09d6ba4eac
Adding max token for consistency per review comment Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
288 lines
12 KiB
JSON
288 lines
12 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-opus-4', '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-opus-4')",
|
|
"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-opus-4') 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)",
|
|
"max_output_tokens": "Maximum number of tokens the model can generate in a single response",
|
|
"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",
|
|
"supports_images": "Whether the model can process images/visual input",
|
|
"max_image_size_mb": "Maximum total size in MB for all images combined (capped at 40MB max for custom models)",
|
|
"supports_temperature": "Whether the model accepts temperature parameter in API calls (set to false for O3/O4 reasoning models)",
|
|
"temperature_constraint": "Type of temperature constraint: 'fixed' (fixed value), 'range' (continuous range), 'discrete' (specific values), or omit for default range",
|
|
"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,
|
|
"max_output_tokens": 32768,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 10.0,
|
|
"supports_temperature": true,
|
|
"temperature_constraint": "range",
|
|
"is_custom": true,
|
|
"description": "Example custom/local model for Ollama, vLLM, etc."
|
|
}
|
|
},
|
|
"models": [
|
|
{
|
|
"model_name": "anthropic/claude-opus-4.1",
|
|
"aliases": ["opus", "claude-opus", "claude-opus-4.1", "claude-4.1-opus"],
|
|
"context_window": 200000,
|
|
"max_output_tokens": 64000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": false,
|
|
"supports_function_calling": false,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 5.0,
|
|
"description": "Claude Opus 4.1 - Our most capable and intelligent model yet"
|
|
},
|
|
{
|
|
"model_name": "anthropic/claude-sonnet-4.1",
|
|
"aliases": ["sonnet", "claude-sonnet", "claude-sonnet-4.1", "claude-4.1-sonnet", "claude"],
|
|
"context_window": 200000,
|
|
"max_output_tokens": 64000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": false,
|
|
"supports_function_calling": false,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 5.0,
|
|
"description": "Claude Sonnet 4.1 - High-performance model with exceptional reasoning and efficiency"
|
|
},
|
|
{
|
|
"model_name": "anthropic/claude-3.5-haiku",
|
|
"aliases": ["haiku", "claude-haiku", "claude3-haiku", "claude-3-haiku"],
|
|
"context_window": 200000,
|
|
"max_output_tokens": 64000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": false,
|
|
"supports_function_calling": false,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 5.0,
|
|
"description": "Claude 3 Haiku - Fast and efficient with vision"
|
|
},
|
|
{
|
|
"model_name": "google/gemini-2.5-pro",
|
|
"aliases": ["pro","gemini-pro", "gemini", "pro-openrouter"],
|
|
"context_window": 1048576,
|
|
"max_output_tokens": 65536,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": false,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 20.0,
|
|
"description": "Google's Gemini 2.5 Pro via OpenRouter with vision"
|
|
},
|
|
{
|
|
"model_name": "google/gemini-2.5-flash",
|
|
"aliases": ["flash","gemini-flash", "flash-openrouter", "flash-2.5"],
|
|
"context_window": 1048576,
|
|
"max_output_tokens": 65536,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": false,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 15.0,
|
|
"description": "Google's Gemini 2.5 Flash via OpenRouter with vision"
|
|
},
|
|
{
|
|
"model_name": "mistralai/mistral-large-2411",
|
|
"aliases": ["mistral-large", "mistral"],
|
|
"context_window": 128000,
|
|
"max_output_tokens": 32000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": false,
|
|
"max_image_size_mb": 0.0,
|
|
"description": "Mistral's largest model (text-only)"
|
|
},
|
|
{
|
|
"model_name": "meta-llama/llama-3-70b",
|
|
"aliases": ["llama", "llama3", "llama3-70b", "llama-70b", "llama3-openrouter"],
|
|
"context_window": 8192,
|
|
"max_output_tokens": 8192,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": false,
|
|
"supports_function_calling": false,
|
|
"supports_images": false,
|
|
"max_image_size_mb": 0.0,
|
|
"description": "Meta's Llama 3 70B model (text-only)"
|
|
},
|
|
{
|
|
"model_name": "deepseek/deepseek-r1-0528",
|
|
"aliases": ["deepseek-r1", "deepseek", "r1", "deepseek-thinking"],
|
|
"context_window": 65536,
|
|
"max_output_tokens": 32768,
|
|
"supports_extended_thinking": true,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": false,
|
|
"supports_images": false,
|
|
"max_image_size_mb": 0.0,
|
|
"description": "DeepSeek R1 with thinking mode - advanced reasoning capabilities (text-only)"
|
|
},
|
|
{
|
|
"model_name": "perplexity/llama-3-sonar-large-32k-online",
|
|
"aliases": ["perplexity", "sonar", "perplexity-online"],
|
|
"context_window": 32768,
|
|
"max_output_tokens": 32768,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": false,
|
|
"supports_function_calling": false,
|
|
"supports_images": false,
|
|
"max_image_size_mb": 0.0,
|
|
"description": "Perplexity's online model with web search (text-only)"
|
|
},
|
|
{
|
|
"model_name": "openai/o3",
|
|
"aliases": ["o3"],
|
|
"context_window": 200000,
|
|
"max_output_tokens": 100000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 20.0,
|
|
"supports_temperature": false,
|
|
"temperature_constraint": "fixed",
|
|
"description": "OpenAI's o3 model - well-rounded and powerful across domains with vision"
|
|
},
|
|
{
|
|
"model_name": "openai/o3-mini",
|
|
"aliases": ["o3-mini", "o3mini"],
|
|
"context_window": 200000,
|
|
"max_output_tokens": 100000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 20.0,
|
|
"supports_temperature": false,
|
|
"temperature_constraint": "fixed",
|
|
"description": "OpenAI's o3-mini model - balanced performance and speed with vision"
|
|
},
|
|
{
|
|
"model_name": "openai/o3-mini-high",
|
|
"aliases": ["o3-mini-high", "o3mini-high"],
|
|
"context_window": 200000,
|
|
"max_output_tokens": 100000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 20.0,
|
|
"supports_temperature": false,
|
|
"temperature_constraint": "fixed",
|
|
"description": "OpenAI's o3-mini with high reasoning effort - optimized for complex problems with vision"
|
|
},
|
|
{
|
|
"model_name": "openai/o3-pro",
|
|
"aliases": ["o3-pro", "o3pro"],
|
|
"context_window": 200000,
|
|
"max_output_tokens": 100000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 20.0,
|
|
"supports_temperature": false,
|
|
"temperature_constraint": "fixed",
|
|
"description": "OpenAI's o3-pro model - professional-grade reasoning and analysis with vision"
|
|
},
|
|
{
|
|
"model_name": "openai/o4-mini",
|
|
"aliases": ["o4-mini", "o4mini"],
|
|
"context_window": 200000,
|
|
"max_output_tokens": 100000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 20.0,
|
|
"supports_temperature": false,
|
|
"temperature_constraint": "fixed",
|
|
"description": "OpenAI's o4-mini model - optimized for shorter contexts with rapid reasoning and vision"
|
|
},
|
|
{
|
|
"model_name": "gpt-5",
|
|
"aliases": ["gpt5", "gpt-5"],
|
|
"context_window": 400000,
|
|
"max_output_tokens": 128000,
|
|
"supports_extended_thinking": true,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 20.0,
|
|
"supports_temperature": true,
|
|
"temperature_constraint": "range",
|
|
"description": "GPT-5 (400K context, 128K output) - Advanced model with reasoning support"
|
|
},
|
|
{
|
|
"model_name": "gpt-5-mini",
|
|
"aliases": ["gpt5-mini", "gpt5mini", "mini"],
|
|
"context_window": 400000,
|
|
"max_output_tokens": 128000,
|
|
"supports_extended_thinking": true,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 20.0,
|
|
"supports_temperature": true,
|
|
"temperature_constraint": "fixed",
|
|
"description": "GPT-5-mini (400K context, 128K output) - Efficient variant with reasoning support"
|
|
},
|
|
{
|
|
"model_name": "gpt-5-nano",
|
|
"aliases": ["gpt5nano", "gpt5-nano", "nano"],
|
|
"context_window": 400000,
|
|
"max_output_tokens": 128000,
|
|
"supports_extended_thinking": true,
|
|
"supports_json_mode": true,
|
|
"supports_function_calling": true,
|
|
"supports_images": true,
|
|
"max_image_size_mb": 20.0,
|
|
"supports_temperature": true,
|
|
"temperature_constraint": "fixed",
|
|
"description": "GPT-5 nano (400K context, 128K output) - Fastest, cheapest version of GPT-5 for summarization and classification tasks"
|
|
},
|
|
{
|
|
"model_name": "llama3.2",
|
|
"aliases": ["local-llama", "local", "llama3.2", "ollama-llama"],
|
|
"context_window": 128000,
|
|
"max_output_tokens": 64000,
|
|
"supports_extended_thinking": false,
|
|
"supports_json_mode": false,
|
|
"supports_function_calling": false,
|
|
"supports_images": false,
|
|
"max_image_size_mb": 0.0,
|
|
"is_custom": true,
|
|
"description": "Local Llama 3.2 model via custom endpoint (Ollama/vLLM) - 128K context window (text-only)"
|
|
}
|
|
]
|
|
}
|