BerriAI/litellm · error · ValueError

Unsupported MIME type for embedding: {media_type}. Supported

Error message

Unsupported MIME type for embedding: {media_type}. Supported types: {', '.join(sorted(SUPPORTED_EMBEDDING_MIME_TYPES))}

What it means

Gemini data-URL parser guard: the declared media_type is not within SUPPORTED_EMBEDDING_MIME_TYPES, so the payload cannot be embedded by Gemini multimodal embedding and is rejected with the allowed list.

Source

Thrown at litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:119

        ValueError: If data URL format is invalid or MIME type is unsupported
    """
    if not data_url.startswith("data:"):
        raise ValueError(f"Invalid data URL format: {data_url[:50]}...")

    if "," not in data_url:
        raise ValueError(f"Invalid data URL format (missing comma): {data_url[:50]}...")

    metadata, base64_data = data_url.split(",", 1)

    metadata = metadata[5:]

    if ";" in metadata:
        media_type = metadata.split(";")[0]
    else:
        media_type = metadata

    if media_type not in SUPPORTED_EMBEDDING_MIME_TYPES:
        raise ValueError(
            f"Unsupported MIME type for embedding: {media_type}. "
            f"Supported types: {', '.join(sorted(SUPPORTED_EMBEDDING_MIME_TYPES))}"
        )

    return media_type, base64_data


def _is_multimodal_input(input: GeminiEmbeddingInput) -> bool:
    """
    Check if the input contains multimodal data (data URIs, file references,
    GCS URLs, or nested lists for combined embeddings).

    Args:
        input: GeminiEmbeddingInput — str, List[str], or List[List[str]] for combined embeddings

    Returns:
        bool: True if any element is multimodal or a nested list
    """

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Use one of the supported MIME types listed in the error (e.g. image/png, image/jpeg) for the media you embed.
2. Convert the file to a supported format before embedding, or correct the mime_type parameter passed for the media.

When it happens

Trigger: Thrown at litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:119 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/e7912348a52eee7d. Report an issue: GitHub.