torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Differentiate custom from openrouter models

Browse Source 
Split readme into multiple docs
This commit is contained in:
Fahad
2025-06-13 15:59:48 +04:00
parent cf8fb04c1e
commit 6739182c20
8 changed files with 617 additions and 549 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
conf/custom_models.json
View File

@@ -13,6 +13,7 @@
"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')"
@@ -24,37 +25,21 @@
"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": "vendor/model-name-version",
"model_name": "my-local-model",
"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"
"is_custom": true,
"description": "Example custom/local model for Ollama, vLLM, etc."
}
},
"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"],
@@ -83,22 +68,22 @@
"description": "Claude 3 Haiku - Fast and efficient"
},
{
"model_name": "google/gemini-pro-1.5",
"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 Pro 1.5 via OpenRouter"
"description": "Google's Gemini 2.5 Pro via OpenRouter"
},
{
"model_name": "google/gemini-flash-1.5-8b",
"aliases": ["flash","gemini-flash", "flash-openrouter", "flash-8b"],
"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 Flash 1.5 8B via OpenRouter"
"description": "Google's Gemini 2.5 Flash via OpenRouter"
},
{
"model_name": "mistral/mistral-large",
@@ -119,22 +104,13 @@
"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,
"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's coding-focused model"
"description": "DeepSeek R1 with thinking mode - advanced reasoning capabilities"
},
{
"model_name": "perplexity/llama-3-sonar-large-32k-online",
@@ -154,18 +130,9 @@
"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"],
"aliases": ["o3-mini", "o3mini", "o3-mini-high", "o3mini-high"],
"context_window": 200000,
"supports_extended_thinking": false,
"supports_json_mode": true,
@@ -179,6 +146,7 @@
"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"
}
]