BerriAI/litellm · error · ValueError

DASHSCOPE_API_KEY is not set

Error message

DASHSCOPE_API_KEY is not set

What it means

Raised during request preparation for DashScope image generation: neither an explicit api_key parameter nor the DASHSCOPE_API_KEY environment variable is available, so no Authorization header can be built. It is a plain ValueError thrown from validate_environment before any HTTP request is made.

Source

Thrown at litellm/llms/dashscope/image_generation/transformation.py:112

        optional_params: dict,
        litellm_params: dict,
        stream: bool | None = None,
    ) -> str:
        return api_base or get_secret_str("DASHSCOPE_API_BASE_IMAGE") or DEFAULT_API_BASE

    def validate_environment(
        self,
        headers: dict,
        model: str,
        messages: list[AllMessageValues],
        optional_params: dict,
        litellm_params: dict,
        api_key: str | None = None,
        api_base: str | None = None,
    ) -> dict:
        final_api_key: Final = api_key or get_secret_str("DASHSCOPE_API_KEY")
        if not final_api_key:
            raise ValueError("DASHSCOPE_API_KEY is not set")
        headers["Authorization"] = f"Bearer {final_api_key}"
        headers["Content-Type"] = "application/json"
        return headers

    def transform_image_generation_request(
        self,
        model: str,
        prompt: str,
        optional_params: dict,
        litellm_params: dict,
        headers: dict,
    ) -> dict:
        """
        Transform OpenAI-style image generation request to DashScope multimodal-generation format.
        """
        parameters: Final[dict] = {}
        for k, v in optional_params.items():
            parameters[k] = v

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Set DASHSCOPE_API_KEY in the environment: export DASHSCOPE_API_KEY=sk-...
2. Or pass the key explicitly: litellm.image_generation(..., api_key=key)
3. In server deployments, configure it as a provider environment variable in the LiteLLM proxy env settings
4. Verify with: python -c "import os; print(bool(os.getenv('DASHSCOPE_API_KEY')))"

Example fix

# before
img = litellm.image_generation(model="dashscope/wanx-v1", prompt="a cat")

# after
img = litellm.image_generation(model="dashscope/wanx-v1", prompt="a cat", api_key=os.environ["DASHSCOPE_API_KEY"])

api_key = os.getenv("DASHSCOPE_API_KEY")
if not api_key:
    raise RuntimeError("DASHSCOPE_API_KEY missing — set it before image generation")

def has_dashscope_key(params: dict) -> bool:
    return bool(params.get("api_key") or os.getenv("DASHSCOPE_API_KEY"))

try:
    img = litellm.image_generation(model=m, prompt=p, api_key=os.getenv("DASHSCOPE_API_KEY"))
except ValueError as e:
    if "DASHSCOPE_API_KEY" in str(e):
        raise ConfigError("Configure DASHSCOPE_API_KEY") from e
    raise

When it happens

Trigger: Calling litellm.image_generation() with a dashscope model without passing api_key and without DASHSCOPE_API_KEY set in the environment (or set to an empty string).

Common situations: Deploying to a new environment (container, CI) where the env var was not carried over; typos in the variable name (e.g. DASHSCOPE_KEY); expecting LiteLLM's generic API_KEY convention instead of the provider-specific name.

Related errors

• DashScope API key is required. Set 'DASHSCOPE_API_KEY' env v
• 'username' is required in litellm_params when auth_mode='cp4
• Missing Azure Document Intelligence API Key - Set AZURE_DOCU
• Missing Azure AI API Key - A call is being made to Azure AI
• Error transforming image generation config: {e}. Got params:

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/c9dd7207e3546400. Report an issue: GitHub.