BerriAI/litellm · error · ValueError

image_response must be of type ImageResponse got type={type(

Error message

image_response must be of type ImageResponse got type={type(image_response)}

What it means

Error "image_response must be of type ImageResponse got type={type(image_response)}" thrown in BerriAI/litellm.

Source

Thrown at litellm/llms/gemini/image_generation/cost_calculator.py:28

    calculate_image_response_web_search_cost,
)
from litellm.types.utils import ImageResponse


def cost_calculator(
    model: str,
    image_response: Any,
) -> float:
    """
    Google AI Image Generation Cost Calculator
    """
    _model_info: Final = litellm.get_model_info(
        model=model,
        custom_llm_provider="gemini",
    )

    if not isinstance(image_response, ImageResponse):
        raise ValueError(f"image_response must be of type ImageResponse got type={type(image_response)}")

    web_search_cost: Final = calculate_image_response_web_search_cost(
        image_response=image_response,
        custom_llm_provider="gemini",
        model_info=_model_info,
    )

    token_based_cost: Final = calculate_image_response_cost_from_usage(
        model=model,
        image_response=image_response,
        custom_llm_provider="gemini",
    )
    if token_based_cost is not None:
        return token_based_cost + web_search_cost

    output_cost_per_image: Final[float] = _model_info.get("output_cost_per_image") or 0.0
    num_images: Final[int] = len(image_response.data) if image_response.data else 0
    return output_cost_per_image * num_images + web_search_cost

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Pass an ImageResponse object to the Gemini image cost calculator.

When it happens

Trigger: Thrown at litellm/llms/gemini/image_generation/cost_calculator.py:28 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/24b85de84e3ef27f. Report an issue: GitHub.