from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")

models = pc.inference.list_models()

print(models)

[{
    "model": "llama-text-embed-v2",
    "short_description": "A high performance dense embedding model optimized for multilingual and cross-lingual text question-answering retrieval with support for long documents (up to 2048 tokens) and dynamic embedding size (Matryoshka Embeddings).",
    "type": "embed",
    "supported_parameters": [
        {
            "parameter": "input_type",
            "type": "one_of",
            "value_type": "string",
            "required": true,
            "allowed_values": [
                "query",
                "passage"
            ]
        },
        {
            "parameter": "truncate",
            "type": "one_of",
            "value_type": "string",
            "required": false,
            "default": "END",
            "allowed_values": [
                "END",
                "NONE",
                "START"
            ]
        },
        {
            "parameter": "dimension",
            "type": "one_of",
            "value_type": "integer",
            "required": false,
            "default": 1024,
            "allowed_values": [
                384,
                512,
                768,
                1024,
                2048
            ]
        }
    ],
    "vector_type": "dense",
    "default_dimension": 1024,
    "modality": "text",
    "max_sequence_length": 2048,
    "max_batch_size": 96,
    "provider_name": "NVIDIA",
    "supported_metrics": [
        "cosine",
        "dotproduct"
    ],
    "supported_dimensions": [
        384,
        512,
        768,
        1024,
        2048
    ]
}, {
    "model": "multilingual-e5-large",
    "short_description": "A high-performance dense embedding model trained on a mixture of multilingual datasets. It works well on messy data and short queries expected to return medium-length passages of text (1-2 paragraphs)",
    "type": "embed",
    "supported_parameters": [
        {
            "parameter": "input_type",
            "type": "one_of",
            "value_type": "string",
            "required": true,
            "allowed_values": [
                "query",
                "passage"
            ]
        },
        {
            "parameter": "truncate",
            "type": "one_of",
            "value_type": "string",
            "required": false,
            "default": "END",
            "allowed_values": [
                "END",
                "NONE"
            ]
        }
    ],
    "vector_type": "dense",
    "default_dimension": 1024,
    "modality": "text",
    "max_sequence_length": 507,
    "max_batch_size": 96,
    "provider_name": "Microsoft",
    "supported_metrics": [
        "cosine",
        "euclidean"
    ],
    "supported_dimensions": [
        1024
    ]
}, {
    "model": "pinecone-sparse-english-v0",
    "short_description": "A sparse embedding model for converting text to sparse vectors for keyword or hybrid semantic/keyword search. Built on the innovations of the DeepImpact architecture.",
    "type": "embed",
    "supported_parameters": [
        {
            "parameter": "input_type",
            "type": "one_of",
            "value_type": "string",
            "required": true,
            "allowed_values": [
                "query",
                "passage"
            ]
        },
        {
            "parameter": "truncate",
            "type": "one_of",
            "value_type": "string",
            "required": false,
            "default": "END",
            "allowed_values": [
                "END",
                "NONE"
            ]
        },
        {
            "parameter": "return_tokens",
            "type": "any",
            "value_type": "boolean",
            "required": false,
            "default": false
        }
    ],
    "vector_type": "sparse",
    "modality": "text",
    "max_sequence_length": 512,
    "max_batch_size": 96,
    "provider_name": "Pinecone",
    "supported_metrics": [
        "dotproduct"
    ]
}, {
    "model": "bge-reranker-v2-m3",
    "short_description": "A high-performance, multilingual reranking model that works well on messy data and short queries expected to return medium-length passages of text (1-2 paragraphs)",
    "type": "rerank",
    "supported_parameters": [
        {
            "parameter": "truncate",
            "type": "one_of",
            "value_type": "string",
            "required": false,
            "default": "NONE",
            "allowed_values": [
                "END",
                "NONE"
            ]
        }
    ],
    "modality": "text",
    "max_sequence_length": 1024,
    "max_batch_size": 100,
    "provider_name": "BAAI",
    "supported_metrics": []
}, {
    "model": "cohere-rerank-3.5",
    "short_description": "Cohere's leading reranking model, balancing performance and latency for a wide range of enterprise search applications.",
    "type": "rerank",
    "supported_parameters": [
        {
            "parameter": "max_chunks_per_doc",
            "type": "numeric_range",
            "value_type": "integer",
            "required": false,
            "default": 3072,
            "min": 1.0,
            "max": 3072.0
        }
    ],
    "modality": "text",
    "max_sequence_length": 40000,
    "max_batch_size": 200,
    "provider_name": "Cohere",
    "supported_metrics": []
}, {
    "model": "pinecone-rerank-v0",
    "short_description": "A state of the art reranking model that out-performs competitors on widely accepted benchmarks. It can handle chunks up to 512 tokens (1-2 paragraphs)",
    "type": "rerank",
    "supported_parameters": [
        {
            "parameter": "truncate",
            "type": "one_of",
            "value_type": "string",
            "required": false,
            "default": "END",
            "allowed_values": [
                "END",
                "NONE"
            ]
        }
    ],
    "modality": "text",
    "max_sequence_length": 512,
    "max_batch_size": 100,
    "provider_name": "Pinecone",
    "supported_metrics": []
}]