From 01c14bda33b7a9247227360ccd8fc4242d2b29dd Mon Sep 17 00:00:00 2001 From: "jason.mei" Date: Wed, 10 Dec 2025 19:13:03 +0800 Subject: [PATCH 1/2] add more models --- .github/workflows/plugin-publish.yml | 143 ------------------ models/llm/baidu-ernie-4.5-turbo-128k.yaml | 6 +- models/llm/baidu-ernie-4.5-turbo-vl-32k.yaml | 4 +- models/llm/baidu-ernie-x1-turbo-32k.yaml | 4 +- .../bytedance-doubao-1-5-pro-256k-250115.yaml | 4 +- .../bytedance-doubao-1-5-pro-32k-250115.yaml | 4 +- ...edance-doubao-1.5-thinking-vision-pro.yaml | 6 +- .../bytedance-doubao-seed-1.6-thinking.yaml | 6 +- models/llm/bytedance-doubao-seed-1.6.yaml | 6 +- models/llm/claude-4-opus.yaml | 6 +- models/llm/claude-4-sonnet.yaml | 6 +- models/llm/claude-opus-4-1-20250805.yaml | 35 +++++ models/llm/claude-opus-4-1.yaml | 6 +- .../claude-opus-4-5-20251101-thinking.yaml | 35 +++++ models/llm/claude-opus-4-5-20251101.yaml | 35 +++++ models/llm/claude-opus-4.0-thinking.yaml | 35 +++++ models/llm/claude-opus-4.1-thinking.yaml | 35 +++++ models/llm/claude-sonnet-3.5.yaml | 35 +++++ models/llm/claude-sonnet-3.7.yaml | 35 +++++ .../claude-sonnet-4-5-20250929-thinking.yaml | 35 +++++ models/llm/claude-sonnet-4-5-20250929.yaml | 35 +++++ models/llm/claude-sonnet-4.0-thinking.yaml | 35 +++++ models/llm/claude-sonnet-4.5-thinking.yaml | 35 +++++ models/llm/claude-sonnet-4.5.yaml | 35 +++++ models/llm/deepseek-ocr.yaml | 31 ++++ models/llm/deepseek-r1-0528.yaml | 35 +++++ models/llm/deepseek-r1-base.yaml | 6 +- models/llm/deepseek-r1-distill-llama-70b.yaml | 6 +- models/llm/deepseek-r1.yaml | 6 +- models/llm/deepseek-v3-0324.yaml | 35 +++++ models/llm/deepseek-v3.1-0821.yaml | 35 +++++ models/llm/deepseek-v3.1-terminus.yaml | 6 +- models/llm/deepseek-v3.1-think.yaml | 35 +++++ models/llm/deepseek-v3.1.yaml | 6 +- models/llm/deepseek-v3.2-exp-think.yaml | 6 +- models/llm/deepseek-v3.2-exp.yaml | 6 +- models/llm/deepseek-v3.2-speciale.yaml | 35 +++++ models/llm/deepseek-v3.2-think.yaml | 35 +++++ models/llm/deepseek-v3.2.yaml | 35 +++++ models/llm/deepseek-v3.yaml | 5 +- models/llm/gemini-2.5-flash.yaml | 6 +- models/llm/gemini-2.5-pro.yaml | 6 +- models/llm/gemini-3-pro-preview.yaml | 35 +++++ models/llm/gpt-4.1-mini.yaml | 6 +- models/llm/gpt-4.1-nano.yaml | 35 +++++ models/llm/gpt-4o-mini.yaml | 35 +++++ models/llm/gpt-5-chat.yaml | 35 +++++ models/llm/gpt-5.1-chat.yaml | 35 +++++ models/llm/gpt-5.1.yaml | 35 +++++ models/llm/gpt-5.yaml | 35 +++++ models/llm/grok-4-1-fast-non-reasoning.yaml | 35 +++++ models/llm/grok-4-1-fast-reasoning.yaml | 35 +++++ models/llm/grok-4-fast-reasoning.yaml | 35 +++++ models/llm/grok-4-fast.yaml | 35 +++++ models/llm/grok-4.yaml | 6 +- models/llm/kat-coder-256k.yaml | 35 +++++ models/llm/llm.py | 2 +- .../llm/moonshotai-kimi-k2-instruct-0905.yaml | 6 +- models/llm/moonshotai-kimi-k2-instruct.yaml | 6 +- models/llm/moonshotai-kimi-k2-thinking.yaml | 35 +++++ models/llm/o1.yaml | 35 +++++ models/llm/o4-mini-deep-research.yaml | 35 +++++ models/llm/o4-mini.yaml | 35 +++++ models/llm/openai-gpt-4.1.yaml | 6 +- models/llm/openai-gpt-4o.yaml | 6 +- models/llm/openai-gpt-5-mini.yaml | 6 +- models/llm/openai-gpt-5-nano.yaml | 6 +- models/llm/openai-gpt-5.1-chat.yaml | 35 +++++ models/llm/openai-gpt-5.1.yaml | 35 +++++ models/llm/openai-gpt-5.yaml | 6 +- models/llm/openai-gpt-oss-120b.yaml | 6 +- models/llm/openai-gpt-oss-20b.yaml | 6 +- models/llm/qwen-plus-thinking.yaml | 35 +++++ models/llm/qwen-plus.yaml | 35 +++++ models/llm/qwen-qwq-32b.yaml | 6 +- models/llm/qwen2.5-vl-72b-instruct.yaml | 6 +- models/llm/qwen3-235b-a22b-thinking-2507.yaml | 35 +++++ models/llm/qwen3-235b-a22b.yaml | 6 +- models/llm/qwen3-30b-a3b-thinking.yaml | 35 +++++ models/llm/qwen3-30b-a3b.yaml | 6 +- models/llm/qwen3-32b-thinking.yaml | 35 +++++ models/llm/qwen3-32b.yaml | 6 +- models/llm/qwen3-coder.yaml | 6 +- models/llm/qwen3-max.yaml | 35 +++++ models/llm/qwen3-vl-235b-a22b-instruct.yaml | 35 +++++ models/llm/qwen3-vl-235b-a22b-thinking.yaml | 35 +++++ models/llm/qwen3-vl-plus.yaml | 35 +++++ models/llm/zai-org-glm-4.5.yaml | 6 +- models/llm/zai-org-glm-4.5v.yaml | 6 +- models/llm/zai-org-glm-4.6.yaml | 35 +++++ provider/modelverse.py | 2 +- 91 files changed, 1832 insertions(+), 222 deletions(-) delete mode 100644 .github/workflows/plugin-publish.yml create mode 100644 models/llm/claude-opus-4-1-20250805.yaml create mode 100644 models/llm/claude-opus-4-5-20251101-thinking.yaml create mode 100644 models/llm/claude-opus-4-5-20251101.yaml create mode 100644 models/llm/claude-opus-4.0-thinking.yaml create mode 100644 models/llm/claude-opus-4.1-thinking.yaml create mode 100644 models/llm/claude-sonnet-3.5.yaml create mode 100644 models/llm/claude-sonnet-3.7.yaml create mode 100644 models/llm/claude-sonnet-4-5-20250929-thinking.yaml create mode 100644 models/llm/claude-sonnet-4-5-20250929.yaml create mode 100644 models/llm/claude-sonnet-4.0-thinking.yaml create mode 100644 models/llm/claude-sonnet-4.5-thinking.yaml create mode 100644 models/llm/claude-sonnet-4.5.yaml create mode 100644 models/llm/deepseek-ocr.yaml create mode 100644 models/llm/deepseek-r1-0528.yaml create mode 100644 models/llm/deepseek-v3-0324.yaml create mode 100644 models/llm/deepseek-v3.1-0821.yaml create mode 100644 models/llm/deepseek-v3.1-think.yaml create mode 100644 models/llm/deepseek-v3.2-speciale.yaml create mode 100644 models/llm/deepseek-v3.2-think.yaml create mode 100644 models/llm/deepseek-v3.2.yaml create mode 100644 models/llm/gemini-3-pro-preview.yaml create mode 100644 models/llm/gpt-4.1-nano.yaml create mode 100644 models/llm/gpt-4o-mini.yaml create mode 100644 models/llm/gpt-5-chat.yaml create mode 100644 models/llm/gpt-5.1-chat.yaml create mode 100644 models/llm/gpt-5.1.yaml create mode 100644 models/llm/gpt-5.yaml create mode 100644 models/llm/grok-4-1-fast-non-reasoning.yaml create mode 100644 models/llm/grok-4-1-fast-reasoning.yaml create mode 100644 models/llm/grok-4-fast-reasoning.yaml create mode 100644 models/llm/grok-4-fast.yaml create mode 100644 models/llm/kat-coder-256k.yaml create mode 100644 models/llm/moonshotai-kimi-k2-thinking.yaml create mode 100644 models/llm/o1.yaml create mode 100644 models/llm/o4-mini-deep-research.yaml create mode 100644 models/llm/o4-mini.yaml create mode 100644 models/llm/openai-gpt-5.1-chat.yaml create mode 100644 models/llm/openai-gpt-5.1.yaml create mode 100644 models/llm/qwen-plus-thinking.yaml create mode 100644 models/llm/qwen-plus.yaml create mode 100644 models/llm/qwen3-235b-a22b-thinking-2507.yaml create mode 100644 models/llm/qwen3-30b-a3b-thinking.yaml create mode 100644 models/llm/qwen3-32b-thinking.yaml create mode 100644 models/llm/qwen3-max.yaml create mode 100644 models/llm/qwen3-vl-235b-a22b-instruct.yaml create mode 100644 models/llm/qwen3-vl-235b-a22b-thinking.yaml create mode 100644 models/llm/qwen3-vl-plus.yaml create mode 100644 models/llm/zai-org-glm-4.6.yaml diff --git a/.github/workflows/plugin-publish.yml b/.github/workflows/plugin-publish.yml deleted file mode 100644 index 9f018e0..0000000 --- a/.github/workflows/plugin-publish.yml +++ /dev/null @@ -1,143 +0,0 @@ -# .github/workflows/auto-pr.yml -name: Auto Create PR on Main Push - -on: - push: - branches: [main] # Trigger on push to main - -jobs: - create_pr: # Renamed job for clarity - runs-on: ubuntu-latest - steps: - - name: Checkout code - uses: actions/checkout@v3 - - - name: Print working directory # Kept for debugging - run: | - pwd - ls -la - - - name: Download CLI tool - run: | - # Create bin directory in runner temp - mkdir -p $RUNNER_TEMP/bin - cd $RUNNER_TEMP/bin - - # Download CLI tool - wget https://github.com/langgenius/dify-plugin-daemon/releases/download/0.0.6/dify-plugin-linux-amd64 - chmod +x dify-plugin-linux-amd64 - - # Show download location and file - echo "CLI tool location:" - pwd - ls -la dify-plugin-linux-amd64 - - - name: Get basic info from manifest # Changed step name and content - id: get_basic_info - run: | - PLUGIN_NAME=$(grep "^name:" manifest.yaml | cut -d' ' -f2) - echo "Plugin name: $PLUGIN_NAME" - echo "plugin_name=$PLUGIN_NAME" >> $GITHUB_OUTPUT - - VERSION=$(grep "^version:" manifest.yaml | cut -d' ' -f2) - echo "Plugin version: $VERSION" - echo "version=$VERSION" >> $GITHUB_OUTPUT - - # If the author's name is not your github username, you can change the author here - AUTHOR=$(grep "^author:" manifest.yaml | cut -d' ' -f2) - echo "Plugin author: $AUTHOR" - echo "author=$AUTHOR" >> $GITHUB_OUTPUT - - - name: Package Plugin - id: package - run: | - # Use the downloaded CLI tool to package - cd $GITHUB_WORKSPACE - # Use variables for package name - PACKAGE_NAME="${{ steps.get_basic_info.outputs.plugin_name }}-${{ steps.get_basic_info.outputs.version }}.difypkg" - # Use CLI from runner temp - $RUNNER_TEMP/bin/dify-plugin-linux-amd64 plugin package . -o "$PACKAGE_NAME" - - # Show packaging result - echo "Package result:" - ls -la "$PACKAGE_NAME" - echo "package_name=$PACKAGE_NAME" >> $GITHUB_OUTPUT - - # Show full file path and directory structure (kept for debugging) - echo "\\nFull file path:" - pwd - echo "\\nDirectory structure:" - tree || ls -R - - - name: Checkout target repo - uses: actions/checkout@v3 - with: - # Use author variable for repository - repository: mfzzf/dify-plugins - path: dify-plugins - token: ${{ secrets.PLUGIN_ACTION }} - fetch-depth: 1 # Fetch only the last commit to speed up checkout - persist-credentials: true # Persist credentials for subsequent git operations - - - name: Prepare and create PR - run: | - # Debug info (kept) - echo "Debug: Current directory $(pwd)" - # Use variable for package name - PACKAGE_NAME="${{ steps.get_basic_info.outputs.plugin_name }}-${{ steps.get_basic_info.outputs.version }}.difypkg" - echo "Debug: Package name: $PACKAGE_NAME" - ls -la - - # Move the packaged file to the target directory using variables - mkdir -p dify-plugins/${{ steps.get_basic_info.outputs.author }}/${{ steps.get_basic_info.outputs.plugin_name }} - mv "$PACKAGE_NAME" dify-plugins/${{ steps.get_basic_info.outputs.author }}/${{ steps.get_basic_info.outputs.plugin_name }}/ - - # Enter the target repository directory - cd dify-plugins - - # Configure git - git config user.name "GitHub Actions" - git config user.email "actions@github.com" - - # Ensure we are on the latest main branch - git fetch origin main - git checkout main - git pull origin main - - # Create and switch to a new branch using variables and new naming convention - BRANCH_NAME="bump-${{ steps.get_basic_info.outputs.plugin_name }}-plugin-${{ steps.get_basic_info.outputs.version }}" - git checkout -b "$BRANCH_NAME" - - # Add and commit changes (using git add .) - git add . - git status # for debugging - # Use variables in commit message - git commit -m "bump ${{ steps.get_basic_info.outputs.plugin_name }} plugin to version ${{ steps.get_basic_info.outputs.version }}" - - # Push to remote (use force just in case the branch existed before from a failed run) - git push -u origin "$BRANCH_NAME" --force - - # Confirm branch has been pushed and wait for sync (GitHub API might need a moment) - git branch -a - echo "Waiting for branch to sync..." - sleep 10 # Wait 10 seconds for branch sync - - - name: Create PR via GitHub API - env: - GH_TOKEN: ${{ secrets.PLUGIN_ACTION }} # Use the provided token for authentication - run: | - gh pr create \ - --repo langgenius/dify-plugins \ - --head "mfzzf:bump-${{ steps.get_basic_info.outputs.plugin_name }}-${{ steps.get_basic_info.outputs.version }}" \ - --base main \ - --title "bump ${{ steps.get_basic_info.outputs.plugin_name }} plugin to version ${{ steps.get_basic_info.outputs.version }}" \ - --body "bump ${{ steps.get_basic_info.outputs.plugin_name }} plugin package to version ${{ steps.get_basic_info.outputs.version }} - - Changes: - - Updated plugin package file" || echo "PR already exists or creation skipped." # Handle cases where PR already exists - - - name: Print environment info # Kept for debugging - run: | - echo "GITHUB_WORKSPACE: $GITHUB_WORKSPACE" - echo "Current directory contents:" - ls -R \ No newline at end of file diff --git a/models/llm/baidu-ernie-4.5-turbo-128k.yaml b/models/llm/baidu-ernie-4.5-turbo-128k.yaml index fe763bd..2e44ee1 100644 --- a/models/llm/baidu-ernie-4.5-turbo-128k.yaml +++ b/models/llm/baidu-ernie-4.5-turbo-128k.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/baidu-ernie-4.5-turbo-vl-32k.yaml b/models/llm/baidu-ernie-4.5-turbo-vl-32k.yaml index 24d1bd2..bd4ac0e 100644 --- a/models/llm/baidu-ernie-4.5-turbo-vl-32k.yaml +++ b/models/llm/baidu-ernie-4.5-turbo-vl-32k.yaml @@ -7,6 +7,8 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat context_size: 32000 @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/baidu-ernie-x1-turbo-32k.yaml b/models/llm/baidu-ernie-x1-turbo-32k.yaml index 9a768f4..c42bd15 100644 --- a/models/llm/baidu-ernie-x1-turbo-32k.yaml +++ b/models/llm/baidu-ernie-x1-turbo-32k.yaml @@ -7,6 +7,8 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat context_size: 32000 @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/bytedance-doubao-1-5-pro-256k-250115.yaml b/models/llm/bytedance-doubao-1-5-pro-256k-250115.yaml index 2e8a959..f5345b3 100644 --- a/models/llm/bytedance-doubao-1-5-pro-256k-250115.yaml +++ b/models/llm/bytedance-doubao-1-5-pro-256k-250115.yaml @@ -7,6 +7,8 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat context_size: 256000 @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/bytedance-doubao-1-5-pro-32k-250115.yaml b/models/llm/bytedance-doubao-1-5-pro-32k-250115.yaml index 5be52d6..6e992c1 100644 --- a/models/llm/bytedance-doubao-1-5-pro-32k-250115.yaml +++ b/models/llm/bytedance-doubao-1-5-pro-32k-250115.yaml @@ -7,6 +7,8 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat context_size: 32000 @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/bytedance-doubao-1.5-thinking-vision-pro.yaml b/models/llm/bytedance-doubao-1.5-thinking-vision-pro.yaml index c5243fe..f895782 100644 --- a/models/llm/bytedance-doubao-1.5-thinking-vision-pro.yaml +++ b/models/llm/bytedance-doubao-1.5-thinking-vision-pro.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/bytedance-doubao-seed-1.6-thinking.yaml b/models/llm/bytedance-doubao-seed-1.6-thinking.yaml index 0909dc8..f6e6321 100644 --- a/models/llm/bytedance-doubao-seed-1.6-thinking.yaml +++ b/models/llm/bytedance-doubao-seed-1.6-thinking.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/bytedance-doubao-seed-1.6.yaml b/models/llm/bytedance-doubao-seed-1.6.yaml index 4d67364..2deb193 100644 --- a/models/llm/bytedance-doubao-seed-1.6.yaml +++ b/models/llm/bytedance-doubao-seed-1.6.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/claude-4-opus.yaml b/models/llm/claude-4-opus.yaml index f550689..4e157f9 100644 --- a/models/llm/claude-4-opus.yaml +++ b/models/llm/claude-4-opus.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/claude-4-sonnet.yaml b/models/llm/claude-4-sonnet.yaml index 8bfb877..f061b4a 100644 --- a/models/llm/claude-4-sonnet.yaml +++ b/models/llm/claude-4-sonnet.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/claude-opus-4-1-20250805.yaml b/models/llm/claude-opus-4-1-20250805.yaml new file mode 100644 index 0000000..3ca6095 --- /dev/null +++ b/models/llm/claude-opus-4-1-20250805.yaml @@ -0,0 +1,35 @@ +model: claude-opus-4-1-20250805 +label: + zh_Hans: claude-opus-4-1-20250805 + en_US: claude-opus-4-1-20250805 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.015' + output: '0.075' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-opus-4-1.yaml b/models/llm/claude-opus-4-1.yaml index 8d37fc9..d3de143 100644 --- a/models/llm/claude-opus-4-1.yaml +++ b/models/llm/claude-opus-4-1.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/claude-opus-4-5-20251101-thinking.yaml b/models/llm/claude-opus-4-5-20251101-thinking.yaml new file mode 100644 index 0000000..aaa553b --- /dev/null +++ b/models/llm/claude-opus-4-5-20251101-thinking.yaml @@ -0,0 +1,35 @@ +model: claude-opus-4-5-20251101-thinking +label: + zh_Hans: claude-opus-4-5-20251101-thinking + en_US: claude-opus-4-5-20251101-thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.015' + output: '0.075' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-opus-4-5-20251101.yaml b/models/llm/claude-opus-4-5-20251101.yaml new file mode 100644 index 0000000..d7c83bd --- /dev/null +++ b/models/llm/claude-opus-4-5-20251101.yaml @@ -0,0 +1,35 @@ +model: claude-opus-4-5-20251101 +label: + zh_Hans: claude-opus-4-5-20251101 + en_US: claude-opus-4-5-20251101 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.015' + output: '0.075' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-opus-4.0-thinking.yaml b/models/llm/claude-opus-4.0-thinking.yaml new file mode 100644 index 0000000..d775821 --- /dev/null +++ b/models/llm/claude-opus-4.0-thinking.yaml @@ -0,0 +1,35 @@ +model: claude-opus-4.0-thinking +label: + zh_Hans: claude-opus-4.0-thinking + en_US: claude-opus-4.0-thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.015' + output: '0.075' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-opus-4.1-thinking.yaml b/models/llm/claude-opus-4.1-thinking.yaml new file mode 100644 index 0000000..d7d6574 --- /dev/null +++ b/models/llm/claude-opus-4.1-thinking.yaml @@ -0,0 +1,35 @@ +model: claude-opus-4.1-thinking +label: + zh_Hans: claude-opus-4.1-thinking + en_US: claude-opus-4.1-thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.015' + output: '0.075' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-sonnet-3.5.yaml b/models/llm/claude-sonnet-3.5.yaml new file mode 100644 index 0000000..da72944 --- /dev/null +++ b/models/llm/claude-sonnet-3.5.yaml @@ -0,0 +1,35 @@ +model: claude-sonnet-3.5 +label: + zh_Hans: claude-sonnet-3.5 + en_US: claude-sonnet-3.5 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-sonnet-3.7.yaml b/models/llm/claude-sonnet-3.7.yaml new file mode 100644 index 0000000..c779661 --- /dev/null +++ b/models/llm/claude-sonnet-3.7.yaml @@ -0,0 +1,35 @@ +model: claude-sonnet-3.7 +label: + zh_Hans: claude-sonnet-3.7 + en_US: claude-sonnet-3.7 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-sonnet-4-5-20250929-thinking.yaml b/models/llm/claude-sonnet-4-5-20250929-thinking.yaml new file mode 100644 index 0000000..5665f88 --- /dev/null +++ b/models/llm/claude-sonnet-4-5-20250929-thinking.yaml @@ -0,0 +1,35 @@ +model: claude-sonnet-4-5-20250929-thinking +label: + zh_Hans: claude-sonnet-4-5-20250929-thinking + en_US: claude-sonnet-4-5-20250929-thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-sonnet-4-5-20250929.yaml b/models/llm/claude-sonnet-4-5-20250929.yaml new file mode 100644 index 0000000..928c917 --- /dev/null +++ b/models/llm/claude-sonnet-4-5-20250929.yaml @@ -0,0 +1,35 @@ +model: claude-sonnet-4-5-20250929 +label: + zh_Hans: claude-sonnet-4-5-20250929 + en_US: claude-sonnet-4-5-20250929 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-sonnet-4.0-thinking.yaml b/models/llm/claude-sonnet-4.0-thinking.yaml new file mode 100644 index 0000000..d12ac59 --- /dev/null +++ b/models/llm/claude-sonnet-4.0-thinking.yaml @@ -0,0 +1,35 @@ +model: claude-sonnet-4.0-thinking +label: + zh_Hans: claude-sonnet-4.0-thinking + en_US: claude-sonnet-4.0-thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-sonnet-4.5-thinking.yaml b/models/llm/claude-sonnet-4.5-thinking.yaml new file mode 100644 index 0000000..ec13799 --- /dev/null +++ b/models/llm/claude-sonnet-4.5-thinking.yaml @@ -0,0 +1,35 @@ +model: claude-sonnet-4.5-thinking +label: + zh_Hans: claude-sonnet-4.5-thinking + en_US: claude-sonnet-4.5-thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/claude-sonnet-4.5.yaml b/models/llm/claude-sonnet-4.5.yaml new file mode 100644 index 0000000..95738ef --- /dev/null +++ b/models/llm/claude-sonnet-4.5.yaml @@ -0,0 +1,35 @@ +model: claude-sonnet-4.5 +label: + zh_Hans: claude-sonnet-4.5 + en_US: claude-sonnet-4.5 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/deepseek-ocr.yaml b/models/llm/deepseek-ocr.yaml new file mode 100644 index 0000000..b6b8f9c --- /dev/null +++ b/models/llm/deepseek-ocr.yaml @@ -0,0 +1,31 @@ +model: deepseek-ai/DeepSeek-OCR +label: + zh_Hans: DeepSeek-OCR + en_US: DeepSeek-OCR +model_type: llm +features: + - vision +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.001' + output: '0.004' + unit: '0.001' + currency: CNY diff --git a/models/llm/deepseek-r1-0528.yaml b/models/llm/deepseek-r1-0528.yaml new file mode 100644 index 0000000..4841477 --- /dev/null +++ b/models/llm/deepseek-r1-0528.yaml @@ -0,0 +1,35 @@ +model: deepseek-ai/DeepSeek-R1-0528 +label: + zh_Hans: DeepSeek-R1-0528 + en_US: DeepSeek-R1-0528 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.016' + unit: '0.001' + currency: CNY diff --git a/models/llm/deepseek-r1-base.yaml b/models/llm/deepseek-r1-base.yaml index 46aae1c..fcf151c 100644 --- a/models/llm/deepseek-r1-base.yaml +++ b/models/llm/deepseek-r1-base.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/deepseek-r1-distill-llama-70b.yaml b/models/llm/deepseek-r1-distill-llama-70b.yaml index e7289d1..73909bf 100644 --- a/models/llm/deepseek-r1-distill-llama-70b.yaml +++ b/models/llm/deepseek-r1-distill-llama-70b.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/deepseek-r1.yaml b/models/llm/deepseek-r1.yaml index 48826e8..804af71 100644 --- a/models/llm/deepseek-r1.yaml +++ b/models/llm/deepseek-r1.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/deepseek-v3-0324.yaml b/models/llm/deepseek-v3-0324.yaml new file mode 100644 index 0000000..e86e17c --- /dev/null +++ b/models/llm/deepseek-v3-0324.yaml @@ -0,0 +1,35 @@ +model: deepseek-ai/DeepSeek-V3-0324 +label: + zh_Hans: DeepSeek-V3-0324 + en_US: DeepSeek-V3-0324 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.002' + output: '0.008' + unit: '0.001' + currency: CNY diff --git a/models/llm/deepseek-v3.1-0821.yaml b/models/llm/deepseek-v3.1-0821.yaml new file mode 100644 index 0000000..b970b5c --- /dev/null +++ b/models/llm/deepseek-v3.1-0821.yaml @@ -0,0 +1,35 @@ +model: deepseek-ai/DeepSeek-V3.1-0821 +label: + zh_Hans: DeepSeek-V3.1-0821 + en_US: DeepSeek-V3.1-0821 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.002' + output: '0.008' + unit: '0.001' + currency: CNY diff --git a/models/llm/deepseek-v3.1-terminus.yaml b/models/llm/deepseek-v3.1-terminus.yaml index 19a8ae2..6e8cf7f 100644 --- a/models/llm/deepseek-v3.1-terminus.yaml +++ b/models/llm/deepseek-v3.1-terminus.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/deepseek-v3.1-think.yaml b/models/llm/deepseek-v3.1-think.yaml new file mode 100644 index 0000000..7bc76d2 --- /dev/null +++ b/models/llm/deepseek-v3.1-think.yaml @@ -0,0 +1,35 @@ +model: deepseek-ai/DeepSeek-V3.1-Think +label: + zh_Hans: DeepSeek-V3.1-Think + en_US: DeepSeek-V3.1-Think +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.002' + output: '0.008' + unit: '0.001' + currency: CNY diff --git a/models/llm/deepseek-v3.1.yaml b/models/llm/deepseek-v3.1.yaml index 476c658..1770736 100644 --- a/models/llm/deepseek-v3.1.yaml +++ b/models/llm/deepseek-v3.1.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/deepseek-v3.2-exp-think.yaml b/models/llm/deepseek-v3.2-exp-think.yaml index 7fa519d..2e67aae 100644 --- a/models/llm/deepseek-v3.2-exp-think.yaml +++ b/models/llm/deepseek-v3.2-exp-think.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/deepseek-v3.2-exp.yaml b/models/llm/deepseek-v3.2-exp.yaml index 7c99e39..909cd32 100644 --- a/models/llm/deepseek-v3.2-exp.yaml +++ b/models/llm/deepseek-v3.2-exp.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/deepseek-v3.2-speciale.yaml b/models/llm/deepseek-v3.2-speciale.yaml new file mode 100644 index 0000000..2a3aa59 --- /dev/null +++ b/models/llm/deepseek-v3.2-speciale.yaml @@ -0,0 +1,35 @@ +model: deepseek-ai/DeepSeek-V3.2-Speciale +label: + zh_Hans: DeepSeek-V3.2-Speciale + en_US: DeepSeek-V3.2-Speciale +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.002' + output: '0.008' + unit: '0.001' + currency: CNY diff --git a/models/llm/deepseek-v3.2-think.yaml b/models/llm/deepseek-v3.2-think.yaml new file mode 100644 index 0000000..8b56bd2 --- /dev/null +++ b/models/llm/deepseek-v3.2-think.yaml @@ -0,0 +1,35 @@ +model: deepseek-ai/DeepSeek-V3.2-Think +label: + zh_Hans: DeepSeek-V3.2-Think + en_US: DeepSeek-V3.2-Think +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.002' + output: '0.008' + unit: '0.001' + currency: CNY diff --git a/models/llm/deepseek-v3.2.yaml b/models/llm/deepseek-v3.2.yaml new file mode 100644 index 0000000..2985d3c --- /dev/null +++ b/models/llm/deepseek-v3.2.yaml @@ -0,0 +1,35 @@ +model: deepseek-ai/DeepSeek-V3.2 +label: + zh_Hans: DeepSeek-V3.2 + en_US: DeepSeek-V3.2 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.002' + output: '0.008' + unit: '0.001' + currency: CNY diff --git a/models/llm/deepseek-v3.yaml b/models/llm/deepseek-v3.yaml index 7f46df2..37ab762 100644 --- a/models/llm/deepseek-v3.yaml +++ b/models/llm/deepseek-v3.yaml @@ -4,14 +4,13 @@ label: en_US: deepseek-v3-0324 model_type: llm features: - - multi-tool-call - agent-thought - stream-tool-call model_properties: mode: chat # 最大上下文大小 - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -25,7 +24,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/gemini-2.5-flash.yaml b/models/llm/gemini-2.5-flash.yaml index ed1ca2b..116189c 100644 --- a/models/llm/gemini-2.5-flash.yaml +++ b/models/llm/gemini-2.5-flash.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/gemini-2.5-pro.yaml b/models/llm/gemini-2.5-pro.yaml index 5b160e7..101257d 100644 --- a/models/llm/gemini-2.5-pro.yaml +++ b/models/llm/gemini-2.5-pro.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/gemini-3-pro-preview.yaml b/models/llm/gemini-3-pro-preview.yaml new file mode 100644 index 0000000..d16d0bd --- /dev/null +++ b/models/llm/gemini-3-pro-preview.yaml @@ -0,0 +1,35 @@ +model: gemini-3-pro-preview +label: + zh_Hans: gemini-3-pro-preview + en_US: gemini-3-pro-preview +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 1000000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.00125' + output: '0.005' + unit: '0.001' + currency: CNY diff --git a/models/llm/gpt-4.1-mini.yaml b/models/llm/gpt-4.1-mini.yaml index 493054c..a0613ad 100644 --- a/models/llm/gpt-4.1-mini.yaml +++ b/models/llm/gpt-4.1-mini.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/gpt-4.1-nano.yaml b/models/llm/gpt-4.1-nano.yaml new file mode 100644 index 0000000..d8cf72d --- /dev/null +++ b/models/llm/gpt-4.1-nano.yaml @@ -0,0 +1,35 @@ +model: gpt-4.1-nano +label: + zh_Hans: gpt-4.1-nano + en_US: gpt-4.1-nano +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.0001' + output: '0.0004' + unit: '0.001' + currency: CNY diff --git a/models/llm/gpt-4o-mini.yaml b/models/llm/gpt-4o-mini.yaml new file mode 100644 index 0000000..46878f6 --- /dev/null +++ b/models/llm/gpt-4o-mini.yaml @@ -0,0 +1,35 @@ +model: gpt-4o-mini +label: + zh_Hans: gpt-4o-mini + en_US: gpt-4o-mini +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.00015' + output: '0.0006' + unit: '0.001' + currency: CNY diff --git a/models/llm/gpt-5-chat.yaml b/models/llm/gpt-5-chat.yaml new file mode 100644 index 0000000..be92fc2 --- /dev/null +++ b/models/llm/gpt-5-chat.yaml @@ -0,0 +1,35 @@ +model: gpt-5-chat +label: + zh_Hans: gpt-5-chat + en_US: gpt-5-chat +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.01' + output: '0.03' + unit: '0.001' + currency: CNY diff --git a/models/llm/gpt-5.1-chat.yaml b/models/llm/gpt-5.1-chat.yaml new file mode 100644 index 0000000..f80ad79 --- /dev/null +++ b/models/llm/gpt-5.1-chat.yaml @@ -0,0 +1,35 @@ +model: gpt-5.1-chat +label: + zh_Hans: gpt-5.1-chat + en_US: gpt-5.1-chat +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.01' + output: '0.03' + unit: '0.001' + currency: CNY diff --git a/models/llm/gpt-5.1.yaml b/models/llm/gpt-5.1.yaml new file mode 100644 index 0000000..7d7d0b4 --- /dev/null +++ b/models/llm/gpt-5.1.yaml @@ -0,0 +1,35 @@ +model: gpt-5.1 +label: + zh_Hans: gpt-5.1 + en_US: gpt-5.1 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.01' + output: '0.03' + unit: '0.001' + currency: CNY diff --git a/models/llm/gpt-5.yaml b/models/llm/gpt-5.yaml new file mode 100644 index 0000000..f6fc40b --- /dev/null +++ b/models/llm/gpt-5.yaml @@ -0,0 +1,35 @@ +model: gpt-5 +label: + zh_Hans: gpt-5 + en_US: gpt-5 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.01' + output: '0.03' + unit: '0.001' + currency: CNY diff --git a/models/llm/grok-4-1-fast-non-reasoning.yaml b/models/llm/grok-4-1-fast-non-reasoning.yaml new file mode 100644 index 0000000..fa53f03 --- /dev/null +++ b/models/llm/grok-4-1-fast-non-reasoning.yaml @@ -0,0 +1,35 @@ +model: grok-4-1-fast-non-reasoning +label: + zh_Hans: grok-4-1-fast-non-reasoning + en_US: grok-4-1-fast-non-reasoning +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/grok-4-1-fast-reasoning.yaml b/models/llm/grok-4-1-fast-reasoning.yaml new file mode 100644 index 0000000..8a2205a --- /dev/null +++ b/models/llm/grok-4-1-fast-reasoning.yaml @@ -0,0 +1,35 @@ +model: grok-4-1-fast-reasoning +label: + zh_Hans: grok-4-1-fast-reasoning + en_US: grok-4-1-fast-reasoning +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/grok-4-fast-reasoning.yaml b/models/llm/grok-4-fast-reasoning.yaml new file mode 100644 index 0000000..5011269 --- /dev/null +++ b/models/llm/grok-4-fast-reasoning.yaml @@ -0,0 +1,35 @@ +model: grok-4-fast-reasoning +label: + zh_Hans: grok-4-fast-reasoning + en_US: grok-4-fast-reasoning +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/grok-4-fast.yaml b/models/llm/grok-4-fast.yaml new file mode 100644 index 0000000..6d7f382 --- /dev/null +++ b/models/llm/grok-4-fast.yaml @@ -0,0 +1,35 @@ +model: grok-4-fast +label: + zh_Hans: grok-4-fast + en_US: grok-4-fast +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/grok-4.yaml b/models/llm/grok-4.yaml index ab98d0c..c9b8b2c 100644 --- a/models/llm/grok-4.yaml +++ b/models/llm/grok-4.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/kat-coder-256k.yaml b/models/llm/kat-coder-256k.yaml new file mode 100644 index 0000000..8019376 --- /dev/null +++ b/models/llm/kat-coder-256k.yaml @@ -0,0 +1,35 @@ +model: kat-coder-256k +label: + zh_Hans: kat-coder-256k + en_US: kat-coder-256k +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 256000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.015' + unit: '0.001' + currency: CNY diff --git a/models/llm/llm.py b/models/llm/llm.py index c5836df..0d21832 100644 --- a/models/llm/llm.py +++ b/models/llm/llm.py @@ -115,7 +115,7 @@ def _get_client(self, api_key: str) -> openai.OpenAI: if api_key not in self._client_cache: self._client_cache[api_key] = openai.OpenAI( api_key=api_key, - base_url="https://deepseek.modelverse.cn/v1" + base_url="https://api.modelverse.cn/v1" ) return self._client_cache[api_key] diff --git a/models/llm/moonshotai-kimi-k2-instruct-0905.yaml b/models/llm/moonshotai-kimi-k2-instruct-0905.yaml index 56a5a60..9f2f643 100644 --- a/models/llm/moonshotai-kimi-k2-instruct-0905.yaml +++ b/models/llm/moonshotai-kimi-k2-instruct-0905.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/moonshotai-kimi-k2-instruct.yaml b/models/llm/moonshotai-kimi-k2-instruct.yaml index 17bde53..8d3c39c 100644 --- a/models/llm/moonshotai-kimi-k2-instruct.yaml +++ b/models/llm/moonshotai-kimi-k2-instruct.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/moonshotai-kimi-k2-thinking.yaml b/models/llm/moonshotai-kimi-k2-thinking.yaml new file mode 100644 index 0000000..7debe88 --- /dev/null +++ b/models/llm/moonshotai-kimi-k2-thinking.yaml @@ -0,0 +1,35 @@ +model: moonshotai/Kimi-K2-Thinking +label: + zh_Hans: Kimi-K2-Thinking + en_US: Kimi-K2-Thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.016' + unit: '0.001' + currency: CNY diff --git a/models/llm/o1.yaml b/models/llm/o1.yaml new file mode 100644 index 0000000..cc01f6d --- /dev/null +++ b/models/llm/o1.yaml @@ -0,0 +1,35 @@ +model: o1 +label: + zh_Hans: o1 + en_US: o1 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.015' + output: '0.06' + unit: '0.001' + currency: CNY diff --git a/models/llm/o4-mini-deep-research.yaml b/models/llm/o4-mini-deep-research.yaml new file mode 100644 index 0000000..30370f8 --- /dev/null +++ b/models/llm/o4-mini-deep-research.yaml @@ -0,0 +1,35 @@ +model: o4-mini-deep-research +label: + zh_Hans: o4-mini-deep-research + en_US: o4-mini-deep-research +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/o4-mini.yaml b/models/llm/o4-mini.yaml new file mode 100644 index 0000000..5c30c09 --- /dev/null +++ b/models/llm/o4-mini.yaml @@ -0,0 +1,35 @@ +model: o4-mini +label: + zh_Hans: o4-mini + en_US: o4-mini +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 200000 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.003' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/openai-gpt-4.1.yaml b/models/llm/openai-gpt-4.1.yaml index 2c87a8f..827b817 100644 --- a/models/llm/openai-gpt-4.1.yaml +++ b/models/llm/openai-gpt-4.1.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/openai-gpt-4o.yaml b/models/llm/openai-gpt-4o.yaml index 3fdc643..bd43a8a 100644 --- a/models/llm/openai-gpt-4o.yaml +++ b/models/llm/openai-gpt-4o.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/openai-gpt-5-mini.yaml b/models/llm/openai-gpt-5-mini.yaml index fc7d440..00df82a 100644 --- a/models/llm/openai-gpt-5-mini.yaml +++ b/models/llm/openai-gpt-5-mini.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/openai-gpt-5-nano.yaml b/models/llm/openai-gpt-5-nano.yaml index 581b127..8a7b24d 100644 --- a/models/llm/openai-gpt-5-nano.yaml +++ b/models/llm/openai-gpt-5-nano.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/openai-gpt-5.1-chat.yaml b/models/llm/openai-gpt-5.1-chat.yaml new file mode 100644 index 0000000..0aa8769 --- /dev/null +++ b/models/llm/openai-gpt-5.1-chat.yaml @@ -0,0 +1,35 @@ +model: openai/gpt-5.1-chat +label: + zh_Hans: openai-gpt-5.1-chat + en_US: openai-gpt-5.1-chat +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.01' + output: '0.03' + unit: '0.001' + currency: CNY diff --git a/models/llm/openai-gpt-5.1.yaml b/models/llm/openai-gpt-5.1.yaml new file mode 100644 index 0000000..5e75519 --- /dev/null +++ b/models/llm/openai-gpt-5.1.yaml @@ -0,0 +1,35 @@ +model: openai/gpt-5.1 +label: + zh_Hans: openai-gpt-5.1 + en_US: openai-gpt-5.1 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.01' + output: '0.03' + unit: '0.001' + currency: CNY diff --git a/models/llm/openai-gpt-5.yaml b/models/llm/openai-gpt-5.yaml index fb39c62..09a7261 100644 --- a/models/llm/openai-gpt-5.yaml +++ b/models/llm/openai-gpt-5.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/openai-gpt-oss-120b.yaml b/models/llm/openai-gpt-oss-120b.yaml index cc44cc4..cfbaf92 100644 --- a/models/llm/openai-gpt-oss-120b.yaml +++ b/models/llm/openai-gpt-oss-120b.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/openai-gpt-oss-20b.yaml b/models/llm/openai-gpt-oss-20b.yaml index 505a143..818781c 100644 --- a/models/llm/openai-gpt-oss-20b.yaml +++ b/models/llm/openai-gpt-oss-20b.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/qwen-plus-thinking.yaml b/models/llm/qwen-plus-thinking.yaml new file mode 100644 index 0000000..ce5d971 --- /dev/null +++ b/models/llm/qwen-plus-thinking.yaml @@ -0,0 +1,35 @@ +model: Qwen/Qwen-Plus-Thinking +label: + zh_Hans: Qwen-Plus-Thinking + en_US: Qwen-Plus-Thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/qwen-plus.yaml b/models/llm/qwen-plus.yaml new file mode 100644 index 0000000..695e105 --- /dev/null +++ b/models/llm/qwen-plus.yaml @@ -0,0 +1,35 @@ +model: Qwen/Qwen-Plus +label: + zh_Hans: Qwen-Plus + en_US: Qwen-Plus +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/qwen-qwq-32b.yaml b/models/llm/qwen-qwq-32b.yaml index a9a8c7c..d7b90f2 100644 --- a/models/llm/qwen-qwq-32b.yaml +++ b/models/llm/qwen-qwq-32b.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/qwen2.5-vl-72b-instruct.yaml b/models/llm/qwen2.5-vl-72b-instruct.yaml index 8d6a43a..81e38fb 100644 --- a/models/llm/qwen2.5-vl-72b-instruct.yaml +++ b/models/llm/qwen2.5-vl-72b-instruct.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/qwen3-235b-a22b-thinking-2507.yaml b/models/llm/qwen3-235b-a22b-thinking-2507.yaml new file mode 100644 index 0000000..f723f49 --- /dev/null +++ b/models/llm/qwen3-235b-a22b-thinking-2507.yaml @@ -0,0 +1,35 @@ +model: Qwen/Qwen3-235B-A22B-Thinking-2507 +label: + zh_Hans: Qwen3-235B-A22B-Thinking-2507 + en_US: Qwen3-235B-A22B-Thinking-2507 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/qwen3-235b-a22b.yaml b/models/llm/qwen3-235b-a22b.yaml index 4adeac2..6742178 100644 --- a/models/llm/qwen3-235b-a22b.yaml +++ b/models/llm/qwen3-235b-a22b.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/qwen3-30b-a3b-thinking.yaml b/models/llm/qwen3-30b-a3b-thinking.yaml new file mode 100644 index 0000000..8e0d7f7 --- /dev/null +++ b/models/llm/qwen3-30b-a3b-thinking.yaml @@ -0,0 +1,35 @@ +model: Qwen/Qwen3-30B-A3B-Thinking +label: + zh_Hans: Qwen3-30B-A3B-Thinking + en_US: Qwen3-30B-A3B-Thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/qwen3-30b-a3b.yaml b/models/llm/qwen3-30b-a3b.yaml index baf38e7..023850a 100644 --- a/models/llm/qwen3-30b-a3b.yaml +++ b/models/llm/qwen3-30b-a3b.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/qwen3-32b-thinking.yaml b/models/llm/qwen3-32b-thinking.yaml new file mode 100644 index 0000000..34132e1 --- /dev/null +++ b/models/llm/qwen3-32b-thinking.yaml @@ -0,0 +1,35 @@ +model: Qwen/Qwen3-32B-Thinking +label: + zh_Hans: Qwen3-32B-Thinking + en_US: Qwen3-32B-Thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/qwen3-32b.yaml b/models/llm/qwen3-32b.yaml index 72ca31e..a996a94 100644 --- a/models/llm/qwen3-32b.yaml +++ b/models/llm/qwen3-32b.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/qwen3-coder.yaml b/models/llm/qwen3-coder.yaml index 3fc66f0..e12aba0 100644 --- a/models/llm/qwen3-coder.yaml +++ b/models/llm/qwen3-coder.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/qwen3-max.yaml b/models/llm/qwen3-max.yaml new file mode 100644 index 0000000..6d751fb --- /dev/null +++ b/models/llm/qwen3-max.yaml @@ -0,0 +1,35 @@ +model: Qwen/Qwen3-Max +label: + zh_Hans: Qwen3-Max + en_US: Qwen3-Max +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/qwen3-vl-235b-a22b-instruct.yaml b/models/llm/qwen3-vl-235b-a22b-instruct.yaml new file mode 100644 index 0000000..4988ade --- /dev/null +++ b/models/llm/qwen3-vl-235b-a22b-instruct.yaml @@ -0,0 +1,35 @@ +model: Qwen/Qwen3-VL-235B-A22B-Instruct +label: + zh_Hans: Qwen3-VL-235B-A22B-Instruct + en_US: Qwen3-VL-235B-A22B-Instruct +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/qwen3-vl-235b-a22b-thinking.yaml b/models/llm/qwen3-vl-235b-a22b-thinking.yaml new file mode 100644 index 0000000..3c577cb --- /dev/null +++ b/models/llm/qwen3-vl-235b-a22b-thinking.yaml @@ -0,0 +1,35 @@ +model: Qwen/Qwen3-VL-235B-A22B-Thinking +label: + zh_Hans: Qwen3-VL-235B-A22B-Thinking + en_US: Qwen3-VL-235B-A22B-Thinking +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/qwen3-vl-plus.yaml b/models/llm/qwen3-vl-plus.yaml new file mode 100644 index 0000000..c1fe548 --- /dev/null +++ b/models/llm/qwen3-vl-plus.yaml @@ -0,0 +1,35 @@ +model: Qwen/Qwen3-vl-Plus +label: + zh_Hans: Qwen3-vl-Plus + en_US: Qwen3-vl-Plus +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.012' + unit: '0.001' + currency: CNY diff --git a/models/llm/zai-org-glm-4.5.yaml b/models/llm/zai-org-glm-4.5.yaml index a13b97d..c90345a 100644 --- a/models/llm/zai-org-glm-4.5.yaml +++ b/models/llm/zai-org-glm-4.5.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/zai-org-glm-4.5v.yaml b/models/llm/zai-org-glm-4.5v.yaml index 3686d84..c94ae49 100644 --- a/models/llm/zai-org-glm-4.5v.yaml +++ b/models/llm/zai-org-glm-4.5v.yaml @@ -7,9 +7,11 @@ features: - multi-tool-call - agent-thought - stream-tool-call + - vision + - tool-call model_properties: mode: chat - context_size: 128000 + context_size: 204800 parameter_rules: - name: temperature use_template: temperature @@ -23,7 +25,7 @@ parameter_rules: use_template: max_tokens default: 512 min: 1 - max: 16385 + max: 65535 - name: response_format use_template: response_format pricing: diff --git a/models/llm/zai-org-glm-4.6.yaml b/models/llm/zai-org-glm-4.6.yaml new file mode 100644 index 0000000..8f77ec9 --- /dev/null +++ b/models/llm/zai-org-glm-4.6.yaml @@ -0,0 +1,35 @@ +model: zai-org/glm-4.6 +label: + zh_Hans: glm-4.6 + en_US: glm-4.6 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call + - vision + - tool-call +model_properties: + mode: chat + context_size: 204800 +parameter_rules: + - name: temperature + use_template: temperature + - name: top_p + use_template: top_p + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty + - name: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 65535 + - name: response_format + use_template: response_format +pricing: + input: '0.004' + output: '0.016' + unit: '0.001' + currency: CNY diff --git a/provider/modelverse.py b/provider/modelverse.py index d9a34e6..f073204 100644 --- a/provider/modelverse.py +++ b/provider/modelverse.py @@ -25,7 +25,7 @@ def validate_provider_credentials(self, credentials: Mapping) -> None: client = openai.OpenAI( api_key=api_key, - base_url="https://deepseek.modelverse.cn/v1" + base_url="https://api.modelverse.cn/v1" ) models_response = client.models.list() From d59b03c366a1b1e6a7bdce0dbee2a40fc579b1e4 Mon Sep 17 00:00:00 2001 From: "jason.mei" Date: Wed, 10 Dec 2025 19:27:01 +0800 Subject: [PATCH 2/2] add minifest --- manifest.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/manifest.yaml b/manifest.yaml index 63395cf..829386a 100644 --- a/manifest.yaml +++ b/manifest.yaml @@ -1,4 +1,4 @@ -version: 0.0.2 +version: 0.0.3 type: plugin author: ucloud name: "ucloud"