154 lines
6.7 KiB
JSON
154 lines
6.7 KiB
JSON
{
|
|
"_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",
|
|
"Set is_custom=true for models that should ONLY work with custom endpoints (Ollama, vLLM, etc.)",
|
|
"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",
|
|
"is_custom": "Set to true for models that should ONLY be used with custom API endpoints (Ollama, vLLM, etc.). False or omitted for OpenRouter/cloud models.",
|
|
"description": "Human-readable description of the model"
|
|
},
|
|
"example_custom_model": {
|
|
"model_name": "my-local-model",
|
|
"aliases": ["shortname", "nickname", "abbrev"],
|
|
"context_window": 128000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"is_custom": true,
|
|
"description": "Example custom/local model for Ollama, vLLM, etc."
|
|
}
|
|
},
|
|
"models": [
|
|
{
|
|
"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-2.5-pro-preview",
|
|
"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 2.5 Pro via OpenRouter"
|
|
},
|
|
{
|
|
"model_name": "google/gemini-2.5-flash-preview-05-20",
|
|
"aliases": ["flash","gemini-flash", "flash-openrouter", "flash-2.5"],
|
|
"context_window": 1048576,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": false,
|
|
"description": "Google's Gemini 2.5 Flash 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": "deepseek/deepseek-r1-0528",
|
|
"aliases": ["deepseek-r1", "deepseek", "r1", "deepseek-thinking"],
|
|
"context_window": 65536,
|
|
"supports_extended_thinking": true,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": false,
|
|
"description": "DeepSeek R1 with thinking mode - advanced reasoning capabilities"
|
|
},
|
|
{
|
|
"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-high",
|
|
"aliases": ["o3-mini", "o3mini", "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,
|
|
"is_custom": true,
|
|
"description": "Local Llama 3.2 model via custom endpoint (Ollama/vLLM) - 128K context window"
|
|
}
|
|
]
|
|
}
|