BerriAI/litellm · error · ValueError

Unsupported model: {model}

Error message

Unsupported model: {model}

What it means

Sentinel from get_vertex_ai_partner_model_config: the publisher/API-spec string matched none of the known partner configs (anthropic, ai21, ...), so no BaseConfig exists to transform the response for this model.

Source

Thrown at litellm/llms/vertex_ai/vertex_ai_partner_models/__init__.py:19

from litellm.llms.base_llm.chat.transformation import BaseConfig


def get_vertex_ai_partner_model_config(model: str, vertex_publisher_or_api_spec: str) -> BaseConfig:
    """Return config for handling response transformation for vertex ai partner models"""
    if vertex_publisher_or_api_spec == "anthropic":
        from .anthropic.transformation import VertexAIAnthropicConfig

        return VertexAIAnthropicConfig()
    elif vertex_publisher_or_api_spec == "ai21":
        from .ai21.transformation import VertexAIAi21Config

        return VertexAIAi21Config()
    elif vertex_publisher_or_api_spec == "openapi" or vertex_publisher_or_api_spec == "mistralai":
        from .llama3.transformation import VertexAILlama3Config

        return VertexAILlama3Config()
    else:
        raise ValueError(f"Unsupported model: {model}")

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Use one of the supported partner models routed through vertex_ai (see the litellm docs for the provider's model list).
2. Check the model string for typos and the correct 'vertex_ai/' prefix.

When it happens

Trigger: Thrown at litellm/llms/vertex_ai/vertex_ai_partner_models/__init__.py:19 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/b8e1954a9c638bb5. Report an issue: GitHub.