wandb/openui · warning · HTTPException

You've exceeded our usage quota, come back tomorrow to gener

Error message

You've exceeded our usage quota, come back tomorrow to generate more UI.

What it means

chat_completions enforces a daily usage quota in PROD: if a user's token usage in the last 24h (Usage.tokens_since) exceeds config.MAX_TOKENS, it raises HTTP 429 with the quota message. This protects the hosted service from runaway generation costs.

Source

Thrown at backend/openui/server.py:123

@router.post("/v1/chat/completions", tags=["openui/chat"])
@router.post(
    "/chat/completions",
    tags=["openui/chat"],
)
async def chat_completions(
    request: Request,
    # chat_request: CompletionCreateParams,  # TODO: lots' fo weirdness here, just using raw json
    # ctx: Any = Depends(weave_context),
):
    if request.session.get("user_id") is None:
        raise HTTPException(status_code=401, detail="Login required to use OpenUI")
    user_id = request.session["user_id"]
    yesterday = datetime.now() - timedelta(days=1)
    tokens = Usage.tokens_since(user_id, yesterday.date())
    if config.ENV == config.Env.PROD and tokens > config.MAX_TOKENS:
        raise HTTPException(
            status_code=429,
            detail="You've exceeded our usage quota, come back tomorrow to generate more UI.",
        )
    try:
        data = await request.json()  # chat_request.model_dump(exclude_unset=True)
        input_tokens = count_tokens(data["messages"])
        # TODO: we always assume 4096 max tokens (random fudge factor here)
        data["max_tokens"] = 4096 - input_tokens - 20
        # TODO: refactor all these blocks into one once Ollama supports vision
        # OpenAI Models
        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,
            )

View on GitHub (pinned to 42d7ab4ab6)

Solutions

1. Wait until the 24h rolling window expires and usage drops below MAX_TOKENS.
2. Run with config.ENV != PROD for development (quota check is skipped outside PROD).
3. Raise config.MAX_TOKENS if you control the deployment.
4. Track Usage.tokens_since client-side and throttle requests before hitting the cap.

Example fix

// before
export ENV=PROD && python -m openui
// after
export ENV=DEV && python -m openui  # quota check bypassed outside PROD

# client-side quota pre-check if the endpoint exposes usage
usage = s.get('http://localhost:7878/usage').json()
if usage['tokens'] > MAX_TOKENS: raise RuntimeError('Quota exhausted for today')

try:
    r = s.post(url, json=payload)
    if r.status_code == 429:
        time.sleep(seconds_until_window_reset())
        r = s.post(url, json=payload)
except requests.RequestException:
    backoff_and_retry()

When it happens

Trigger: Accumulating more than MAX_TOKENS of usage within one day in ENV=PROD, then calling chat completions again; the window is rolling from `datetime.now() - timedelta(days=1)`.

Common situations: Automated scripts/benchmarks hammering the endpoint; shared account used by a team; MAX_TOKENS left at the low default while doing heavy dev work in PROD mode.

Related errors

• Login required to use OpenUI
• Model not supported
• msg
• body.error.message
• Unexpected response ${r.status}: ${await r.text()}

AI-assisted analysis of wandb/openui@42d7ab4ab6 (2026-09-01). Data as JSON: /api/errors/71deb3ae9f52df10. Report an issue: GitHub.