BerriAI/litellm · error · ValueError

LiteLLM's `gemini/` route does not support image generation

Error message

LiteLLM's `gemini/` route does not support image generation yet. Let us know if you need this feature by opening an issue at https://github.com/BerriAI/litellm/issues

What it means

Error "LiteLLM's `gemini/` route does not support image generation yet. Let us know if you need this feature by opening an issue at https://github.com/BerriAI/litellm/issues" thrown in BerriAI/litellm.

Source

Thrown at litellm/llms/vertex_ai/common_utils.py:485

    if mode == "chat":
        endpoint = "generateContent"
        if stream is True:
            endpoint = "streamGenerateContent"
            url = f"https://generativelanguage.googleapis.com/{api_version}/{_gemini_model_name}:{endpoint}?alt=sse"
        else:
            url = f"https://generativelanguage.googleapis.com/{api_version}/{_gemini_model_name}:{endpoint}"
    elif mode == "embedding":
        endpoint = "embedContent"
        url = f"https://generativelanguage.googleapis.com/v1beta/{_gemini_model_name}:{endpoint}"
    elif mode == "batch_embedding":
        endpoint = "batchEmbedContents"
        url = f"https://generativelanguage.googleapis.com/v1beta/{_gemini_model_name}:{endpoint}"
    elif mode == "count_tokens":
        endpoint = "countTokens"
        url = f"https://generativelanguage.googleapis.com/v1beta/{_gemini_model_name}:{endpoint}"
    elif mode == "image_generation":
        raise ValueError(
            "LiteLLM's `gemini/` route does not support image generation yet. Let us know if you need this feature by opening an issue at https://github.com/BerriAI/litellm/issues"
        )
    else:
        raise ValueError(f"Unsupported mode: {mode}")

    return url, endpoint


def _check_text_in_content(parts: list[PartType]) -> bool:
    """
    check that user_content has 'text' parameter.
        - Known Vertex Error: Unable to submit request because it must have a text parameter.
        - 'text' param needs to be present (empty strings are valid)
        - Relevant Issue: https://github.com/BerriAI/litellm/issues/5515
    """
    has_text_param = False
    for part in parts:
        if "text" in part and part.get("text") is not None:

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Use the vertex_ai/ route (e.g. vertex_ai/imagen-3.0-generate-001) for image generation instead of gemini/.
2. Or request support via the linked GitHub issue.

Example fix

litellm.image_generation(model="vertex_ai/imagen-3.0-generate-001", prompt=...)

When it happens

Trigger: Triggered when requesting image generation through LiteLLM's gemini/ route, which is not yet supported.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/23f1b559dfe4a678. Report an issue: GitHub.