xtekky/gpt4free · error · ModelNotFoundError

No API endpoint found for model: {model}

Error message

No API endpoint found for model: {model}

What it means

Azure routes requests by model name: create_async_generator looks up the api_endpoint in the cls.routes dict loaded from AZURE_ROUTES. ModelNotFoundError is raised when routes are configured but the requested model (after alias expansion) has no entry, so the provider has no URL to send the request to.

Source

Thrown at g4f/Provider/needs_auth/Azure.py:79

        cls,
        model: str,
        messages: Messages,
        stream: bool = True,
        media: MediaListType = None,
        api_key: str = None,
        api_endpoint: str = None,
        **kwargs,
    ) -> AsyncResult:
        if not model:
            model = os.environ.get("AZURE_DEFAULT_MODEL", cls.default_model)
        if model in cls.model_aliases:
            model = cls.model_aliases[model]
        if not api_endpoint:
            if not cls.routes:
                cls.get_models()
            api_endpoint = cls.routes.get(model)
            if cls.routes and not api_endpoint:
                raise ModelNotFoundError(f"No API endpoint found for model: {model}")
        if not api_endpoint:
            api_endpoint = os.environ.get("AZURE_API_ENDPOINT")
        if cls.api_keys:
            api_key = cls.api_keys.get(model, cls.api_keys.get("default"))
            if not api_key:
                raise ValueError(
                    f"API key is required for Azure provider. Ask for API key in the {cls.login_url} Discord server."
                )
        if api_endpoint and "/images/" in api_endpoint:
            prompt = format_media_prompt(messages, kwargs.get("prompt"))
            width, height = get_width_height(
                kwargs.get("aspect_ratio", "1:1"),
                kwargs.get("width"),
                kwargs.get("height"),
            )
            output_format = kwargs.get("output_format", "png")
            form = None
            data = None

View on GitHub (pinned to 973504e177)

Solutions

1. Add the model -> deployment endpoint mapping to AZURE_ROUTES and restart the process.
2. Check spelling: the requested model string must exactly match a key in AZURE_ROUTES (after model_aliases expansion).
3. Use a model alias in cls.model_aliases or pass api_endpoint explicitly to bypass routing.
4. Call Azure.get_models() to list the currently configured route keys and verify your model is there.

Example fix

# before
export AZURE_ROUTES='{"gpt-4o": "https://res.openai.azure.com/openai/deployments/gpt-4o"}'
# client.calls(model="gpt-4o-mini") -> ModelNotFoundError

# after
export AZURE_ROUTES='{"gpt-4o": "https://res.openai.azure.com/openai/deployments/gpt-4o", "gpt-4o-mini": "https://res.openai.azure.com/openai/deployments/gpt-4o-mini"}'

routes = json.loads(os.environ.get("AZURE_ROUTES", "{}"))
if model not in routes and model not in Azure.model_aliases:
    available = list(routes.keys())
    raise ValueError(f"model {model!r} has no route; available: {available}")

def model_is_routed(model: str) -> bool:
    """True when the model (after alias expansion) has an AZURE_ROUTES endpoint."""
    resolved = Azure.model_aliases.get(model, model)
    return resolved in Azure.routes

from g4f.errors import ModelNotFoundError

try:
    await Azure.create_async_generator(model=model, messages=messages)
except ModelNotFoundError as e:
    if "No API endpoint" in str(e):
        # config gap: add route or fix model name; do not retry
        raise

When it happens

Trigger: AZURE_ROUTES contains e.g. only 'gpt-4o', and the caller requests model='gpt-4o-mini' (and it is not in model_aliases). The lookup cls.routes.get(model) returns None while cls.routes is non-empty -> immediate raise.

Common situations: New deployment added in Azure but AZURE_ROUTES not updated; typo in the model name; using a public model name that differs from your custom Azure deployment name; forgetting to restart the process after updating the env var.

Related errors

• Invalid AZURE_API_KEYS environment variable
• Invalid AZURE_ROUTES environment variable format: {routes}
• API key is required for Azure provider. Ask for API key in t
• No Yupp accounts configured. Set YUPP_API_KEY environment va
• TokenError.FILE_ACCESS_ERROR

AI-assisted analysis of xtekky/gpt4free@973504e177 (2026-08-14). Data as JSON: /api/errors/d2ec73b1690cc96d. Report an issue: GitHub.