BerriAI/litellm · error · Exception

Unable to parse anthropic file message: {message}

Error message

Unable to parse anthropic file message: {message}

What it means

While converting a file content block for Anthropic: file_data/file_id was present, but the block's type was not one of the handled kinds (e.g. 'image', 'document', 'container_upload' branches), so return_block_param stayed None. The error includes the full message so you can see the unsupported type value.

Source

Thrown at litellm/litellm_core_utils/prompt_templates/factory.py:1969

                type="document",
                source=AnthropicContentParamSourceUrl(
                    type="url",
                    url=file_id,
                ),
            )
        elif content_block_type == "image":
            return_block_param = AnthropicMessagesImageParam(
                type="image",
                source=AnthropicContentParamSourceFileId(
                    type="file",
                    file_id=file_id,
                ),
            )
        elif content_block_type == "container_upload":
            return_block_param = AnthropicMessagesContainerUploadParam(type="container_upload", file_id=file_id)

        if return_block_param is None:
            raise Exception(f"Unable to parse anthropic file message: {message}")
        return return_block_param
    raise Exception(f"Either file_data or file_id must be present in the file message: {message}")


_EMPTY_TEXT_PLACEHOLDER: Final = "[System: Empty message content sanitised to satisfy protocol]"


def _sanitize_empty_text_content(
    message: AllMessageValues,
) -> AllMessageValues:
    """
    Case C: Sanitize empty text content
    - Replace empty or whitespace-only text content with a placeholder message.
    - Handles both string content and list-of-blocks content (rewriting only
      the empty text blocks in place; non-text blocks like images are left
      untouched).

    Returns:

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Use a supported content_block_type: 'image', 'document', or 'container_upload' (per this source)
2. Upgrade LiteLLM to a version that supports the file block type you are sending
3. Convert the file to a supported representation, e.g. inline PDF bytes as a base64 document source instead

Example fix

# before
{"type": "file", "file": {"file_id": "file_abc", "content_block_type": "audio"}}

# after
{"type": "file", "file": {"file_id": "file_abc", "content_block_type": "document"}}

SUPPORTED_FILE_BLOCK_TYPES = {"image", "document", "container_upload"}

def validate_file_blocks(messages) -> None:
    for m in messages:
        for block in m.get("content", []) if isinstance(m.get("content"), list) else []:
            if isinstance(block, dict) and block.get("type") == "file":
                cbt = block.get("file", {}).get("content_block_type")
                if cbt not in SUPPORTED_FILE_BLOCK_TYPES:
                    raise ValueError(f"unsupported file content_block_type: {cbt}")

from typing import Any

_OK = {"image", "document", "container_upload"}

def is_supported_file_block(block: Any) -> bool:
    return (
        isinstance(block, dict)
        and block.get("type") == "file"
        and isinstance(block.get("file"), dict)
        and block["file"].get("content_block_type") in _OK
    )

When it happens

Trigger: Sending {"type": "file", "file": {"file_id": ..., "content_block_type": "audio"}} (or any unrecognized content_block_type) to a Claude model; content_block_type values introduced by newer API versions that this LiteLLM version does not map.

Common situations: Forwarding raw Anthropic API file blocks that use newer content types; mismatches between the content_block_type string stored by your app and what this LiteLLM release supports (upgrade fixes new types).

Understand the failure class

• Parsing and encoding errors: unexpected token, malformed input — why parsers reject input and how to find the real culprit.

Related errors

• Either file_data or file_id must be present in the file mess
• file_id is required in file_content_request
• File data is required
• WebSearchInterception: missing follow-up messages
• file_id and file_data are both None

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/aa89f4e284129f86. Report an issue: GitHub.