{
    "chat": {
        "llama3.2:3b": {
            "description": "Meta's Llama 3.2 model with 3 billion parameters.",
            "inputTokens": 8192,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "llama3.2:1b": {
            "description": "Meta's Llama 3.2 model with 1 billion parameters.",
            "inputTokens": 8192,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "llama3.1:405b": {
            "description": "Llama 3.1 is a new state-of-the-art model from Meta. 405 billion parameters.",
            "inputTokens": 8192,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "llama3.1:70b": {
            "description": "Llama 3.1 is a new state-of-the-art model from Meta. 70 billion parameters.",
            "inputTokens": 8192,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "llama3.1:8b": {
            "description": "Llama 3.1 is a new state-of-the-art model from Meta. 8 billion parameters.",
            "inputTokens": 8192,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "gemma2:27b": {
            "description": "Google Gemma 2 is a high-performing and efficient model. 27 billion parameters.",
            "inputTokens": 4096,
            "inputTokenPrice": 0,
            "outputTokens": 4096,
            "outputTokenPrice": 0
        },
        "gemma2:9b": {
            "description": "Google Gemma 2 is a high-performing and efficient model. 9 billion parameters.",
            "inputTokens": 4096,
            "inputTokenPrice": 0,
            "outputTokens": 4096,
            "outputTokenPrice": 0
        },
        "gemma2:2b": {
            "description": "Google Gemma 2 is a high-performing and efficient model. 2 billion parameters.",
            "inputTokens": 4096,
            "inputTokenPrice": 0,
            "outputTokens": 4096,
            "outputTokenPrice": 0
        },
        "qwen2.5:72b": {
            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 72 billion parameters.",
            "inputTokens": 128000,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "qwen2.5:32b": {
            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 32 billion parameters.",
            "inputTokens": 128000,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "qwen2.5:14b": {
            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 14 billion parameters.",
            "inputTokens": 128000,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "qwen2.5:7b": {
            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 7 billion parameters.",
            "inputTokens": 128000,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "qwen2.5:3b": {
            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 3 billion parameters.",
            "inputTokens": 128000,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "qwen2.5:1.5b": {
            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 1.5 billion parameters.",
            "inputTokens": 128000,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        },
        "qwen2.5:0.5b": {
            "description": "Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset. 0.5 billion parameters.",
            "inputTokens": 128000,
            "inputTokenPrice": 0,
            "outputTokens": 8192,
            "outputTokenPrice": 0
        }
    },
    "embedding": {
        "nomic-embed-text": {
            "description": "A high-performing open embedding model with a large token context window.",
            "inputTokens": 8192,
            "inputTokenPrice": 0,
            "dimensions": 768
        },
        "mxbai-embed-large": {
            "description": "State-of-the-art large embedding model from mixedbread.ai",
            "inputTokens": 512,
            "inputTokenPrice": 0,
            "dimensions": 1024
        },
        "all-minilm": {
            "description": "The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective.",
            "inputTokens": 256,
            "inputTokenPrice": 0,
            "dimensions": 384
        },
        "bge-large": {
            "description": "Embedding model from BAAI mapping texts to vectors.",
            "inputTokens": 512,
            "inputTokenPrice": 0,
            "dimensions": 1024
        }
    }
}