)を参照して貢献ガイドラインを確認してください
-
-## 始め方
-
-1. **リポジトリをフォーク**：フォークしてローカルマシンにクローンします
-2. **ブランチを作成**：変更のためのブランチを作成します
-3. **変更を提出**：変更をコミットしてプッシュします
-4. **プルリクエストを開く**：変更内容と理由を説明します
-
-詳細なガイドラインについては、[貢献ガイド](../CONTRIBUTING.md)をご覧ください。
-
-ご支援と貢献に感謝します！
-
-# 🔗 関連プロジェクト
-
-- [one-api](https://github.com/songquanpeng/one-api)：LLM API の管理・配信システム。OpenAI、Azure、Anthropic などの主要モデルに対応し、統一 API インターフェースを提供。API キー管理と再配布に利用可能。
-
-- [ublacklist](https://github.com/iorate/ublacklist)：Google 検索結果から特定のサイトを非表示にします
-
-# 🚀 コントリビューター
-
-<a href="https://github.com/CherryHQ/cherry-studio/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=CherryHQ/cherry-studio" />
-</a>
-<br /><br />
-
-# ⭐️ スター履歴
-
-[![Star History Chart](https://api.star-history.com/svg?repos=CherryHQ/cherry-studio&type=Timeline)](https://star-history.com/#CherryHQ/cherry-studio&Timeline)
-
-<!-- リンクと画像 -->
-[deepwiki-shield]: https://img.shields.io/badge/Deepwiki-CherryHQ-0088CC?style=plastic
-[deepwiki-link]: https://deepwiki.com/CherryHQ/cherry-studio
-[twitter-shield]: https://img.shields.io/badge/Twitter-CherryStudioApp-0088CC?style=plastic&logo=x
-[twitter-link]: https://twitter.com/CherryStudioHQ
-[discord-shield]: https://img.shields.io/badge/Discord-@CherryStudio-0088CC?style=plastic&logo=discord
-[discord-link]: https://discord.gg/wez8HtpxqQ
-[telegram-shield]: https://img.shields.io/badge/Telegram-@CherryStudioAI-0088CC?style=plastic&logo=telegram
-[telegram-link]: https://t.me/CherryStudioAI
-
-<!-- プロジェクト統計 -->
-[github-stars-shield]: https://img.shields.io/github/stars/CherryHQ/cherry-studio?style=social
-[github-stars-link]: https://github.com/CherryHQ/cherry-studio/stargazers
-[github-forks-shield]: https://img.shields.io/github/forks/CherryHQ/cherry-studio?style=social
-[github-forks-link]: https://github.com/CherryHQ/cherry-studio/network
-[github-release-shield]: https://img.shields.io/github/v/release/CherryHQ/cherry-studio
-[github-release-link]: https://github.com/CherryHQ/cherry-studio/releases
-[github-contributors-shield]: https://img.shields.io/github/contributors/CherryHQ/cherry-studio
-[github-contributors-link]: https://github.com/CherryHQ/cherry-studio/graphs/contributors
-
-<!-- ライセンスとスポンサー -->
-[license-shield]: https://img.shields.io/badge/License-AGPLv3-important.svg?style=plastic&logo=gnu
-[license-link]: https://www.gnu.org/licenses/agpl-3.0
-[commercial-shield]: https://img.shields.io/badge/商用ライセンス-お問い合わせ-white.svg?style=plastic&logoColor=white&logo=telegram&color=blue
-[commercial-link]: mailto:license@cherry-ai.com?subject=商業ライセンスについて
-[sponsor-shield]: https://img.shields.io/badge/スポンサー-FF6699.svg?style=plastic&logo=githubsponsors&logoColor=white
-[sponsor-link]: https://github.com/CherryHQ/cherry-studio/blob/main/docs/sponsor.md

docs/README.zh.md

@@ -1,10 +1,40 @@
+<div align="right" >
+  <details>
+    <summary >🌐 Language</summary>
+    <div>
+      <div align="right">
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=en">English</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=zh-CN">简体中文</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=zh-TW">繁體中文</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=ja">日本語</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=ko">한국어</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=hi">हिन्दी</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=th">ไทย</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=fr">Français</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=de">Deutsch</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=es">Español</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=it">Itapano</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=ru">Русский</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=pt">Português</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=nl">Nederlands</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=pl">Polski</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=ar">العربية</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=fa">فارسی</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=tr">Türkçe</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=vi">Tiếng Việt</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=id">Bahasa Indonesia</a></p>
+      </div>
+    </div>
+  </details>
+</div>
+
 <h1 align="center">
   <a href="https://github.com/CherryHQ/cherry-studio/releases">
     <img src="https://github.com/CherryHQ/cherry-studio/blob/main/build/icon.png?raw=true" width="150" height="150" alt="banner" /><br>
   </a>
 </h1>
 <p align="center">
-  <a href="https://github.com/CherryHQ/cherry-studio">English</a> | 中文 | <a href="./README.ja.md">日本語</a> | <a href="https://cherry-ai.com">官方网站</a> | <a href="https://docs.cherry-ai.com/cherry-studio-wen-dang/zh-cn">文档</a> | <a href="./dev.md">开发</a> | <a href="https://github.com/CherryHQ/cherry-studio/issues">反馈</a><br>
+  <a href="https://github.com/CherryHQ/cherry-studio">English</a> | 中文 | <a href="https://cherry-ai.com">官方网站</a> | <a href="https://docs.cherry-ai.com/cherry-studio-wen-dang/zh-cn">文档</a> | <a href="./dev.md">开发</a> | <a href="https://github.com/CherryHQ/cherry-studio/issues">反馈</a><br>
 </p>
 
 <!-- 题头徽章组合 -->
@@ -18,19 +48,10 @@
 
 </div>
 
-<!-- 项目统计徽章 -->
-
 <div align="center">
 
-[![][github-stars-shield]][github-stars-link]
-[![][github-forks-shield]][github-forks-link]
 [![][github-release-shield]][github-release-link]
 [![][github-contributors-shield]][github-contributors-link]
-
-</div>
-
-<div align="center">
-
 [![][license-shield]][license-link]
 [![][commercial-shield]][commercial-link]
 [![][sponsor-shield]][sponsor-link]
@@ -38,9 +59,9 @@
 </div>
 
 <div align="center">
- <a href="https://hellogithub.com/repository/1605492e1e2a4df3be07abfa4578dd37" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=1605492e1e2a4df3be07abfa4578dd37" alt="Featured｜HelloGitHub" style="width: 200px; height: 43px;" width="200" height="43" /></a>
- <a href="https://trendshift.io/repositories/11772" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11772" alt="kangfenmao%2Fcherry-studio | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
- <a href="https://www.producthunt.com/posts/cherry-studio?embed=true&utm_source=badge-featured&utm_medium=badge&utm_souce=badge-cherry&#0045;studio" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=496640&theme=light" alt="Cherry&#0032;Studio - AI&#0032;Chatbots&#0044;&#0032;AI&#0032;Desktop&#0032;Client | Product Hunt" style="width: 200px; height: 43px;" width="200" height="43" /></a>
+ <a href="https://hellogithub.com/repository/1605492e1e2a4df3be07abfa4578dd37" target="_blank" style="text-decoration: none"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=1605492e1e2a4df3be07abfa4578dd37" alt="Featured｜HelloGitHub"  width="220" height="55" /></a>
+ <a href="https://trendshift.io/repositories/11772" target="_blank" style="text-decoration: none"><img src="https://trendshift.io/api/badge/repositories/11772" alt="kangfenmao%2Fcherry-studio | Trendshift" width="220" height="55" /></a>
+ <a href="https://www.producthunt.com/posts/cherry-studio?embed=true&utm_source=badge-featured&utm_medium=badge&utm_souce=badge-cherry&#0045;studio" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=496640&theme=light" alt="Cherry&#0032;Studio - AI&#0032;Chatbots&#0044;&#0032;AI&#0032;Desktop&#0032;Client | Product Hunt" width="220" height="55" /></a>
 </div>
 
 # 🍒 Cherry Studio
@@ -51,14 +72,6 @@ Cherry Studio 是一款支持多个大语言模型（LLM）服务商的桌面客
 
 ❤️ 喜欢 Cherry Studio? 点亮小星星 🌟 或 [赞助开发者](sponsor.md)! ❤️
 
-# GitCode✖️Cherry Studio【新源力】贡献挑战赛
-
-<p align="center">
-  <a href="https://gitcode.com/CherryHQ/cherry-studio/discussion/2">
-    <img src="https://raw.gitcode.com/user-images/assets/5007375/8d8d7559-1141-4691-b90f-d154558c6896/cherry-studio-gitcode.jpg" width="100%" alt="banner" />
-  </a>
-</p>
-
 # 📖 使用教程
 
 https://docs.cherry-ai.com
@@ -177,10 +190,82 @@ https://docs.cherry-ai.com
 3. **提交更改**：提交并推送您的更改
 4. **打开 Pull Request**：描述您的更改和原因
 
-有关更详细的指南，请参阅我们的 [贡献指南](./CONTRIBUTING.zh.md)
+有关更详细的指南，请参阅我们的 [贡献指南](CONTRIBUTING.zh.md)
 
 感谢您的支持和贡献！
 
+# 🔧 开发者共创计划
+
+我们正在启动 Cherry Studio 开发者共创计划，旨在为开源生态系统构建一个健康、正向反馈的循环。我们相信，优秀的软件是通过协作构建的，每一个合并的拉取请求都为项目注入新的生命力。
+
+我们诚挚地邀请您加入我们的贡献者队伍，与我们一起塑造 Cherry Studio 的未来。
+
+## 贡献者奖励计划
+
+为了回馈我们的核心贡献者并创造良性循环，我们建立了以下长期激励计划。
+
+**该计划的首个跟踪周期将是 2025 年第三季度（7月、8月、9月）。此周期的奖励将在 10月1日 发放。**
+
+在任何跟踪周期内（例如，首个周期的 7月1日 至 9月30日），任何为 Cherry Studio 在 GitHub 上的开源项目贡献超过 **30 个有意义提交** 的开发者都有资格获得以下福利：
+
+- **Cursor 订阅赞助**：获得 **70 美元** 的 [Cursor](https://cursor.sh/) 订阅积分或报销，让 AI 成为您最高效的编码伙伴。
+- **无限模型访问**：获得 **DeepSeek** 和 **Qwen** 模型的 **无限次** API 调用。
+- **前沿技术访问**：享受偶尔的特殊福利，包括 **Claude**、**Gemini** 和 **OpenAI** 等模型的 API 访问权限，让您始终站在技术前沿。
+
+## 共同成长与未来规划
+
+活跃的社区是任何可持续开源项目背后的推动力。随着 Cherry Studio 的发展，我们的奖励计划也将随之发展。我们致力于持续将我们的福利与行业内最优秀的工具和资源保持一致。这确保我们的核心贡献者获得有意义的支持，创造一个开发者、社区和项目共同成长的正向循环。
+
+**展望未来，该项目还将采取越来越开放的态度来回馈整个开源社区。**
+
+## 如何开始？
+
+我们期待您的第一个拉取请求！
+
+您可以从探索我们的仓库开始，选择一个 `good first issue`，或者提出您自己的改进建议。每一个提交都是开源精神的体现。
+
+感谢您的关注和贡献。
+
+让我们一起建设。
+
+# 🏢 企业版
+
+在社区版的基础上，我们自豪地推出 **Cherry Studio 企业版**——一个为现代团队和企业设计的私有部署 AI 生产力与管理平台。
+
+企业版通过集中管理 AI 资源、知识和数据，解决了团队协作中的核心挑战。它赋能组织提升效率、促进创新并确保合规，同时在安全环境中保持对数据的 100% 控制。
+
+## 核心优势
+
+- **统一模型管理**：集中整合和管理各种基于云的大语言模型（如 OpenAI、Anthropic、Google Gemini）和本地部署的私有模型。员工可以开箱即用，无需单独配置。
+- **企业级知识库**：构建、管理和分享全团队的知识库。确保知识得到保留且一致，使团队成员能够基于统一准确的信息与 AI 交互。
+- **细粒度访问控制**：通过统一的管理后台轻松管理员工账户，并为不同模型、知识库和功能分配基于角色的权限。
+- **完全私有部署**：在您的本地服务器或私有云上部署整个后端服务，确保您的数据 100% 私有且在您的控制之下，满足最严格的安全和合规标准。
+- **可靠的后端服务**：提供稳定的 API 服务、企业级数据备份和恢复机制，确保业务连续性。
+
+## ✨ 在线演示
+
+> 🚧 **公开测试版通知**
+>
+> 企业版目前处于早期公开测试阶段，我们正在积极迭代和优化其功能。我们知道它可能还不够完全稳定。如果您在试用过程中遇到任何问题或有宝贵建议，我们非常感谢您能通过邮件联系我们提供反馈。
+
+**🔗 [Cherry Studio 企业版](https://www.cherry-ai.com/enterprise)**
+
+## 版本对比
+
+| 功能         | 社区版                  | 企业版                                                                                         |
+| :----------- | :---------------------- | :--------------------------------------------------------------------------------------------- |
+| **开源**     | ✅ 是                   | ⭕️ 部分开源，对客户开放                                                                        |
+| **成本**     | 个人使用免费 / 商业授权 | 买断 / 订阅费用                                                                                |
+| **管理后台** | —                       | ● 集中化**模型**访问<br>● **员工**管理<br>● 共享**知识库**<br>● **访问**控制<br>● **数据**备份 |
+| **服务器**   | —                       | ✅ 专用私有部署                                                                                |
+
+## 获取企业版
+
+我们相信企业版将成为您团队的 AI 生产力引擎。如果您对 Cherry Studio 企业版感兴趣，希望了解更多信息、请求报价或安排演示，请联系我们。
+
+- **商业咨询与购买**：
+  **📧 [bd@cherry-ai.com](mailto:bd@cherry-ai.com)**
+
 # 🔗 相关项目
 
 - [one-api](https://github.com/songquanpeng/one-api)：LLM API 管理及分发系统，支持 OpenAI、Azure、Anthropic 等主流模型，统一 API 接口，可用于密钥管理与二次分发。
@@ -194,34 +279,43 @@ https://docs.cherry-ai.com
 </a>
 <br /><br />
 
+# 📊 GitHub 统计
+
+![Stats](https://repobeats.axiom.co/api/embed/a693f2e5f773eed620f70031e974552156c7f397.svg 'Repobeats analytics image')
+
 # ⭐️ Star 记录
 
-[![Star History Chart](https://api.star-history.com/svg?repos=CherryHQ/cherry-studio&type=Timeline)](https://star-history.com/#CherryHQ/cherry-studio&Timeline)
+<a href="https://www.star-history.com/#CherryHQ/cherry-studio&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=CherryHQ/cherry-studio&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=CherryHQ/cherry-studio&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=CherryHQ/cherry-studio&type=Date" />
+ </picture>
+</a>
 
 <!-- Links & Images -->
-[deepwiki-shield]: https://img.shields.io/badge/Deepwiki-CherryHQ-0088CC?style=plastic
+
+[deepwiki-shield]: https://img.shields.io/badge/Deepwiki-CherryHQ-0088CC
 [deepwiki-link]: https://deepwiki.com/CherryHQ/cherry-studio
-[twitter-shield]: https://img.shields.io/badge/Twitter-CherryStudioApp-0088CC?style=plastic&logo=x
+[twitter-shield]: https://img.shields.io/badge/Twitter-CherryStudioApp-0088CC?logo=x
 [twitter-link]: https://twitter.com/CherryStudioHQ
-[discord-shield]: https://img.shields.io/badge/Discord-@CherryStudio-0088CC?style=plastic&logo=discord
+[discord-shield]: https://img.shields.io/badge/Discord-@CherryStudio-0088CC?logo=discord
 [discord-link]: https://discord.gg/wez8HtpxqQ
-[telegram-shield]: https://img.shields.io/badge/Telegram-@CherryStudioAI-0088CC?style=plastic&logo=telegram
+[telegram-shield]: https://img.shields.io/badge/Telegram-@CherryStudioAI-0088CC?logo=telegram
 [telegram-link]: https://t.me/CherryStudioAI
 
 <!-- 项目统计徽章 -->
-[github-stars-shield]: https://img.shields.io/github/stars/CherryHQ/cherry-studio?style=social
-[github-stars-link]: https://github.com/CherryHQ/cherry-studio/stargazers
-[github-forks-shield]: https://img.shields.io/github/forks/CherryHQ/cherry-studio?style=social
-[github-forks-link]: https://github.com/CherryHQ/cherry-studio/network
+
 [github-release-shield]: https://img.shields.io/github/v/release/CherryHQ/cherry-studio
 [github-release-link]: https://github.com/CherryHQ/cherry-studio/releases
 [github-contributors-shield]: https://img.shields.io/github/contributors/CherryHQ/cherry-studio
 [github-contributors-link]: https://github.com/CherryHQ/cherry-studio/graphs/contributors
 
 <!-- 许可和赞助徽章 -->
-[license-shield]: https://img.shields.io/badge/License-AGPLv3-important.svg?style=plastic&logo=gnu
+
+[license-shield]: https://img.shields.io/badge/License-AGPLv3-important.svg?logo=gnu
 [license-link]: https://www.gnu.org/licenses/agpl-3.0
-[commercial-shield]: https://img.shields.io/badge/商用授权-联系-white.svg?style=plastic&logoColor=white&logo=telegram&color=blue
+[commercial-shield]: https://img.shields.io/badge/商用授权-联系-white.svg?logoColor=white&logo=telegram&color=blue
 [commercial-link]: mailto:license@cherry-ai.com?subject=商业授权咨询
-[sponsor-shield]: https://img.shields.io/badge/赞助支持-FF6699.svg?style=plastic&logo=githubsponsors&logoColor=white
+[sponsor-shield]: https://img.shields.io/badge/赞助支持-FF6699.svg?logo=githubsponsors&logoColor=white
 [sponsor-link]: https://github.com/CherryHQ/cherry-studio/blob/main/docs/sponsor.md

docs/branching-strategy-en.md

@@ -16,6 +16,8 @@ Cherry Studio implements a structured branching strategy to maintain code qualit
   - Only accepts documentation updates and bug fixes
   - Thoroughly tested before production deployment
 
+For details about the `testplan` branch used in the Test Plan, please refer to the [Test Plan](testplan-en.md).
+
 ## Contributing Branches
 
 When contributing to Cherry Studio, please follow these guidelines:

docs/branching-strategy-zh.md

@@ -16,6 +16,8 @@ Cherry Studio 采用结构化的分支策略来维护代码质量并简化开发
   - 只接受文档更新和 bug 修复
   - 经过完整测试后可以发布到生产环境
 
+关于测试计划所使用的`testplan`分支，请查阅[测试计划](testplan-zh.md)。
+
 ## 贡献分支
 
 在为 Cherry Studio 贡献代码时，请遵循以下准则：

docs/testplan-en.md

@@ -0,0 +1,99 @@
+# Test Plan
+
+To provide users with a more stable application experience and faster iteration speed, Cherry Studio has launched the "Test Plan".
+
+## User Guide
+
+The Test Plan is divided into the RC channel and the Beta channel, with the following differences:
+
+- **RC (Release Candidate)**: The features are stable, with fewer bugs, and it is close to the official release.
+- **Beta**: Features may change at any time, and there may be more bugs, but users can experience future features earlier.
+
+Users can enable the "Test Plan" and select the version channel in the software's `Settings` > `About`. Please note that the versions in the "Test Plan" cannot guarantee data consistency, so be sure to back up your data before using them.
+
+Users are welcome to submit issues or provide feedback through other channels for any bugs encountered during testing. Your feedback is very important to us.
+
+## Developer Guide
+
+### Participating in the Test Plan
+
+Developers should submit `PRs` according to the [Contributor Guide](../CONTRIBUTING.md) (and ensure the target branch is `main`). The repository maintainers will evaluate whether the `PR` should be included in the Test Plan based on factors such as the impact of the feature on the application, its importance, and whether broader testing is needed.
+
+If the `PR` is added to the Test Plan, the repository maintainers will:
+
+- Notify the `PR` submitter.
+- Set the PR to `draft` status (to avoid accidental merging into `main` before testing is complete).
+- Set the `milestone` to the specific Test Plan version.
+- Modify the `PR` title.
+
+During participation in the Test Plan, `PR` submitters should:
+
+- Keep the `PR` branch synchronized with the latest `main` (i.e., the `PR` branch should always be based on the latest `main` code).
+- Ensure the `PR` branch is conflict-free.
+- Actively respond to comments & reviews and fix bugs.
+- Enable maintainers to modify the `PR` branch to allow for bug fixes at any time.
+
+Inclusion in the Test Plan does not guarantee the final merging of the `PR`. It may be shelved due to immature features or poor testing feedback.
+
+### Test Plan Lead
+
+A maintainer will be assigned as the lead for a specific version (e.g., `1.5.0-rc`). The responsibilities of the Test Plan lead include:
+
+- Determining whether a `PR` meets the Test Plan requirements and deciding whether it should be included in the current Test Plan.
+- Modifying the status of `PRs` added to the Test Plan and communicating relevant matters with the `PR` submitter.
+- Before the Test Plan release, merging the branches of `PRs` added to the Test Plan (using squash merge) into the corresponding version branch of `testplan` and resolving conflicts.
+- Ensuring the `testplan` branch is synchronized with the latest `main`.
+- Overseeing the Test Plan release.
+
+## In-Depth Understanding
+
+### About `PRs`
+
+A `PR` is a collection of a specific branch (and commits), comments, reviews, and other information, and it is the **smallest management unit** of the Test Plan.
+
+Compared to submitting all features to a single branch, the Test Plan manages features through `PRs`, which offers greater flexibility and efficiency:
+
+- Features can be added or removed between different versions of the Test Plan without cumbersome `revert` operations.
+- Clear feature boundaries and responsibilities are established. Bug fixes are completed within their respective `PRs`, isolating cross-impact and better tracking progress.
+- The `PR` submitter is responsible for resolving conflicts with the latest `main`. The Test Plan lead is responsible for resolving conflicts between `PR` branches. However, since features added to the Test Plan are relatively independent (in other words, if a feature has broad implications, it should be independently included in the Test Plan), conflicts are generally few or simple.
+
+### The `testplan` Branch
+
+The `testplan` branch is a **temporary** branch used for Test Plan releases.
+
+Note:
+
+- **Do not develop based on this branch**. It may change or even be deleted at any time, and there is no guarantee of commit completeness or order.
+- **Do not submit `commits` or `PRs` to this branch**, as they will not be retained.
+- The `testplan` branch is always based on the latest `main` branch (not on a released version), with features added on top.
+
+#### RC Branch
+
+Branch name: `testplan/rc/x.y.z`
+
+Used for RC releases, where `x.y.z` is the target version number. Note that whether it is rc.1 or rc.5, as long as the major version number is `x.y.z`, it is completed in this branch.
+
+Generally, the version number for releases from this branch is named `x.y.z-rc.n`.
+
+#### Beta Branch
+
+Branch name: `testplan/beta/x.y.z`
+
+Used for Beta releases, where `x.y.z` is the target version number. Note that whether it is beta.1 or beta.5, as long as the major version number is `x.y.z`, it is completed in this branch.
+
+Generally, the version number for releases from this branch is named `x.y.z-beta.n`.
+
+### Version Rules
+
+The application version number for the Test Plan is: `x.y.z-CHA.n`, where:
+
+- `x.y.z` is the conventional version number, referred to here as the **target version number**.
+- `CHA` is the channel code (Channel), currently divided into `rc` and `beta`.
+- `n` is the release number, starting from `1`.
+
+Examples of complete version numbers: `1.5.0-rc.3`, `1.5.1-beta.1`, `1.6.0-beta.6`.
+
+The **target version number** of the Test Plan points to the official version number where these features are expected to be added. For example:
+
+- `1.5.0-rc.3` means this is a preview of the `1.5.0` official release (the current latest official release is `1.4.9`, and `1.5.0` has not yet been officially released).
+- `1.5.1-beta.1` means this is a beta version of the `1.5.1` official release (the current latest official release is `1.5.0`, and `1.5.1` has not yet been officially released).

docs/testplan-zh.md

@@ -0,0 +1,99 @@
+# 测试计划
+
+为了给用户提供更稳定的应用体验，并提供更快的迭代速度，Cherry Studio推出“测试计划”。
+
+## 用户指南
+
+测试计划分为RC版通道和Beta版通道吗，区别在于：
+
+- **RC版（预览版）**：RC即Release Candidate，功能已经稳定，BUG较少，接近正式版
+- **Beta版（测试版）**：功能可能随时变化，BUG较多，可以较早体验未来功能
+
+用户可以在软件的`设置`-`关于`中，开启“测试计划”并选择版本通道。请注意“测试计划”的版本无法保证数据的一致性，请使用前一定要备份数据。
+
+用户在测试过程中发现的BUG，欢迎提交issue或通过其他渠道反馈。用户的反馈对我们非常重要。
+
+## 开发者指南
+
+### 参与测试计划
+
+开发者按照[贡献者指南](CONTRIBUTING.zh.md)要求正常提交`PR`（并注意提交target为`main`）。仓库维护者会综合考虑（例如该功能对应用的影响程度，功能的重要性，是否需要更广泛的测试等），决定该`PR`是否应加入测试计划。
+
+若该`PR`加入测试计划，仓库维护者会做如下操作：
+
+- 通知`PR`提交人
+- 设置PR为`draft`状态（避免在测试完成前意外并入`main`）
+- `milestone`设置为具体测试计划版本
+- 修改`PR`标题
+
+`PR`提交人在参与测试计划过程中，应做到：
+
+- 保持`PR`分支与最新`main`同步（即`PR`分支总是应基于最新`main`代码）
+- 保持`PR`分支为无冲突状态
+- 积极响应 comments & reviews，修复bug
+- 开启维护者可以修改`PR`分支的权限，以便维护者能随时修改BUG
+
+加入测试计划并不保证`PR`的最终合并，也有可能由于功能不成熟或测试反馈不佳而搁置
+
+### 测试计划负责人
+
+某个维护者会被指定为某个版本期间（例如`1.5.0-rc`）的测试计划负责人。测试计划负责人的工作为：
+
+- 判断某个`PR`是否符合测试计划要求，并决定是否应合入当期测试计划
+- 修改加入测试计划的`PR`状态，并与`PR`提交人沟通相关事宜
+- 在测试计划发版前，将加入测试计划的`PR`分支逐一合并（采用squash merge）至`testplan`对应版本分支，并解决冲突
+- 保证`testplan`分支与最新`main`同步
+- 负责测试计划发版
+
+## 深入理解
+
+### 关于`PR`
+
+`PR`是特定分支（及commits）、comments、reviews等各种信息的集合，也是测试计划的**最小管理单元**。
+
+相比将所有功能都提交到某个分支，测试计划通过`PR`来管理功能，这可以带来极大的灵活度和效率：
+
+- 测试计划的各个版本间，可以随意增减功能，而无需繁琐的`revert`操作
+- 明确了功能边界和负责人，bug修复在各自`PR`中完成，隔离了交叉影响，也能更好观察进度
+- `PR`提交人负责与最新`main`之间的冲突；测试计划负责人负责各`PR`分支之间的冲突，但因加入测试计划的各功能相对比较独立（话句话说，如果功能牵涉较广，则应独立上测试计划），冲突一般比较少或简单。
+
+### `testplan`分支
+
+`testplan`分支是用于测试计划发版所用的**临时**分支。
+
+注意：
+
+- **请勿基于该分支开发**。该分支随时会变化甚至删除，且并不保证commit的完整和顺序。
+- **请勿向该分支提交`commit`及`PR`**，将不会得到保留
+- `testplan`分支总是基于最新`main`分支（而不是基于已发布版本），在其之上添加功能
+
+#### RC版分支
+
+分支名称：`testplan/rc/x.y.z`
+
+用于RC版的发版，x.y.z为目标版本号，注意无论是rc.1还是rc.5，只要主版本号为x.y.z，都在该分支完成。
+
+一般而言，该分支发版的版本号命名为`x.y.z-rc.n`
+
+#### Beta版分支
+
+分支名称：`testplan/beta/x.y.z`
+
+用于Beta版的发版，x.y.z为目标版本号，注意无论是beta.1还是beta.5，只要主版本号为x.y.z，都在该分支完成。
+
+一般而言，该分支发版的版本号命名为`x.y.z-beta.n`
+
+### 版本规则
+
+测试计划的应用版本号为：`x.y.z-CHA.n`，其中：
+
+- `x.y.z`为一般意义上的版本号，在这里称为**目标版本号**
+- `CHA`为通道号（Channel），现在分为`rc`和`beta`
+- `n`为发版编号，从`1`计数
+
+完整的版本号举例：`1.5.0-rc.3`、`1.5.1-beta.1`、`1.6.0-beta.6`
+
+测试计划的**目标版本号**指向希望添加这些功能的正式版版本号。例如：
+
+- `1.5.0-rc.3`是指，这是`1.5.0`正式版的预览版（当前最新正式版是`1.4.9`，而`1.5.0`正式版还未发布）
+- `1.5.1-beta.1`是指，这是`1.5.1`正式版的测试版（当前最新正式版是`1.5.0`，而`1.5.1`正式版还未发布）

electron-builder.yml

@@ -11,6 +11,11 @@ electronLanguages:
   - en # for macOS
 directories:
   buildResources: build
+
+protocols:
+  - name: Cherry Studio
+    schemes:
+      - cherrystudio
 files:
   - '**/*'
   - '!**/{.vscode,.yarn,.yarn-lock,.github,.cursorrules,.prettierrc}'
@@ -48,7 +53,11 @@ files:
   - '!node_modules/pdf-parse/lib/pdf.js/{v1.9.426,v1.10.88,v2.0.550}'
   - '!node_modules/mammoth/{mammoth.browser.js,mammoth.browser.min.js}'
   - '!node_modules/selection-hook/prebuilds/**/*' # we rebuild .node, don't use prebuilds
-  - '!**/*.{h,iobj,ipdb,tlog,recipe,vcxproj,vcxproj.filters}' # filter .node build files
+  - '!node_modules/pdfjs-dist/web/**/*'
+  - '!node_modules/pdfjs-dist/legacy/web/*'
+  - '!node_modules/selection-hook/node_modules' # we don't need what in the node_modules dir
+  - '!node_modules/selection-hook/src' # we don't need source files
+  - '!**/*.{h,iobj,ipdb,tlog,recipe,vcxproj,vcxproj.filters,Makefile,*.Makefile}' # filter .node build files
 asarUnpack:
   - resources/**
   - '**/*.{metal,exp,lib}'
@@ -90,6 +99,7 @@ linux:
   artifactName: ${productName}-${version}-${arch}.${ext}
   target:
     - target: AppImage
+    - target: deb
   maintainer: electronjs.org
   category: Utility
   desktop:
@@ -107,11 +117,9 @@ afterSign: scripts/notarize.js
 artifactBuildCompleted: scripts/artifact-build-completed.js
 releaseInfo:
   releaseNotes: |
-    划词助手：支持文本选择快捷键、开关快捷键、思考块支持和引用功能
-    复制功能：新增纯文本复制（去除Markdown格式符号）
-    知识库：支持设置向量维度，修复Ollama分数错误和维度编辑问题
-    多语言：增加模型名称多语言提示和翻译源语言手动选择
-    文件管理：修复主题/消息删除时文件未清理问题，优化文件选择流程
-    模型：修复Gemini模型推理预算、Voyage AI嵌入问题和DeepSeek翻译模型更新
-    图像功能：统一图片查看器，支持Base64图片渲染，修复图片预览相关问题
-    UI：实现标签折叠/拖拽排序，修复气泡溢出，增加引文索引显示
+    划词助手：支持 macOS 系统
+    文档处理：增加 MinerU、Doc2x，Mistral 等服务商支持
+    知识库：新的知识库界面，增加扫描版 PDF 支持
+    OCR：macOS 增加系统 OCR 支持
+    服务商：支持一键添加服务商，新增 PH8 大模型开放平台, 支持 PPIO OAuth 登录
+    修复：Linux下数据目录移动问题

electron.vite.config.ts

@@ -1,4 +1,5 @@
 import react from '@vitejs/plugin-react-swc'
+import { CodeInspectorPlugin } from 'code-inspector-plugin'
 import { defineConfig, externalizeDepsPlugin } from 'electron-vite'
 import { resolve } from 'path'
 import { visualizer } from 'rollup-plugin-visualizer'
@@ -19,7 +20,7 @@ export default defineConfig({
     },
     build: {
       rollupOptions: {
-        external: ['@libsql/client', 'bufferutil', 'utf-8-validate'],
+        external: ['@libsql/client', 'bufferutil', 'utf-8-validate', '@cherrystudio/mac-system-ocr'],
         output: {
           // 彻底禁用代码分割 - 返回 null 强制单文件打包
           manualChunks: undefined,
@@ -59,6 +60,14 @@ export default defineConfig({
           ]
         ]
       }),
+      // 只在开发环境下启用 CodeInspectorPlugin
+      ...(process.env.NODE_ENV === 'development'
+        ? [
+            CodeInspectorPlugin({
+              bundler: 'vite'
+            })
+          ]
+        : []),
       ...visualizerPlugin('renderer')
     ],
     resolve: {
@@ -68,12 +77,16 @@ export default defineConfig({
       }
     },
     optimizeDeps: {
-      exclude: ['pyodide']
+      exclude: ['pyodide'],
+      esbuildOptions: {
+        target: 'esnext' // for dev
+      }
     },
     worker: {
       format: 'es'
     },
     build: {
+      target: 'esnext', // for build
       rollupOptions: {
         input: {
           index: resolve(__dirname, 'src/renderer/index.html'),

package.json

@@ -1,6 +1,6 @@
 {
   "name": "CherryStudio",
-  "version": "1.4.2",
+  "version": "1.4.8",
   "private": true,
   "description": "A powerful AI assistant for producer.",
   "main": "./out/main/index.js",
@@ -58,13 +58,17 @@
     "prepare": "husky"
   },
   "dependencies": {
+    "@cherrystudio/pdf-to-img-napi": "^0.0.1",
     "@libsql/client": "0.14.0",
     "@libsql/win32-x64-msvc": "^0.4.7",
     "@strongtz/win32-arm64-msvc": "^0.4.7",
     "jsdom": "26.1.0",
+    "macos-release": "^3.4.0",
+    "node-stream-zip": "^1.15.0",
     "notion-helper": "^1.3.22",
     "os-proxy-config": "^1.1.2",
-    "selection-hook": "^0.9.23",
+    "pdfjs-dist": "4.10.38",
+    "selection-hook": "^1.0.4",
     "turndown": "7.2.0"
   },
   "devDependencies": {
@@ -99,14 +103,16 @@
     "@kangfenmao/keyv-storage": "^0.1.0",
     "@langchain/community": "^0.3.36",
     "@langchain/ollama": "^0.2.1",
+    "@mistralai/mistralai": "^1.6.0",
     "@modelcontextprotocol/sdk": "^1.11.4",
     "@mozilla/readability": "^0.6.0",
     "@notionhq/client": "^2.2.15",
     "@playwright/test": "^1.52.0",
     "@reduxjs/toolkit": "^2.2.5",
-    "@shikijs/markdown-it": "^3.4.2",
+    "@shikijs/markdown-it": "^3.7.0",
     "@swc/plugin-styled-components": "^7.1.5",
     "@tanstack/react-query": "^5.27.0",
+    "@tanstack/react-virtual": "^3.13.12",
     "@testing-library/dom": "^10.4.0",
     "@testing-library/jest-dom": "^6.6.3",
     "@testing-library/react": "^16.3.0",
@@ -123,28 +129,31 @@
     "@types/react-infinite-scroll-component": "^5.0.0",
     "@types/react-window": "^1",
     "@types/tinycolor2": "^1",
-    "@uiw/codemirror-extensions-langs": "^4.23.12",
-    "@uiw/codemirror-themes-all": "^4.23.12",
-    "@uiw/react-codemirror": "^4.23.12",
+    "@types/word-extractor": "^1",
+    "@uiw/codemirror-extensions-langs": "^4.23.14",
+    "@uiw/codemirror-themes-all": "^4.23.14",
+    "@uiw/react-codemirror": "^4.23.14",
     "@vitejs/plugin-react-swc": "^3.9.0",
     "@vitest/browser": "^3.1.4",
     "@vitest/coverage-v8": "^3.1.4",
     "@vitest/ui": "^3.1.4",
     "@vitest/web-worker": "^3.1.4",
     "@xyflow/react": "^12.4.4",
-    "antd": "^5.22.5",
+    "antd": "patch:antd@npm%3A5.24.7#~/.yarn/patches/antd-npm-5.24.7-356a553ae5.patch",
     "archiver": "^7.0.1",
     "async-mutex": "^0.5.0",
     "axios": "^1.7.3",
     "browser-image-compression": "^2.0.2",
+    "code-inspector-plugin": "^0.20.14",
     "color": "^5.0.0",
+    "country-flag-emoji-polyfill": "0.1.8",
     "dayjs": "^1.11.11",
     "dexie": "^4.0.8",
     "dexie-react-hooks": "^1.1.7",
     "diff": "^7.0.0",
     "docx": "^9.0.2",
     "dotenv-cli": "^7.4.2",
-    "electron": "35.4.0",
+    "electron": "35.6.0",
     "electron-builder": "26.0.15",
     "electron-devtools-installer": "^3.2.0",
     "electron-log": "^5.1.5",
@@ -173,10 +182,9 @@
     "lru-cache": "^11.1.0",
     "lucide-react": "^0.487.0",
     "markdown-it": "^14.1.0",
-    "mermaid": "^11.6.0",
+    "mermaid": "^11.7.0",
     "mime": "^4.0.4",
     "motion": "^12.10.5",
-    "node-stream-zip": "^1.15.0",
     "npx-scope-finder": "^1.2.0",
     "officeparser": "^4.1.1",
     "openai": "patch:openai@npm%3A5.1.0#~/.yarn/patches/openai-npm-5.1.0-0e7b3ccb07.patch",
@@ -190,7 +198,7 @@
     "react-hotkeys-hook": "^4.6.1",
     "react-i18next": "^14.1.2",
     "react-infinite-scroll-component": "^6.1.0",
-    "react-markdown": "^9.0.1",
+    "react-markdown": "^10.1.0",
     "react-redux": "^9.1.2",
     "react-router": "6",
     "react-router-dom": "6",
@@ -199,27 +207,31 @@
     "redux": "^5.0.1",
     "redux-persist": "^6.0.0",
     "rehype-katex": "^7.0.1",
-    "rehype-mathjax": "^7.0.0",
+    "rehype-mathjax": "^7.1.0",
     "rehype-raw": "^7.0.0",
-    "remark-cjk-friendly": "^1.1.0",
-    "remark-gfm": "^4.0.0",
+    "remark-cjk-friendly": "^1.2.0",
+    "remark-gfm": "^4.0.1",
     "remark-math": "^6.0.0",
     "remove-markdown": "^0.6.2",
     "rollup-plugin-visualizer": "^5.12.0",
     "sass": "^1.88.0",
-    "shiki": "^3.4.2",
+    "shiki": "^3.7.0",
     "string-width": "^7.2.0",
     "styled-components": "^6.1.11",
     "tar": "^7.4.3",
     "tiny-pinyin": "^1.3.2",
-    "tokenx": "^0.4.1",
+    "tokenx": "^1.1.0",
     "typescript": "^5.6.2",
     "uuid": "^10.0.0",
     "vite": "6.2.6",
     "vitest": "^3.1.4",
     "webdav": "^5.8.0",
+    "word-extractor": "^1.0.4",
     "zipread": "^1.3.3"
   },
+  "optionalDependencies": {
+    "@cherrystudio/mac-system-ocr": "^0.2.2"
+  },
   "resolutions": {
     "pdf-parse@npm:1.1.1": "patch:pdf-parse@npm%3A1.1.1#~/.yarn/patches/pdf-parse-npm-1.1.1-04a6109b2a.patch",
     "@langchain/openai@npm:^0.3.16": "patch:@langchain/openai@npm%3A0.3.16#~/.yarn/patches/@langchain-openai-npm-0.3.16-e525b59526.patch",

packages/shared/IpcChannel.ts

@@ -3,6 +3,8 @@ export enum IpcChannel {
   App_ClearCache = 'app:clear-cache',
   App_SetLaunchOnBoot = 'app:set-launch-on-boot',
   App_SetLanguage = 'app:set-language',
+  App_SetEnableSpellCheck = 'app:set-enable-spell-check',
+  App_SetSpellCheckLanguages = 'app:set-spell-check-languages',
   App_ShowUpdateDialog = 'app:show-update-dialog',
   App_CheckForUpdate = 'app:check-for-update',
   App_Reload = 'app:reload',
@@ -13,20 +15,34 @@ export enum IpcChannel {
   App_SetTrayOnClose = 'app:set-tray-on-close',
   App_SetTheme = 'app:set-theme',
   App_SetAutoUpdate = 'app:set-auto-update',
-  App_SetFeedUrl = 'app:set-feed-url',
+  App_SetTestPlan = 'app:set-test-plan',
+  App_SetTestChannel = 'app:set-test-channel',
   App_HandleZoomFactor = 'app:handle-zoom-factor',
-
+  App_Select = 'app:select',
+  App_HasWritePermission = 'app:has-write-permission',
+  App_Copy = 'app:copy',
+  App_SetStopQuitApp = 'app:set-stop-quit-app',
+  App_SetAppDataPath = 'app:set-app-data-path',
+  App_GetDataPathFromArgs = 'app:get-data-path-from-args',
+  App_FlushAppData = 'app:flush-app-data',
+  App_IsNotEmptyDir = 'app:is-not-empty-dir',
+  App_RelaunchApp = 'app:relaunch-app',
   App_IsBinaryExist = 'app:is-binary-exist',
   App_GetBinaryPath = 'app:get-binary-path',
   App_InstallUvBinary = 'app:install-uv-binary',
   App_InstallBunBinary = 'app:install-bun-binary',
 
+  App_MacIsProcessTrusted = 'app:mac-is-process-trusted',
+  App_MacRequestProcessTrust = 'app:mac-request-process-trust',
+
   App_QuoteToMain = 'app:quote-to-main',
+  App_SetDisableHardwareAcceleration = 'app:set-disable-hardware-acceleration',
 
   Notification_Send = 'notification:send',
   Notification_OnClick = 'notification:on-click',
 
   Webview_SetOpenLinkExternal = 'webview:set-open-link-external',
+  Webview_SetSpellCheckEnabled = 'webview:set-spell-check-enabled',
 
   // Open
   Open_Path = 'open:path',
@@ -59,6 +75,9 @@ export enum IpcChannel {
   Mcp_ServersUpdated = 'mcp:servers-updated',
   Mcp_CheckConnectivity = 'mcp:check-connectivity',
 
+  // Python
+  Python_Execute = 'python:execute',
+
   //copilot
   Copilot_GetAuthMessage = 'copilot:get-auth-message',
   Copilot_GetCopilotToken = 'copilot:get-copilot-token',
@@ -100,6 +119,7 @@ export enum IpcChannel {
   KnowledgeBase_Remove = 'knowledge-base:remove',
   KnowledgeBase_Search = 'knowledge-base:search',
   KnowledgeBase_Rerank = 'knowledge-base:rerank',
+  KnowledgeBase_Check_Quota = 'knowledge-base:check-quota',
 
   //file
   File_Open = 'file:open',
@@ -110,9 +130,10 @@ export enum IpcChannel {
   File_Clear = 'file:clear',
   File_Read = 'file:read',
   File_Delete = 'file:delete',
+  File_DeleteDir = 'file:deleteDir',
   File_Get = 'file:get',
   File_SelectFolder = 'file:selectFolder',
-  File_Create = 'file:create',
+  File_CreateTempFile = 'file:createTempFile',
   File_Write = 'file:write',
   File_WriteWithId = 'file:writeWithId',
   File_SaveImage = 'file:saveImage',
@@ -125,6 +146,12 @@ export enum IpcChannel {
   File_GetPdfInfo = 'file:getPdfInfo',
   Fs_Read = 'fs:read',
 
+  // file service
+  FileService_Upload = 'file-service:upload',
+  FileService_List = 'file-service:list',
+  FileService_Delete = 'file-service:delete',
+  FileService_Retrieve = 'file-service:retrieve',
+
   Export_Word = 'export:word',
 
   Shortcuts_Update = 'shortcuts:update',

packages/shared/config/constant.ts

@@ -1,7 +1,7 @@
 export const imageExts = ['.jpg', '.jpeg', '.png', '.gif', '.bmp', '.webp']
 export const videoExts = ['.mp4', '.avi', '.mov', '.wmv', '.flv', '.mkv']
 export const audioExts = ['.mp3', '.wav', '.ogg', '.flac', '.aac']
-export const documentExts = ['.pdf', '.docx', '.pptx', '.xlsx', '.odt', '.odp', '.ods']
+export const documentExts = ['.pdf', '.doc', '.docx', '.pptx', '.xlsx', '.odt', '.odp', '.ods']
 export const thirdPartyApplicationExts = ['.draftsExport']
 export const bookExts = ['.epub']
 const textExtsByCategory = new Map([
@@ -406,6 +406,16 @@ export const defaultLanguage = 'en-US'
 
 export enum FeedUrl {
   PRODUCTION = 'https://releases.cherry-ai.com',
-  EARLY_ACCESS = 'https://github.com/CherryHQ/cherry-studio/releases/latest/download'
+  GITHUB_LATEST = 'https://github.com/CherryHQ/cherry-studio/releases/latest/download',
+  PRERELEASE_LOWEST = 'https://github.com/CherryHQ/cherry-studio/releases/download/v1.4.0'
 }
-export const defaultTimeout = 5 * 1000 * 60
+
+export enum UpgradeChannel {
+  LATEST = 'latest', // 最新稳定版本
+  RC = 'rc', // 公测版本
+  BETA = 'beta' // 预览版本
+}
+
+export const defaultTimeout = 10 * 1000 * 60
+
+export const occupiedDirs = ['logs', 'Network', 'Partitions/webview/Network']

packages/shared/config/types.ts

@@ -1,6 +1,11 @@
+import { ProcessingStatus } from '@types'
+
 export type LoaderReturn = {
   entriesAdded: number
   uniqueId: string
   uniqueIds: string[]
   loaderType: string
+  status?: ProcessingStatus
+  message?: string
+  messageSource?: 'preprocess' | 'embedding'
 }

resources/model-catalogs/01-ai/yi-large.yaml

@@ -0,0 +1,47 @@
+id: 01-ai/yi-large
+canonical_slug: 01-ai/yi-large
+hugging_face_id: ''
+name: '01.AI: Yi Large'
+type: chat
+created: 1719273600
+description: |-
+  The Yi Large model was designed by 01.AI with the following usecases in mind: knowledge search, data classification, human-like chat bots, and customer service.
+
+  It stands out for its multilingual proficiency, particularly in Spanish, Chinese, Japanese, German, and French.
+
+  Check out the [launch announcement](https://01-ai.github.io/blog/01.ai-yi-large-llm-launch) to learn more.
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Yi
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000003'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - response_format
+  - structured_outputs
+  - logit_bias
+  - logprobs
+  - top_logprobs
+model_provider: 01-ai

resources/model-catalogs/aetherwiing/mn-starcannon-12b.yaml

@@ -0,0 +1,42 @@
+id: aetherwiing/mn-starcannon-12b
+canonical_slug: aetherwiing/mn-starcannon-12b
+hugging_face_id: aetherwiing/MN-12B-Starcannon-v2
+name: 'Aetherwiing: Starcannon 12B'
+type: chat
+created: 1723507200
+description: |-
+  Starcannon 12B v2 is a creative roleplay and story writing model, based on Mistral Nemo, using [nothingiisreal/mn-celeste-12b](/nothingiisreal/mn-celeste-12b) as a base, with [intervitens/mini-magnum-12b-v1.1](https://huggingface.co/intervitens/mini-magnum-12b-v1.1) merged in using the [TIES](https://arxiv.org/abs/2306.01708) method.
+
+  Although more similar to Magnum overall, the model remains very creative, with a pleasant writing style. It is recommended for people wanting more variety than Magnum, and yet more verbose prose than Celeste.
+context_length: 16384
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Mistral
+  instruct_type: chatml
+pricing:
+  prompt: '0.0000008'
+  completion: '0.0000012'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+model_provider: aetherwiing

resources/model-catalogs/ai21/jamba-1.6-large.yaml

@@ -0,0 +1,38 @@
+id: ai21/jamba-1.6-large
+canonical_slug: ai21/jamba-1.6-large
+hugging_face_id: ai21labs/AI21-Jamba-Large-1.6
+name: 'AI21: Jamba 1.6 Large'
+type: chat
+created: 1741905173
+description: |-
+  AI21 Jamba Large 1.6 is a high-performance hybrid foundation model combining State Space Models (Mamba) with Transformer attention mechanisms. Developed by AI21, it excels in extremely long-context handling (256K tokens), demonstrates superior inference efficiency (up to 2.5x faster than comparable models), and supports structured JSON output and tool-use capabilities. It has 94 billion active parameters (398 billion total), optimized quantization support (ExpertsInt8), and multilingual proficiency in languages such as English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, and Hebrew.
+
+  Usage of this model is subject to the [Jamba Open Model License](https://www.ai21.com/licenses/jamba-open-model-license).
+context_length: 256000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.000002'
+  completion: '0.000008'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+model_provider: ai21

resources/model-catalogs/ai21/jamba-1.6-mini.yaml

@@ -0,0 +1,38 @@
+id: ai21/jamba-1.6-mini
+canonical_slug: ai21/jamba-1.6-mini
+hugging_face_id: ai21labs/AI21-Jamba-Mini-1.6
+name: 'AI21: Jamba Mini 1.6'
+type: chat
+created: 1741905171
+description: |-
+  AI21 Jamba Mini 1.6 is a hybrid foundation model combining State Space Models (Mamba) with Transformer attention mechanisms. With 12 billion active parameters (52 billion total), this model excels in extremely long-context tasks (up to 256K tokens) and achieves superior inference efficiency, outperforming comparable open models on tasks such as retrieval-augmented generation (RAG) and grounded question answering. Jamba Mini 1.6 supports multilingual tasks across English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, and Hebrew, along with structured JSON output and tool-use capabilities.
+
+  Usage of this model is subject to the [Jamba Open Model License](https://www.ai21.com/licenses/jamba-open-model-license).
+context_length: 256000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000002'
+  completion: '0.0000004'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+model_provider: ai21

resources/model-catalogs/aion-labs/aion-1.0-mini.yaml

@@ -0,0 +1,34 @@
+id: aion-labs/aion-1.0-mini
+canonical_slug: aion-labs/aion-1.0-mini
+hugging_face_id: FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview
+name: 'AionLabs: Aion-1.0-Mini'
+type: chat
+created: 1738697107
+description: Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant of a FuseAI model that outperforms R1-Distill-Qwen-32B and R1-Distill-Llama-70B, with benchmark results available on its [Hugging Face page](https://huggingface.co/FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview), independently replicated for verification.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000007'
+  completion: '0.0000014'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+model_provider: aion-labs

resources/model-catalogs/aion-labs/aion-1.0.yaml

@@ -0,0 +1,34 @@
+id: aion-labs/aion-1.0
+canonical_slug: aion-labs/aion-1.0
+hugging_face_id: ''
+name: 'AionLabs: Aion-1.0'
+type: chat
+created: 1738697557
+description: Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree of Thoughts (ToT) and Mixture of Experts (MoE). It is Aion Lab's most powerful reasoning model.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.000004'
+  completion: '0.000008'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+model_provider: aion-labs

resources/model-catalogs/aion-labs/aion-rp-llama-3.1-8b.yaml

@@ -0,0 +1,32 @@
+id: aion-labs/aion-rp-llama-3.1-8b
+canonical_slug: aion-labs/aion-rp-llama-3.1-8b
+hugging_face_id: ''
+name: 'AionLabs: Aion-RP 1.0 (8B)'
+type: chat
+created: 1738696718
+description: Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model rather than an instruct model, designed to produce more natural and varied writing.
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000002'
+  completion: '0.0000002'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+model_provider: aion-labs

resources/model-catalogs/alfredpros/codellama-7b-instruct-solidity.yaml

@@ -0,0 +1,39 @@
+id: alfredpros/codellama-7b-instruct-solidity
+canonical_slug: alfredpros/codellama-7b-instruct-solidity
+hugging_face_id: AlfredPros/CodeLlama-7b-Instruct-Solidity
+name: 'AlfredPros: CodeLLaMa 7B Instruct Solidity'
+type: chat
+created: 1744641874
+description: A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.
+context_length: 4096
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: alpaca
+pricing:
+  prompt: '0.0000008'
+  completion: '0.0000012'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+model_provider: alfredpros

resources/model-catalogs/all-hands/openhands-lm-32b-v0.1.yaml

@@ -0,0 +1,44 @@
+id: all-hands/openhands-lm-32b-v0.1
+canonical_slug: all-hands/openhands-lm-32b-v0.1
+hugging_face_id: all-hands/openhands-lm-32b-v0.1
+name: OpenHands LM 32B V0.1
+type: chat
+created: 1743613013
+description: |-
+  OpenHands LM v0.1 is a 32B open-source coding model fine-tuned from Qwen2.5-Coder-32B-Instruct using reinforcement learning techniques outlined in SWE-Gym. It is optimized for autonomous software development agents and achieves strong performance on SWE-Bench Verified, with a 37.2% resolve rate. The model supports a 128K token context window, making it well-suited for long-horizon code reasoning and large codebase tasks.
+
+  OpenHands LM is designed for local deployment and runs on consumer-grade GPUs such as a single 3090. It enables fully offline agent workflows without dependency on proprietary APIs. This release is intended as a research preview, and future updates aim to improve generalizability, reduce repetition, and offer smaller variants.
+context_length: 16384
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000026'
+  completion: '0.0000034'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+model_provider: all-hands

resources/model-catalogs/alpindale/goliath-120b.yaml

@@ -0,0 +1,48 @@
+id: alpindale/goliath-120b
+canonical_slug: alpindale/goliath-120b
+hugging_face_id: alpindale/goliath-120b
+name: Goliath 120B
+type: chat
+created: 1699574400
+description: |-
+  A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale.
+
+  Credits to
+  - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge the model - [mergekit](https://github.com/cg123/mergekit).
+  - [@Undi95](https://huggingface.co/Undi95) for helping with the merge ratios.
+
+  #merge
+context_length: 6144
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Llama2
+  instruct_type: airoboros
+pricing:
+  prompt: '0.00001'
+  completion: '0.0000125'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - logit_bias
+  - top_k
+  - min_p
+  - seed
+  - top_a
+model_provider: alpindale

resources/model-catalogs/alpindale/magnum-72b.yaml

@@ -0,0 +1,42 @@
+id: alpindale/magnum-72b
+canonical_slug: alpindale/magnum-72b
+hugging_face_id: alpindale/magnum-72b-v1
+name: Magnum 72B
+type: chat
+created: 1720656000
+description: |-
+  From the maker of [Goliath](https://openrouter.ai/models/alpindale/goliath-120b), Magnum 72B is the first in a new family of models designed to achieve the prose quality of the Claude 3 models, notably Opus & Sonnet.
+
+  The model is based on [Qwen2 72B](https://openrouter.ai/models/qwen/qwen-2-72b-instruct) and trained with 55 million tokens of highly curated roleplay (RP) data.
+context_length: 16384
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Qwen
+  instruct_type: chatml
+pricing:
+  prompt: '0.000004'
+  completion: '0.000006'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+model_provider: alpindale

resources/model-catalogs/amazon/nova-lite-v1.yaml

@@ -0,0 +1,39 @@
+id: amazon/nova-lite-v1
+canonical_slug: amazon/nova-lite-v1
+hugging_face_id: ''
+name: 'Amazon: Nova Lite 1.0'
+type: chat
+created: 1733437363
+description: |-
+  Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.
+
+  With an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.
+context_length: 300000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Nova
+  instruct_type: null
+pricing:
+  prompt: '0.00000006'
+  completion: '0.00000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0.00009'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: amazon

resources/model-catalogs/amazon/nova-micro-v1.yaml

@@ -0,0 +1,35 @@
+id: amazon/nova-micro-v1
+canonical_slug: amazon/nova-micro-v1
+hugging_face_id: ''
+name: 'Amazon: Nova Micro 1.0'
+type: chat
+created: 1733437237
+description: Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has  simple mathematical reasoning and coding abilities.
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Nova
+  instruct_type: null
+pricing:
+  prompt: '0.000000035'
+  completion: '0.00000014'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: amazon

resources/model-catalogs/amazon/nova-pro-v1.yaml

@@ -0,0 +1,41 @@
+id: amazon/nova-pro-v1
+canonical_slug: amazon/nova-pro-v1
+hugging_face_id: ''
+name: 'Amazon: Nova Pro 1.0'
+type: chat
+created: 1733436303
+description: |-
+  Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).
+
+  Amazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents.
+
+  **NOTE**: Video input is not supported at this time.
+context_length: 300000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Nova
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.0000032'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0.0012'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: amazon

resources/model-catalogs/anthracite-org/magnum-v2-72b.yaml

@@ -0,0 +1,43 @@
+id: anthracite-org/magnum-v2-72b
+canonical_slug: anthracite-org/magnum-v2-72b
+hugging_face_id: anthracite-org/magnum-v2-72b
+name: Magnum v2 72B
+type: chat
+created: 1727654400
+description: |-
+  From the maker of [Goliath](https://openrouter.ai/models/alpindale/goliath-120b), Magnum 72B is the seventh in a family of models designed to achieve the prose quality of the Claude 3 models, notably Opus & Sonnet.
+
+  The model is based on [Qwen2 72B](https://openrouter.ai/models/qwen/qwen-2-72b-instruct) and trained with 55 million tokens of highly curated roleplay (RP) data.
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Qwen
+  instruct_type: chatml
+pricing:
+  prompt: '0.000003'
+  completion: '0.000003'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - logit_bias
+  - top_k
+  - min_p
+  - seed
+model_provider: anthracite-org

resources/model-catalogs/anthracite-org/magnum-v4-72b.yaml

@@ -0,0 +1,44 @@
+id: anthracite-org/magnum-v4-72b
+canonical_slug: anthracite-org/magnum-v4-72b
+hugging_face_id: anthracite-org/magnum-v4-72b
+name: Magnum v4 72B
+type: chat
+created: 1729555200
+description: |-
+  This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).
+
+  The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).
+context_length: 16384
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Qwen
+  instruct_type: chatml
+pricing:
+  prompt: '0.0000025'
+  completion: '0.000003'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+  - logit_bias
+  - top_a
+model_provider: anthracite-org

resources/model-catalogs/anthropic/claude-2-beta.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2:beta
+canonical_slug: anthropic/claude-2
+hugging_face_id: ''
+name: 'Anthropic: Claude v2 (self-moderated)'
+type: chat
+created: 1700611200
+description: 'Claude 2 delivers advancements in key capabilities for enterprises—including an industry-leading 200K token context window, significant reductions in rates of model hallucination, system prompts and a new beta feature: tool use.'
+context_length: 200000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.0-beta.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2.0:beta
+canonical_slug: anthropic/claude-2.0
+hugging_face_id: ''
+name: 'Anthropic: Claude v2.0 (self-moderated)'
+type: chat
+created: 1690502400
+description: Anthropic's flagship model. Superior performance on tasks that require complex reasoning. Supports hundreds of pages of text.
+context_length: 100000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.0.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2.0
+canonical_slug: anthropic/claude-2.0
+hugging_face_id: ''
+name: 'Anthropic: Claude v2.0'
+type: chat
+created: 1690502400
+description: Anthropic's flagship model. Superior performance on tasks that require complex reasoning. Supports hundreds of pages of text.
+context_length: 100000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.1-beta.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2.1:beta
+canonical_slug: anthropic/claude-2.1
+hugging_face_id: ''
+name: 'Anthropic: Claude v2.1 (self-moderated)'
+type: chat
+created: 1700611200
+description: 'Claude 2 delivers advancements in key capabilities for enterprises—including an industry-leading 200K token context window, significant reductions in rates of model hallucination, system prompts and a new beta feature: tool use.'
+context_length: 200000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.1.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2.1
+canonical_slug: anthropic/claude-2.1
+hugging_face_id: ''
+name: 'Anthropic: Claude v2.1'
+type: chat
+created: 1700611200
+description: 'Claude 2 delivers advancements in key capabilities for enterprises—including an industry-leading 200K token context window, significant reductions in rates of model hallucination, system prompts and a new beta feature: tool use.'
+context_length: 200000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2
+canonical_slug: anthropic/claude-2
+hugging_face_id: ''
+name: 'Anthropic: Claude v2'
+type: chat
+created: 1700611200
+description: 'Claude 2 delivers advancements in key capabilities for enterprises—including an industry-leading 200K token context window, significant reductions in rates of model hallucination, system prompts and a new beta feature: tool use.'
+context_length: 200000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-haiku-beta.yaml

@@ -0,0 +1,43 @@
+id: anthropic/claude-3-haiku:beta
+canonical_slug: anthropic/claude-3-haiku
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Haiku (self-moderated)'
+type: chat
+created: 1710288000
+description: |-
+  Claude 3 Haiku is Anthropic's fastest and most compact model for
+  near-instant responsiveness. Quick and accurate targeted performance.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.00000025'
+  completion: '0.00000125'
+  input_cache_read: '0.00000003'
+  input_cache_write: '0.0000003'
+  request: '0'
+  image: '0.0004'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-haiku.yaml

@@ -0,0 +1,43 @@
+id: anthropic/claude-3-haiku
+canonical_slug: anthropic/claude-3-haiku
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Haiku'
+type: chat
+created: 1710288000
+description: |-
+  Claude 3 Haiku is Anthropic's fastest and most compact model for
+  near-instant responsiveness. Quick and accurate targeted performance.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.00000025'
+  completion: '0.00000125'
+  input_cache_read: '0.00000003'
+  input_cache_write: '0.0000003'
+  request: '0'
+  image: '0.0004'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-opus-beta.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3-opus:beta
+canonical_slug: anthropic/claude-3-opus
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Opus (self-moderated)'
+type: chat
+created: 1709596800
+description: |-
+  Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000015'
+  completion: '0.000075'
+  input_cache_read: '0.0000015'
+  input_cache_write: '0.00001875'
+  request: '0'
+  image: '0.024'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-opus.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3-opus
+canonical_slug: anthropic/claude-3-opus
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Opus'
+type: chat
+created: 1709596800
+description: |-
+  Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000015'
+  completion: '0.000075'
+  input_cache_read: '0.0000015'
+  input_cache_write: '0.00001875'
+  request: '0'
+  image: '0.024'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-sonnet-beta.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3-sonnet:beta
+canonical_slug: anthropic/claude-3-sonnet
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Sonnet (self-moderated)'
+type: chat
+created: 1709596800
+description: |-
+  Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-sonnet.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3-sonnet
+canonical_slug: anthropic/claude-3-sonnet
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Sonnet'
+type: chat
+created: 1709596800
+description: |-
+  Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-haiku-20241022-beta.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3.5-haiku-20241022:beta
+canonical_slug: anthropic/claude-3-5-haiku-20241022
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Haiku (2024-10-22) (self-moderated)'
+type: chat
+created: 1730678400
+description: |-
+  Claude 3.5 Haiku features enhancements across all skill sets including coding, tool use, and reasoning. As the fastest model in the Anthropic lineup, it offers rapid response times suitable for applications that require high interactivity and low latency, such as user-facing chatbots and on-the-fly code completions. It also excels in specialized tasks like data extraction and real-time content moderation, making it a versatile tool for a broad range of industries.
+
+  It does not support image inputs.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/3-5-models-and-computer-use)
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.000004'
+  input_cache_read: '0.00000008'
+  input_cache_write: '0.000001'
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-haiku-20241022.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3.5-haiku-20241022
+canonical_slug: anthropic/claude-3-5-haiku-20241022
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Haiku (2024-10-22)'
+type: chat
+created: 1730678400
+description: |-
+  Claude 3.5 Haiku features enhancements across all skill sets including coding, tool use, and reasoning. As the fastest model in the Anthropic lineup, it offers rapid response times suitable for applications that require high interactivity and low latency, such as user-facing chatbots and on-the-fly code completions. It also excels in specialized tasks like data extraction and real-time content moderation, making it a versatile tool for a broad range of industries.
+
+  It does not support image inputs.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/3-5-models-and-computer-use)
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.000004'
+  input_cache_read: '0.00000008'
+  input_cache_write: '0.000001'
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-haiku-beta.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3.5-haiku:beta
+canonical_slug: anthropic/claude-3-5-haiku
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Haiku (self-moderated)'
+type: chat
+created: 1730678400
+description: |-
+  Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.
+
+  This makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.
+
+  This model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.000004'
+  input_cache_read: '0.00000008'
+  input_cache_write: '0.000001'
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-haiku.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3.5-haiku
+canonical_slug: anthropic/claude-3-5-haiku
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Haiku'
+type: chat
+created: 1730678400
+description: |-
+  Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.
+
+  This makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.
+
+  This model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.000004'
+  input_cache_read: '0.00000008'
+  input_cache_write: '0.000001'
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-sonnet-20240620-beta.yaml

@@ -0,0 +1,47 @@
+id: anthropic/claude-3.5-sonnet-20240620:beta
+canonical_slug: anthropic/claude-3.5-sonnet-20240620
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Sonnet (2024-06-20) (self-moderated)'
+type: chat
+created: 1718841600
+description: |-
+  Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:
+
+  - Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting
+  - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights
+  - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone
+  - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)
+
+  For the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet).
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-sonnet-20240620.yaml

@@ -0,0 +1,47 @@
+id: anthropic/claude-3.5-sonnet-20240620
+canonical_slug: anthropic/claude-3.5-sonnet-20240620
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Sonnet (2024-06-20)'
+type: chat
+created: 1718841600
+description: |-
+  Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:
+
+  - Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting
+  - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights
+  - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone
+  - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)
+
+  For the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet).
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-sonnet-beta.yaml

@@ -0,0 +1,45 @@
+id: anthropic/claude-3.5-sonnet:beta
+canonical_slug: anthropic/claude-3.5-sonnet
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Sonnet (self-moderated)'
+type: chat
+created: 1729555200
+description: |-
+  New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:
+
+  - Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding
+  - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights
+  - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone
+  - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-sonnet.yaml

@@ -0,0 +1,45 @@
+id: anthropic/claude-3.5-sonnet
+canonical_slug: anthropic/claude-3.5-sonnet
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Sonnet'
+type: chat
+created: 1729555200
+description: |-
+  New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:
+
+  - Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding
+  - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights
+  - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone
+  - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.7-sonnet-beta.yaml

@@ -0,0 +1,37 @@
+id: anthropic/claude-3.7-sonnet:beta
+canonical_slug: anthropic/claude-3-7-sonnet-20250219
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.7 Sonnet (self-moderated)'
+type: chat
+created: 1740422110
+description: "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)"
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.7-sonnet-thinking.yaml

@@ -0,0 +1,37 @@
+id: anthropic/claude-3.7-sonnet:thinking
+canonical_slug: anthropic/claude-3-7-sonnet-20250219
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.7 Sonnet (thinking)'
+type: chat
+created: 1740422110
+description: "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)"
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.7-sonnet.yaml

@@ -0,0 +1,39 @@
+id: anthropic/claude-3.7-sonnet
+canonical_slug: anthropic/claude-3-7-sonnet-20250219
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.7 Sonnet'
+type: chat
+created: 1740422110
+description: "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)"
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-opus-4.yaml

@@ -0,0 +1,39 @@
+id: anthropic/claude-opus-4
+canonical_slug: anthropic/claude-4-opus-20250522
+hugging_face_id: ''
+name: 'Anthropic: Claude Opus 4'
+type: chat
+created: 1747931245
+description: "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation. \n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)"
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - image
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000015'
+  completion: '0.000075'
+  input_cache_read: '0.0000015'
+  input_cache_write: '0.00001875'
+  request: '0'
+  image: '0.024'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-sonnet-4.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-sonnet-4
+canonical_slug: anthropic/claude-4-sonnet-20250522
+hugging_face_id: ''
+name: 'Anthropic: Claude Sonnet 4'
+type: chat
+created: 1747930371
+description: |-
+  Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.
+
+  Read more at the [blog post here](https://www.anthropic.com/news/claude-4)
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - image
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+model_provider: anthropic

resources/model-catalogs/arcee-ai/arcee-blitz.yaml

@@ -0,0 +1,40 @@
+id: arcee-ai/arcee-blitz
+canonical_slug: arcee-ai/arcee-blitz
+hugging_face_id: arcee-ai/arcee-blitz
+name: 'Arcee AI: Arcee Blitz'
+type: chat
+created: 1746470100
+description: 'Arcee Blitz is a 24 B‑parameter dense model distilled from DeepSeek and built on Mistral architecture for "everyday" chat. The distillation‑plus‑refinement pipeline trims compute while keeping DeepSeek‑style reasoning, so Blitz punches above its weight on MMLU, GSM‑8K and BBH compared with other mid‑size open models. With a default 128 k context window and competitive throughput, it serves as a cost‑efficient workhorse for summarization, brainstorming and light code help. Internally, Arcee uses Blitz as the default writer in Conductor pipelines when the heavier Virtuoso line is not required. Users therefore get near‑70 B quality at ~⅓ the latency and price. '
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.00000045'
+  completion: '0.00000075'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/caller-large.yaml

@@ -0,0 +1,42 @@
+id: arcee-ai/caller-large
+canonical_slug: arcee-ai/caller-large
+hugging_face_id: ''
+name: 'Arcee AI: Caller Large'
+type: chat
+created: 1746487869
+description: 'Caller Large is Arcee''s specialist "function‑calling" SLM built to orchestrate external tools and APIs. Instead of maximizing next‑token accuracy, training focuses on structured JSON outputs, parameter extraction and multi‑step tool chains, making Caller a natural choice for retrieval‑augmented generation, robotic process automation or data‑pull chatbots. It incorporates a routing head that decides when (and how) to invoke a tool versus answering directly, reducing hallucinated calls. The model is already the backbone of Arcee Conductor''s auto‑tool mode, where it parses user intent, emits clean function signatures and hands control back once the tool response is ready. Developers thus gain an OpenAI‑style function‑calling UX without handing requests to a frontier‑scale model. '
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.00000055'
+  completion: '0.00000085'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/coder-large.yaml

@@ -0,0 +1,40 @@
+id: arcee-ai/coder-large
+canonical_slug: arcee-ai/coder-large
+hugging_face_id: ''
+name: 'Arcee AI: Coder Large'
+type: chat
+created: 1746478663
+description: 'Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file refactoring or long diff review in a single call, and understands 30‑plus programming languages with special attention to TypeScript, Go and Terraform. Internal benchmarks show 5–8 pt gains over CodeLlama‑34 B‑Python on HumanEval and competitive BugFix scores thanks to a reinforcement pass that rewards compilable output. The model emits structured explanations alongside code blocks by default, making it suitable for educational tooling as well as production copilot scenarios. Cost‑wise, Together AI prices it well below proprietary incumbents, so teams can scale interactive coding without runaway spend. '
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000005'
+  completion: '0.0000008'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/maestro-reasoning.yaml

@@ -0,0 +1,40 @@
+id: arcee-ai/maestro-reasoning
+canonical_slug: arcee-ai/maestro-reasoning
+hugging_face_id: ''
+name: 'Arcee AI: Maestro Reasoning'
+type: chat
+created: 1746481269
+description: 'Maestro Reasoning is Arcee''s flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B preview, the production 32 B release widens the context window to 128 k tokens and doubles pass‑rate on MATH and GSM‑8K, while also lifting code completion accuracy. Its instruction style encourages structured "thought → answer" traces that can be parsed or hidden according to user preference. That transparency pairs well with audit‑focused industries like finance or healthcare where seeing the reasoning path matters. In Arcee Conductor, Maestro is automatically selected for complex, multi‑constraint queries that smaller SLMs bounce. '
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000009'
+  completion: '0.0000033'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/spotlight.yaml

@@ -0,0 +1,41 @@
+id: arcee-ai/spotlight
+canonical_slug: arcee-ai/spotlight
+hugging_face_id: ''
+name: 'Arcee AI: Spotlight'
+type: chat
+created: 1746481552
+description: 'Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal conversations that combine lengthy documents with one or more images. Training emphasized fast inference on consumer GPUs while retaining strong captioning, visual‐question‑answering, and diagram‑analysis accuracy. As a result, Spotlight slots neatly into agent workflows where screenshots, charts or UI mock‑ups need to be interpreted on the fly. Early benchmarks show it matching or out‑scoring larger VLMs such as LLaVA‑1.6 13 B on popular VQA and POPE alignment tests. '
+context_length: 131072
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - image
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.00000018'
+  completion: '0.00000018'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/virtuoso-large.yaml

@@ -0,0 +1,42 @@
+id: arcee-ai/virtuoso-large
+canonical_slug: arcee-ai/virtuoso-large
+hugging_face_id: ''
+name: 'Arcee AI: Virtuoso Large'
+type: chat
+created: 1746478885
+description: Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k context inherited from Qwen 2.5, letting it ingest books, codebases or financial filings wholesale. Training blended DeepSeek R1 distillation, multi‑epoch supervised fine‑tuning and a final DPO/RLHF alignment stage, yielding strong performance on BIG‑Bench‑Hard, GSM‑8K and long‑context Needle‑In‑Haystack tests. Enterprises use Virtuoso‑Large as the "fallback" brain in Conductor pipelines when other SLMs flag low confidence. Despite its size, aggressive KV‑cache optimizations keep first‑token latency in the low‑second range on 8× H100 nodes, making it a practical production‑grade powerhouse.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.00000075'
+  completion: '0.0000012'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/virtuoso-medium-v2.yaml

@@ -0,0 +1,42 @@
+id: arcee-ai/virtuoso-medium-v2
+canonical_slug: arcee-ai/virtuoso-medium-v2
+hugging_face_id: arcee-ai/Virtuoso-Medium-v2
+name: 'Arcee AI: Virtuoso Medium V2'
+type: chat
+created: 1746478434
+description: 'Virtuoso‑Medium‑v2 is a 32 B model distilled from DeepSeek‑v3 logits and merged back onto a Qwen 2.5 backbone, yielding a sharper, more factual successor to the original Virtuoso Medium. The team harvested ~1.1 B logit tokens and applied "fusion‑merging" plus DPO alignment, which pushed scores past Arcee‑Nova 2024 and many 40 B‑plus peers on MMLU‑Pro, MATH and HumanEval. With a 128 k context and aggressive quantization options (from BF16 down to 4‑bit GGUF), it balances capability with deployability on single‑GPU nodes. Typical use cases include enterprise chat assistants, technical writing aids and medium‑complexity code drafting where Virtuoso‑Large would be overkill. '
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000005'
+  completion: '0.0000008'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/bytedance/doubao-embedding-large-text-240715.yaml

@@ -0,0 +1,24 @@
+id: bytedance/doubao-embedding-text-240715
+canonical_slug: bytedance/doubao-embedding-text-240715
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding Text (240715)'
+description: |-
+  Doubao Embedding Large 是字节跳动语义向量化模型的最新升级版，模型以豆包语言模型为基座，具备强大的语言理解能力；主要面向向量检索的使用场景，支持中、英双语。
+context_length: 4000
+dimensions:
+  - 512
+  - 1024
+  - 2048
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.7'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-large-text-240915.yaml

@@ -0,0 +1,25 @@
+id: bytedance/doubao-embedding-large-text-240915
+canonical_slug: bytedance/doubao-embedding-large-text-240915
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding Large Text (240915)'
+description: |-
+  Doubao Embedding Large 是字节跳动语义向量化模型的最新升级版，模型以豆包语言模型为基座，具备强大的语言理解能力；主要面向向量检索的使用场景，支持中、英双语。
+context_length: 4000
+dimensions:
+  - 512
+  - 1024
+  - 2048
+  - 4096
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.7'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-text-240515.yaml

@@ -0,0 +1,24 @@
+id: bytedance/doubao-embedding-text-240715
+canonical_slug: bytedance/doubao-embedding-text-240715
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding'
+description: |-
+  由字节跳动研发的语义向量化模型，主要面向向量检索的使用场景，支持中、英双语，最长 4K 上下文长度。向量维度 2048 维，支持 512、1024 降维使用。
+context_length: 4000
+dimensions:
+  - 512
+  - 1024
+  - 2048
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.5'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-text-240715.yaml

@@ -0,0 +1,25 @@
+id: bytedance/doubao-embedding-text-240715
+canonical_slug: bytedance/doubao-embedding-text-240715
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding'
+description: |-
+  由字节跳动研发的语义向量化模型，主要面向向量检索的使用场景，支持中、英双语，最长 4K 上下文长度。向量维度 2048 维，支持 512、1024 降维使用。
+context_length: 4000
+dimensions:
+  - 512
+  - 1024
+  - 2048
+  - 2560
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.5'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-vision-241215.yaml

@@ -0,0 +1,24 @@
+id: bytedance/doubao-embedding-vision-241215
+canonical_slug: bytedance/doubao-embedding-vision-241215
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding Vision'
+description: |-
+  Doubao-embedding-vision，全新升级图文多模态向量化模型，主要面向图文多模向量检索的使用场景，支持图片输入及中、英双语文本输入，最长 8K 上下文长度。
+context_length: 8000
+dimensions:
+  - 3072
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.7'
+  prompt_image: '1.8'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-vision-250328.yaml

@@ -0,0 +1,25 @@
+id: bytedance/doubao-embedding-vision-250328
+canonical_slug: bytedance/doubao-embedding-vision-250328
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding Vision'
+description: |-
+  Doubao-embedding-vision，全新升级图文多模态向量化模型，主要面向图文多模向量检索的使用场景，支持图片输入及中、英双语文本输入，最长 8K 上下文长度。
+context_length: 8000
+dimensions:
+  - 1024
+  - 2048
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.7'
+  prompt_image: '1.8'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-seed-1.6-flash.yaml

@@ -0,0 +1,41 @@
+id: bytedance/doubao-seed-1.6-flash
+canonical_slug: bytedance/doubao-seed-1.6-flash
+type: chat
+hugging_face_id: ''
+name: 'ByteDance: Doubao Seed 1.6 Flash'
+created: 1738402289
+description: 有极致推理速度的多模态深度思考模型；同时支持文本和视觉理解。文本理解能力超过上一代 Lite 系列模型，视觉理解比肩友商 Pro 系列模型。
+context_length: 256000
+architecture:
+  modality: text+image+vedio->text
+  input_modalities:
+    - text
+    - image
+    - video
+  output_modalities:
+    - text
+  tokenizer: Doubao
+  instruct_type: null
+pricing:
+  prompt: '0.15'
+  completion: '1.5'
+  input_cache_read: '0.03'
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  currency: CNY
+  unit: 1000000
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+  - structured_outputs
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-seed-1.6-thinking.yaml

@@ -0,0 +1,41 @@
+id: bytedance/doubao-seed-1.6-thinking
+canonical_slug: bytedance/doubao-seed-1.6-thinking
+type: chat
+hugging_face_id: ''
+name: 'ByteDance: Doubao Seed 1.6 Thinking'
+created: 1738402289
+description: 在思考能力上进行了大幅强化， 对比 doubao 1.5 代深度理解模型，在编程、数学、逻辑推理等基础能力上进一步提升， 支持视觉理解。
+context_length: 256000
+architecture:
+  modality: text+image+vedio->text
+  input_modalities:
+    - text
+    - image
+    - video
+  output_modalities:
+    - text
+  tokenizer: Doubao
+  instruct_type: null
+pricing:
+  prompt: '0.8'
+  completion: '8.0'
+  input_cache_read: '0.16'
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  currency: CNY
+  unit: 1000000
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+  - structured_outputs
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-seed-1.6.yaml

@@ -0,0 +1,41 @@
+id: bytedance/doubao-seed-1.6
+canonical_slug: bytedance/doubao-seed-1.6
+type: chat
+hugging_face_id: ''
+name: 'ByteDance: Doubao Seed 1.6'
+created: 1738402289
+description: 全新多模态深度思考模型，同时支持 thinking、non-thinking、auto三种思考模式。其中 non-thinking 模型对比 doubao-1.5-pro-32k-250115 模型大幅提升。
+context_length: 256000
+architecture:
+  modality: text+image+vedio->text
+  input_modalities:
+    - text
+    - image
+    - video
+  output_modalities:
+    - text
+  tokenizer: Doubao
+  instruct_type: null
+pricing:
+  prompt: '0.8'
+  completion: '8.0'
+  input_cache_read: '0.16'
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  currency: CNY
+  unit: 1000000
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+  - structured_outputs
+model_provider: bytedance

resources/model-catalogs/cognitivecomputations/dolphin-mixtral-8x22b.yaml

@@ -0,0 +1,47 @@
+id: cognitivecomputations/dolphin-mixtral-8x22b
+canonical_slug: cognitivecomputations/dolphin-mixtral-8x22b
+hugging_face_id: cognitivecomputations/dolphin-2.9.2-mixtral-8x22b
+name: "Dolphin 2.9.2 Mixtral 8x22B \U0001F42C"
+type: chat
+created: 1717804800
+description: |-
+  Dolphin 2.9 is designed for instruction following, conversational, and coding. This model is a finetune of [Mixtral 8x22B Instruct](/models/mistralai/mixtral-8x22b-instruct). It features a 64k context length and was fine-tuned with a 16k sequence length using ChatML templates.
+
+  This model is a successor to [Dolphin Mixtral 8x7B](/models/cognitivecomputations/dolphin-mixtral-8x7b).
+
+  The model is uncensored and is stripped of alignment and bias. It requires an external alignment layer for ethical use. Users are cautioned to use this highly compliant model responsibly, as detailed in a blog post about uncensored models at [erichartford.com/uncensored-models](https://erichartford.com/uncensored-models).
+
+  #moe #uncensored
+context_length: 16000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Mistral
+  instruct_type: chatml
+pricing:
+  prompt: '0.0000009'
+  completion: '0.0000009'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - seed
+  - top_k
+  - min_p
+  - repetition_penalty
+  - logit_bias
+model_provider: cognitivecomputations

resources/model-catalogs/cohere/command-a.yaml

@@ -0,0 +1,41 @@
+id: cohere/command-a
+canonical_slug: cohere/command-a-03-2025
+hugging_face_id: CohereForAI/c4ai-command-a-03-2025
+name: 'Cohere: Command A'
+type: chat
+created: 1741894342
+description: |-
+  Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.
+  Compared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.
+context_length: 256000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000025'
+  completion: '0.00001'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - seed
+  - response_format
+  - structured_outputs
+model_provider: cohere

resources/model-catalogs/cohere/command-r-03-2024.yaml

@@ -0,0 +1,45 @@
+id: cohere/command-r-03-2024
+canonical_slug: cohere/command-r-03-2024
+hugging_face_id: ''
+name: 'Cohere: Command R (03-2024)'
+type: chat
+created: 1709341200
+description: |-
+  Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents.
+
+  Read the launch post [here](https://txt.cohere.com/command-r/).
+
+  Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Cohere
+  instruct_type: null
+pricing:
+  prompt: '0.0000005'
+  completion: '0.0000015'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - seed
+  - response_format
+  - structured_outputs
+model_provider: cohere

resources/model-catalogs/cohere/command-r-08-2024.yaml

@@ -0,0 +1,45 @@
+id: cohere/command-r-08-2024
+canonical_slug: cohere/command-r-08-2024
+hugging_face_id: ''
+name: 'Cohere: Command R (08-2024)'
+type: chat
+created: 1724976000
+description: |-
+  command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and is competitive with the previous version of the larger Command R+ model.
+
+  Read the launch post [here](https://docs.cohere.com/changelog/command-gets-refreshed).
+
+  Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Cohere
+  instruct_type: null
+pricing:
+  prompt: '0.00000015'
+  completion: '0.0000006'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - seed
+  - response_format
+  - structured_outputs
+model_provider: cohere

resources/model-catalogs/cohere/command-r-plus-04-2024.yaml

@@ -0,0 +1,45 @@
+id: cohere/command-r-plus-04-2024
+canonical_slug: cohere/command-r-plus-04-2024
+hugging_face_id: ''
+name: 'Cohere: Command R+ (04-2024)'
+type: chat
+created: 1712016000
+description: |-
+  Command R+ is a new, 104B-parameter LLM from Cohere. It's useful for roleplay, general consumer usecases, and Retrieval Augmented Generation (RAG).
+
+  It offers multilingual support for ten key languages to facilitate global business operations. See benchmarks and the launch post [here](https://txt.cohere.com/command-r-plus-microsoft-azure/).
+
+  Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Cohere
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - seed
+  - response_format
+  - structured_outputs
+model_provider: cohere

resources/model-catalogs/cohere/command-r-plus-08-2024.yaml

@@ -0,0 +1,45 @@
+id: cohere/command-r-plus-08-2024
+canonical_slug: cohere/command-r-plus-08-2024
+hugging_face_id: ''
+name: 'Cohere: Command R+ (08-2024)'
+type: chat
+created: 1724976000
+description: |-
+  command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint the same.
+
+  Read the launch post [here](https://docs.cohere.com/changelog/command-gets-refreshed).
+
+  Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Cohere
+  instruct_type: null
+pricing:
+  prompt: '0.0000025'
+  completion: '0.00001'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - seed
+  - response_format
+  - structured_outputs
+model_provider: cohere

resources/model-catalogs/cohere/command-r-plus.yaml

@@ -0,0 +1,45 @@
+id: cohere/command-r-plus
+canonical_slug: cohere/command-r-plus
+hugging_face_id: ''
+name: 'Cohere: Command R+'
+type: chat
+created: 1712188800
+description: |-
+  Command R+ is a new, 104B-parameter LLM from Cohere. It's useful for roleplay, general consumer usecases, and Retrieval Augmented Generation (RAG).
+
+  It offers multilingual support for ten key languages to facilitate global business operations. See benchmarks and the launch post [here](https://txt.cohere.com/command-r-plus-microsoft-azure/).
+
+  Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Cohere
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - seed
+  - response_format
+  - structured_outputs
+model_provider: cohere

resources/model-catalogs/cohere/command-r.yaml

@@ -0,0 +1,45 @@
+id: cohere/command-r
+canonical_slug: cohere/command-r
+hugging_face_id: ''
+name: 'Cohere: Command R'
+type: chat
+created: 1710374400
+description: |-
+  Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents.
+
+  Read the launch post [here](https://txt.cohere.com/command-r/).
+
+  Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Cohere
+  instruct_type: null
+pricing:
+  prompt: '0.0000005'
+  completion: '0.0000015'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - seed
+  - response_format
+  - structured_outputs
+model_provider: cohere

resources/model-catalogs/cohere/command-r7b-12-2024.yaml

@@ -0,0 +1,42 @@
+id: cohere/command-r7b-12-2024
+canonical_slug: cohere/command-r7b-12-2024
+hugging_face_id: ''
+name: 'Cohere: Command R7B (12-2024)'
+type: chat
+created: 1734158152
+description: |-
+  Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.
+
+  Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Cohere
+  instruct_type: null
+pricing:
+  prompt: '0.0000000375'
+  completion: '0.00000015'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - seed
+  - response_format
+  - structured_outputs
+model_provider: cohere

resources/model-catalogs/cohere/command.yaml

@@ -0,0 +1,42 @@
+id: cohere/command
+canonical_slug: cohere/command
+hugging_face_id: ''
+name: 'Cohere: Command'
+type: chat
+created: 1710374400
+description: |-
+  Command is an instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.
+
+  Use of this model is subject to Cohere's [Usage Policy](https://docs.cohere.com/docs/usage-policy) and [SaaS Agreement](https://cohere.com/saas-agreement).
+context_length: 4096
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Cohere
+  instruct_type: null
+pricing:
+  prompt: '0.000001'
+  completion: '0.000002'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - seed
+  - response_format
+  - structured_outputs
+model_provider: cohere

resources/model-catalogs/deepseek/deepseek-chat-v3-0324.yaml

@@ -0,0 +1,49 @@
+id: deepseek/deepseek-chat-v3-0324
+canonical_slug: deepseek/deepseek-chat-v3-0324
+hugging_face_id: deepseek-ai/DeepSeek-V3-0324
+name: 'DeepSeek: DeepSeek V3 0324'
+type: chat
+created: 1742824755
+description: |-
+  DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.
+
+  It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.
+context_length: 163840
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: DeepSeek
+  instruct_type: null
+pricing:
+  prompt: '0.0000003'
+  completion: '0.00000088'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - structured_outputs
+  - response_format
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - logprobs
+  - top_logprobs
+  - seed
+  - min_p
+model_provider: deepseek

resources/model-catalogs/deepseek/deepseek-chat.yaml

@@ -0,0 +1,49 @@
+id: deepseek/deepseek-chat
+canonical_slug: deepseek/deepseek-chat-v3
+hugging_face_id: deepseek-ai/DeepSeek-V3
+name: 'DeepSeek: DeepSeek V3'
+type: chat
+created: 1735241320
+description: |-
+  DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.
+
+  For model details, please visit [the DeepSeek-V3 repo](https://github.com/deepseek-ai/DeepSeek-V3) for more information, or see the [launch announcement](https://api-docs.deepseek.com/news/news1226).
+context_length: 163840
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: DeepSeek
+  instruct_type: null
+pricing:
+  prompt: '0.00000038'
+  completion: '0.00000089'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - structured_outputs
+  - response_format
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - logprobs
+  - top_logprobs
+  - seed
+  - min_p
+model_provider: deepseek

resources/model-catalogs/deepseek/deepseek-prover-v2.yaml

@@ -0,0 +1,41 @@
+id: deepseek/deepseek-prover-v2
+canonical_slug: deepseek/deepseek-prover-v2
+hugging_face_id: deepseek-ai/DeepSeek-Prover-V2-671B
+name: 'DeepSeek: DeepSeek Prover V2'
+type: chat
+created: 1746013094
+description: DeepSeek Prover V2 is a 671B parameter model, speculated to be geared towards logic and mathematics. Likely an upgrade from [DeepSeek-Prover-V1.5](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V1.5-RL) Not much is known about the model yet, as DeepSeek released it on Hugging Face without an announcement or description.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: DeepSeek
+  instruct_type: null
+pricing:
+  prompt: '0.0000005'
+  completion: '0.00000218'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - seed
+  - top_k
+  - min_p
+  - repetition_penalty
+  - logit_bias
+  - response_format
+model_provider: deepseek

resources/model-catalogs/deepseek/deepseek-r1-0528-qwen3-8b.yaml

@@ -0,0 +1,45 @@
+id: deepseek/deepseek-r1-0528-qwen3-8b
+canonical_slug: deepseek/deepseek-r1-0528-qwen3-8b
+hugging_face_id: deepseek-ai/deepseek-r1-0528-qwen3-8b
+name: 'DeepSeek: Deepseek R1 0528 Qwen3 8B'
+type: chat
+created: 1748538543
+description: |-
+  DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro.
+  It now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought.
+  The distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Qwen
+  instruct_type: deepseek-r1
+pricing:
+  prompt: '0.00000005'
+  completion: '0.0000001'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+  - presence_penalty
+  - frequency_penalty
+  - repetition_penalty
+  - top_k
+  - stop
+  - seed
+  - min_p
+  - logit_bias
+model_provider: deepseek

resources/model-catalogs/deepseek/deepseek-r1-0528.yaml

@@ -0,0 +1,51 @@
+id: deepseek/deepseek-r1-0528
+canonical_slug: deepseek/deepseek-r1-0528
+hugging_face_id: deepseek-ai/DeepSeek-R1-0528
+name: 'DeepSeek: R1 0528'
+type: chat
+created: 1748455170
+description: |-
+  May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.
+
+  Fully open-source model.
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: DeepSeek
+  instruct_type: deepseek-r1
+pricing:
+  prompt: '0.0000005'
+  completion: '0.00000215'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+  - logprobs
+  - top_logprobs
+  - tools
+  - tool_choice
+  - seed
+  - structured_outputs
+model_provider: deepseek

resources/model-catalogs/deepseek/deepseek-r1-distill-llama-70b.yaml

@@ -0,0 +1,55 @@
+id: deepseek/deepseek-r1-distill-llama-70b
+canonical_slug: deepseek/deepseek-r1-distill-llama-70b
+hugging_face_id: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+name: 'DeepSeek: R1 Distill Llama 70B'
+type: chat
+created: 1737663169
+description: |-
+  DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including:
+
+  - AIME 2024 pass@1: 70.0
+  - MATH-500 pass@1: 94.5
+  - CodeForces Rating: 1633
+
+  The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Llama3
+  instruct_type: deepseek-r1
+pricing:
+  prompt: '0.0000001'
+  completion: '0.0000004'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+  - seed
+  - top_k
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - logit_bias
+  - logprobs
+  - top_logprobs
+  - min_p
+  - repetition_penalty
+  - tools
+  - tool_choice
+  - response_format
+  - structured_outputs
+model_provider: deepseek

resources/model-catalogs/deepseek/deepseek-r1-distill-llama-8b.yaml

@@ -0,0 +1,42 @@
+id: deepseek/deepseek-r1-distill-llama-8b
+canonical_slug: deepseek/deepseek-r1-distill-llama-8b
+hugging_face_id: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+name: 'DeepSeek: R1 Distill Llama 8B'
+type: chat
+created: 1738937718
+description: "DeepSeek R1 Distill Llama 8B is a distilled large language model based on [Llama-3.1-8B-Instruct](/meta-llama/llama-3.1-8b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including:\n\n- AIME 2024 pass@1: 50.4\n- MATH-500 pass@1: 89.1\n- CodeForces Rating: 1205\n\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.\n\nHugging Face: \n- [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) \n- [DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B)   |"
+context_length: 32000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Llama3
+  instruct_type: deepseek-r1
+pricing:
+  prompt: '0.00000004'
+  completion: '0.00000004'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - seed
+  - top_k
+  - min_p
+  - repetition_penalty
+  - logit_bias
+model_provider: deepseek

resources/model-catalogs/deepseek/deepseek-r1-distill-qwen-1.5b.yaml

@@ -0,0 +1,51 @@
+id: deepseek/deepseek-r1-distill-qwen-1.5b
+canonical_slug: deepseek/deepseek-r1-distill-qwen-1.5b
+hugging_face_id: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+name: 'DeepSeek: R1 Distill Qwen 1.5B'
+type: chat
+created: 1738328067
+description: |-
+  DeepSeek R1 Distill Qwen 1.5B is a distilled large language model based on  [Qwen 2.5 Math 1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It's a very small and efficient model which outperforms [GPT 4o 0513](/openai/gpt-4o-2024-05-13) on Math Benchmarks.
+
+  Other benchmark results include:
+
+  - AIME 2024 pass@1: 28.9
+  - AIME 2024 cons@64: 52.7
+  - MATH-500 pass@1: 83.9
+
+  The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: deepseek-r1
+pricing:
+  prompt: '0.00000018'
+  completion: '0.00000018'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: deepseek

resources/model-catalogs/deepseek/deepseek-r1-distill-qwen-14b.yaml

@@ -0,0 +1,52 @@
+id: deepseek/deepseek-r1-distill-qwen-14b
+canonical_slug: deepseek/deepseek-r1-distill-qwen-14b
+hugging_face_id: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+name: 'DeepSeek: R1 Distill Qwen 14B'
+type: chat
+created: 1738193940
+description: |-
+  DeepSeek R1 Distill Qwen 14B is a distilled large language model based on [Qwen 2.5 14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
+
+  Other benchmark results include:
+
+  - AIME 2024 pass@1: 69.7
+  - MATH-500 pass@1: 93.9
+  - CodeForces Rating: 1481
+
+  The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.
+context_length: 64000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Qwen
+  instruct_type: deepseek-r1
+pricing:
+  prompt: '0.00000015'
+  completion: '0.00000015'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+  - seed
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - min_p
+  - repetition_penalty
+  - logit_bias
+  - response_format
+model_provider: deepseek

resources/model-catalogs/deepseek/deepseek-r1-distill-qwen-32b.yaml

@@ -0,0 +1,43 @@
+id: deepseek/deepseek-r1-distill-qwen-32b
+canonical_slug: deepseek/deepseek-r1-distill-qwen-32b
+hugging_face_id: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+name: 'DeepSeek: R1 Distill Qwen 32B'
+type: chat
+created: 1738194830
+description: 'DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI''s o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.\n\nOther benchmark results include:\n\n- AIME 2024 pass@1: 72.6\n- MATH-500 pass@1: 94.3\n- CodeForces Rating: 1691\n\nThe model leverages fine-tuning from DeepSeek R1''s outputs, enabling competitive performance comparable to larger frontier models.'
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Qwen
+  instruct_type: deepseek-r1
+pricing:
+  prompt: '0.00000012'
+  completion: '0.00000018'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+  - seed
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - min_p
+  - repetition_penalty
+  - logit_bias
+  - response_format
+model_provider: deepseek