BerriAI/litellm · error · Exception

Missing api_key, make sure you pass in your api key

Error message

Missing api_key, make sure you pass in your api key

What it means

In Bytez's validate_environment, after headers are built it checks the resolved api_key argument; if falsy it raises this generic Exception. The Authorization header would otherwise read 'Key None'. Unlike other providers it does not fall back to an env var here — the key must arrive via the api_key argument (litellm resolves env-based keys before this point).

Solutions

1. Pass api_key on the call: litellm.completion(..., api_key="...").
2. Set the key in the environment so litellm resolves it (standard provider env pattern, e.g. BYTEZ_API_KEY) for the process running litellm.
3. For LiteLLM proxy, add api_key to the model's config entry (litellm_params).
4. Verify the key reaches your code path by printing bool(api_key) just before the call.

Example fix

# before
litellm.completion(model="bytez/meta-llama/Llama-3.1-8B-Instruct", messages=msgs)

# after
litellm.completion(
    model="bytez/meta-llama/Llama-3.1-8B-Instruct",
    messages=msgs,
    api_key=os.environ["BYTEZ_API_KEY"],
)

import os

def bytez_key() -> str | None:
    return os.environ.get("BYTEZ_API_KEY") or os.environ.get("BYTEZ_API_TOKEN")

try:
    litellm.completion(model="bytez/org/model", messages=msgs, api_key=key)
except Exception as e:
    if "api_key" in str(e):
        raise RuntimeError("BYTEZ credentials missing") from e
    raise

When it happens

Trigger: Calling litellm.completion(model="bytez/...", messages=msgs) with no api_key and no BYTEZ_API_KEY available for litellm to auto-resolve; passing api_key=None explicitly; proxy model entry missing the api_key field.

Common situations: First call to a newly added bytez model; proxy config listing the model without api_key and without the env var on the host; key stored under a differently-named env var.

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

• BFL_API_KEY is not set. Please set it via environment…
• BRAVE_API_KEY is not set. Set `BRAVE_API_KEY` environment…
• LINKUP_API_KEY is not set. Set `LINKUP_API_KEY` environment…
• XAI API key is required. Set api_key, litellm.xai_key…
• api_key is required

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/68115b97477350dc. Report an issue: GitHub.

Appendix: source

Thrown at litellm/llms/bytez/chat/transformation.py:138

        messages: list[AllMessageValues],
        optional_params: dict,
        litellm_params: dict,
        api_key: str | None = None,
        api_base: str | None = None,
    ) -> dict:
        headers.update(
            {
                "content-type": "application/json",
                "Authorization": f"Key {api_key}",
                "user-agent": f"litellm/{version}",
            }
        )

        if not messages:
            raise Exception("kwarg `messages` must be an array of messages that follow the openai chat standard")

        if not api_key:
            raise Exception("Missing api_key, make sure you pass in your api key")

        return headers

    def get_complete_url(
        self,
        api_base: str | None,
        api_key: str | None,
        model: str,
        optional_params: dict,
        litellm_params: dict,
        stream: bool | None = None,
    ) -> str:
        encoded_model: Final = encode_url_path_segments(model, field_name="model")
        return f"{API_BASE}/{encoded_model}"

    def transform_request(
        self,
        model: str,

View on GitHub (pinned to 77b7c6c40c)