Breaking change: openrouter_models.json -> custom_models.json
* Support for Custom URLs and custom models, including locally hosted models such as ollama * Support for native + openrouter + local models (i.e. dozens of models) means you can start delegating sub-tasks to particular models or work to local models such as localizations or other boring work etc. * Several tests added * precommit to also include untracked (new) files * Logfile auto rollover * Improved logging
This commit is contained in:
Fahad
185
conf/custom_models.json
Normal file
185
conf/custom_models.json
Normal file
@@ -0,0 +1,185 @@
|
||||
{
|
||||
"_README": {
|
||||
"description": "Unified model configuration for multiple AI providers and endpoints, including OpenRouter",
|
||||
"providers_supported": [
|
||||
"OpenRouter - Access to GPT-4, Claude, Mistral, etc. via unified API",
|
||||
"Custom API endpoints - Local models (Ollama, vLLM, LM Studio, etc.)",
|
||||
"Self-hosted APIs - Any OpenAI-compatible endpoint"
|
||||
],
|
||||
"documentation": "https://github.com/BeehiveInnovations/zen-mcp-server/blob/main/docs/custom_models.md",
|
||||
"usage": "Models can be accessed via aliases (e.g., 'opus', 'local-llama') or full names (e.g., 'anthropic/claude-3-opus', 'llama3.2')",
|
||||
"instructions": [
|
||||
"Add new models by copying an existing entry and modifying it",
|
||||
"Aliases are case-insensitive and should be unique across all models",
|
||||
"context_window is the model's total context window size in tokens (input + output)",
|
||||
"Set supports_* flags based on the model's actual capabilities",
|
||||
"Models not listed here will use generic defaults (32K context window, basic features)",
|
||||
"For OpenRouter models: Use official OpenRouter model names (e.g., 'anthropic/claude-3-opus')",
|
||||
"For local/custom models: Use model names as they appear in your API (e.g., 'llama3.2', 'gpt-3.5-turbo')"
|
||||
],
|
||||
"field_descriptions": {
|
||||
"model_name": "The model identifier - OpenRouter format (e.g., 'anthropic/claude-3-opus') or custom model name (e.g., 'llama3.2')",
|
||||
"aliases": "Array of short names users can type instead of the full model name",
|
||||
"context_window": "Total number of tokens the model can process (input + output combined)",
|
||||
"supports_extended_thinking": "Whether the model supports extended reasoning tokens (currently none do via OpenRouter or custom APIs)",
|
||||
"supports_json_mode": "Whether the model can guarantee valid JSON output",
|
||||
"supports_function_calling": "Whether the model supports function/tool calling",
|
||||
"description": "Human-readable description of the model"
|
||||
},
|
||||
"example_custom_model": {
|
||||
"model_name": "vendor/model-name-version",
|
||||
"aliases": ["shortname", "nickname", "abbrev"],
|
||||
"context_window": 128000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": true,
|
||||
"supports_function_calling": true,
|
||||
"description": "Brief description of the model"
|
||||
}
|
||||
},
|
||||
"models": [
|
||||
{
|
||||
"model_name": "openai/gpt-4o",
|
||||
"aliases": ["gpt4o", "4o", "gpt-4o"],
|
||||
"context_window": 128000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": true,
|
||||
"supports_function_calling": true,
|
||||
"description": "OpenAI's most capable model, GPT-4 Optimized"
|
||||
},
|
||||
{
|
||||
"model_name": "openai/gpt-4o-mini",
|
||||
"aliases": ["gpt4o-mini", "4o-mini", "gpt-4o-mini"],
|
||||
"context_window": 128000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": true,
|
||||
"supports_function_calling": true,
|
||||
"description": "Smaller, faster version of GPT-4o"
|
||||
},
|
||||
{
|
||||
"model_name": "anthropic/claude-3-opus",
|
||||
"aliases": ["opus", "claude-opus", "claude3-opus", "claude-3-opus"],
|
||||
"context_window": 200000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": false,
|
||||
"supports_function_calling": false,
|
||||
"description": "Claude 3 Opus - Most capable Claude model"
|
||||
},
|
||||
{
|
||||
"model_name": "anthropic/claude-3-sonnet",
|
||||
"aliases": ["sonnet", "claude-sonnet", "claude3-sonnet", "claude-3-sonnet", "claude"],
|
||||
"context_window": 200000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": false,
|
||||
"supports_function_calling": false,
|
||||
"description": "Claude 3 Sonnet - Balanced performance"
|
||||
},
|
||||
{
|
||||
"model_name": "anthropic/claude-3-haiku",
|
||||
"aliases": ["haiku", "claude-haiku", "claude3-haiku", "claude-3-haiku"],
|
||||
"context_window": 200000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": false,
|
||||
"supports_function_calling": false,
|
||||
"description": "Claude 3 Haiku - Fast and efficient"
|
||||
},
|
||||
{
|
||||
"model_name": "google/gemini-pro-1.5",
|
||||
"aliases": ["pro","gemini-pro", "gemini", "pro-openrouter"],
|
||||
"context_window": 1048576,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": true,
|
||||
"supports_function_calling": false,
|
||||
"description": "Google's Gemini Pro 1.5 via OpenRouter"
|
||||
},
|
||||
{
|
||||
"model_name": "google/gemini-flash-1.5-8b",
|
||||
"aliases": ["flash","gemini-flash", "flash-openrouter", "flash-8b"],
|
||||
"context_window": 1048576,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": true,
|
||||
"supports_function_calling": false,
|
||||
"description": "Google's Gemini Flash 1.5 8B via OpenRouter"
|
||||
},
|
||||
{
|
||||
"model_name": "mistral/mistral-large",
|
||||
"aliases": ["mistral-large", "mistral"],
|
||||
"context_window": 128000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": true,
|
||||
"supports_function_calling": true,
|
||||
"description": "Mistral's largest model"
|
||||
},
|
||||
{
|
||||
"model_name": "meta-llama/llama-3-70b",
|
||||
"aliases": ["llama", "llama3", "llama3-70b", "llama-70b", "llama3-openrouter"],
|
||||
"context_window": 8192,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": false,
|
||||
"supports_function_calling": false,
|
||||
"description": "Meta's Llama 3 70B model"
|
||||
},
|
||||
{
|
||||
"model_name": "cohere/command-r-plus",
|
||||
"aliases": ["command-r-plus", "command-r", "cohere"],
|
||||
"context_window": 128000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": false,
|
||||
"supports_function_calling": true,
|
||||
"description": "Cohere's Command R Plus model"
|
||||
},
|
||||
{
|
||||
"model_name": "deepseek/deepseek-coder",
|
||||
"aliases": ["deepseek-coder", "deepseek", "coder"],
|
||||
"context_window": 16384,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": false,
|
||||
"supports_function_calling": false,
|
||||
"description": "DeepSeek's coding-focused model"
|
||||
},
|
||||
{
|
||||
"model_name": "perplexity/llama-3-sonar-large-32k-online",
|
||||
"aliases": ["perplexity", "sonar", "perplexity-online"],
|
||||
"context_window": 32768,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": false,
|
||||
"supports_function_calling": false,
|
||||
"description": "Perplexity's online model with web search"
|
||||
},
|
||||
{
|
||||
"model_name": "openai/o3",
|
||||
"aliases": ["o3"],
|
||||
"context_window": 200000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": true,
|
||||
"supports_function_calling": true,
|
||||
"description": "OpenAI's o3 model - well-rounded and powerful across domains"
|
||||
},
|
||||
{
|
||||
"model_name": "openai/o3-mini",
|
||||
"aliases": ["o3-mini", "o3mini"],
|
||||
"context_window": 200000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": true,
|
||||
"supports_function_calling": true,
|
||||
"description": "OpenAI's o3-mini reasoning model - cost-efficient with STEM performance"
|
||||
},
|
||||
{
|
||||
"model_name": "openai/o3-mini-high",
|
||||
"aliases": ["o3-mini-high", "o3mini-high"],
|
||||
"context_window": 200000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": true,
|
||||
"supports_function_calling": true,
|
||||
"description": "OpenAI's o3-mini with high reasoning effort - optimized for complex problems"
|
||||
},
|
||||
{
|
||||
"model_name": "llama3.2",
|
||||
"aliases": ["local-llama", "local", "llama3.2", "ollama-llama"],
|
||||
"context_window": 128000,
|
||||
"supports_extended_thinking": false,
|
||||
"supports_json_mode": false,
|
||||
"supports_function_calling": false,
|
||||
"description": "Local Llama 3.2 model via custom endpoint (Ollama/vLLM) - 128K context window"
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user