BerriAI/litellm · error · ValueError

DASHSCOPE_API_KEY is not set

Error message

DASHSCOPE_API_KEY is not set

What it means

The DashScope image-generation handler's validate_environment needs a bearer token before any HTTP request: either an explicit api_key argument or the DASHSCOPE_API_KEY environment variable. Neither was present, so it raises ValueError('DASHSCOPE_API_KEY is not set') — a pure client-side configuration failure, no network call happened.

Solutions

  1. Export the variable in the runtime environment: export DASHSCOPE_API_KEY=sk-... (or inject it via your container/CI secret store)
  2. Or pass it per call: litellm.image_generation(..., api_key='sk-...')
  3. If using the LiteLLM proxy, set DASHSCOPE_API_KEY in the dashscope deployment's litellm_params/environment_variables in litellm_config.yaml
  4. Verify visibility in the failing process: python -c "import os; print(bool(os.getenv('DASHSCOPE_API_KEY')))"

Example fix

# before
img = litellm.image_generation(model='dashscope/wanx2.1-t2i-turbo', prompt='a cat')  # ValueError

# after
img = litellm.image_generation(
    model='dashscope/wanx2.1-t2i-turbo',
    prompt='a cat',
    api_key=os.environ['DASHSCOPE_API_KEY'],  # or export DASHSCOPE_API_KEY first
)
Defensive patterns

Strategy: validation

Validate before calling

import os

def dashscope_ready() -> bool:
    return bool(os.getenv('DASHSCOPE_API_KEY'))

if not dashscope_ready():
    raise RuntimeError('DASHSCOPE_API_KEY missing - refusing to start image-generation worker')

Try / catch

try:
    litellm.image_generation(model='dashscope/wanx2.1-t2i-turbo', prompt=p)
except ValueError as e:
    if 'DASHSCOPE_API_KEY' in str(e):
        raise ConfigError('DashScope key not provisioned for this environment') from e
    raise

Prevention

When it happens

Trigger: litellm.image_generation(model='dashscope/<image-model>', prompt=...) executed in a process where DASHSCOPE_API_KEY was never exported and no api_key was passed (or supplied by the LiteLLM proxy config).

Common situations: .env file not loaded (python-dotenv not run at startup); key exported in a different shell/venv than the running app; Docker/K8s secret not mounted; proxy config lists the deployment under a provider whose env var name is misspelled.

Understand the failure class

Background: "API key is required" / "API key not found" / "No API key was set": the missing-api-key error family across 16 libraries — this error's family across 16 libraries.

Related errors

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/c9dd7207e3546400. Report an issue: GitHub.

Appendix: 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 77b7c6c40c)