wandb/openui · error · HTTPException

Groq API key is not set.

Error message

Groq API key is not set.

What it means

This error is raised by OpenUI's chat_completions endpoint when a request targets a model prefixed with 'groq/' but the Groq client was never initialized because the GROQ_API_KEY environment variable was not set at startup. The endpoint checks `if groq is None` and aborts with HTTP 500 before calling the Groq API. It is a server-side configuration error, not an API error from Groq itself.

Source

Thrown at backend/openui/server.py:152

        if data.get("model").startswith("gpt"):
            if data["model"] == "gpt-4" or data["model"] == "gpt-4-32k":
                raise HTTPException(status=400, data="Model not supported")
            response: AsyncStream[
                ChatCompletionChunk
            ] = await openai.chat.completions.create(
                **data,
            )
            # gpt-4 tokens are 20x more expensive
            multiplier = 20 if "gpt-4" in data["model"] else 1
            return StreamingResponse(
                openai_stream_generator(response, input_tokens, user_id, multiplier),
                media_type="text/event-stream",
            )
        # Groq Models
        elif data.get("model").startswith("groq/"):
            data["model"] = data["model"].replace("groq/", "")
            if groq is None:
                raise HTTPException(status=500, detail="Groq API key is not set.")
            response: AsyncStream[
                ChatCompletionChunk
            ] = await groq.chat.completions.create(
                **data,
            )
            return StreamingResponse(
                openai_stream_generator(response, input_tokens, user_id, 1),
                media_type="text/event-stream",
            )
        # Litellm Models
        elif data.get("model").startswith("litellm/"):
            data["model"] = data["model"].replace("litellm/", "")
            if litellm is None:
                raise HTTPException(status=500, detail="LiteLLM API key is not set.")
            response: AsyncStream[
                ChatCompletionChunk
            ] = await litellm.chat.completions.create(
                **data,

View on GitHub (pinned to 42d7ab4ab6)

Solutions

1. Set the GROQ_API_KEY environment variable before starting the server (e.g. export GROQ_API_KEY=gsk_... or add it to .env) and restart OpenUI.
2. Verify the key is loaded in the running process (docker exec env | grep GROQ or print os.environ in a startup log) since the check happens at import time.
3. If you don't intend to use Groq, select a model from a provider whose key is configured instead of a groq/ prefixed model.
4. Get a key from console.groq.com if you don't have one and add it to your deployment secrets.

Example fix

// before (start server without key -> 500)
python -m uvicorn openui.server:app
// after
GROQ_API_KEY=gsk_yourkeyhere python -m uvicorn openui.server:app

import os
def ensure_groq_ready():
    if not os.environ.get("GROQ_API_KEY"):
        raise RuntimeError("GROQ_API_KEY is not set; groq/ models are unavailable")
# call before issuing any groq/ model request

When it happens

Trigger: POSTing to /chat/completions with data.model starting with 'groq/' (e.g. 'groq/llama3-70b-8192') while the server process was started without GROQ_API_KEY set, so the module-level groq client is None.

Common situations: Deploying OpenUI without configuring the Groq key in the environment (.env not loaded, key omitted in docker-compose or k8s secrets), switching to a Groq model after deploying with only other providers' keys, or restarting a container that lost its env vars.

Understand the failure class

Background: "environment variable is not set" and "Missing keys in environment" errors: what missing required env var messages mean and how to fix them — this error's family across 28 libraries.

Related errors

• LiteLLM API key is not set.
• Login required to use OpenUI
• You've exceeded our usage quota, come back tomorrow to gener
• Model not supported
• Invalid model

AI-assisted analysis of wandb/openui@42d7ab4ab6 (2026-09-01). Data as JSON: /api/errors/33cf0a4b1cd0c928. Report an issue: GitHub.