[
  {
    "model": "o4-mini",
    "category": "Reasoning",
    "supported_parameters": ["input", "max_output_tokens"],
    "endpoint": "https://api.openai.com/v1/responses",
    "description": "Faster, more affordable reasoning model",
    "provider": "openai"
  },
  {
    "model": "o3",
    "category": "Reasoning",
    "supported_parameters": ["input", "max_output_tokens"],
    "endpoint": "https://api.openai.com/v1/responses",
    "description": "Our most powerful reasoning model",
    "provider": "openai"
  },
  {
    "model": "o3-pro",
    "category": "Reasoning",
    "supported_parameters": ["input", "max_output_tokens"],
    "endpoint": "https://api.openai.com/v1/responses",
    "description": "Version of o3 with more compute for better responses",
    "provider": "openai"
  },
  {
    "model": "o3-mini",
    "category": "Reasoning",
    "supported_parameters": ["input", "max_output_tokens"],
    "endpoint": "https://api.openai.com/v1/responses",
    "description": "A small model alternative to o3",
    "provider": "openai"
  },
  {
    "model": "gpt-4.1",
    "category": "Flagship Chat",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "Flagship GPT model for complex tasks",
    "provider": "openai"
  },
  {
    "model": "gpt-4o",
    "category": "Flagship Chat",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "Fast, intelligent, flexible GPT model",
    "provider": "openai"
  },
  {
    "model": "gpt-4-turbo",
    "category": "Flagship Chat",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "High-performance GPT-4 model optimized for speed and efficiency",
    "provider": "openai"
  },
  {
    "model": "gpt-4",
    "category": "Flagship Chat",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "Original GPT-4 model for complex reasoning and language tasks",
    "provider": "openai"
  },
  {
    "model": "gpt-5",
    "category": "Flagship Chat",
    "supported_parameters": ["input", "max_output_tokens"],
    "endpoint": "https://api.openai.com/v1/responses",
    "description": "The best model for coding and agentic tasks across domains",
    "provider": "openai"
  },
  {
    "model": "gpt-5-mini",
    "category": "Flagship Chat",
    "supported_parameters": ["input", "max_output_tokens"],
    "endpoint": "https://api.openai.com/v1/responses",
    "description": "A faster, more cost-efficient version of GPT-5 for well-defined tasks",
    "provider": "openai"
  },
  {
    "model": "gpt-3.5-turbo-16k",
    "category": "Legacy Chat",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "GPT-3.5 model with extended 16K token context",
    "provider": "openai"
  },
  {
    "model": "gpt-3.5-turbo-0125",
    "category": "Legacy Chat",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "January 25 update of GPT-3.5 Turbo",
    "provider": "openai"
  },
  {
    "model": "gpt-3.5-turbo",
    "category": "Legacy Chat",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "Efficient and cost-effective GPT-3.5 Turbo model",
    "provider": "openai"
  },
  {
    "model": "gpt-4.1-mini",
    "category": "Cost-Optimized",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "Balanced for intelligence, speed, and cost",
    "provider": "openai"
  },
  {
    "model": "gpt-4.1-nano",
    "category": "Cost-Optimized",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "Fastest, most cost-effective GPT-4.1 model",
    "provider": "openai"
  },
  {
    "model": "gpt-4o-mini",
    "category": "Cost-Optimized",
    "supported_parameters": ["messages", "temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty"],
    "endpoint": "https://api.openai.com/v1/chat/completions",
    "description": "Fast, affordable small model for focused tasks",
    "provider": "openai"
  }
]