xtekky/gpt4free · error · ModelNotFoundError

Model is not supported

Error message

Model is not supported: {model} in: {cls.__name__}

What it means

Raised by HuggingFaceMedia when the model-to-provider mapping fetched from the HuggingFace router (filtered/merged for replicate, together, hf-inference) ends up empty. ModelNotFoundError means the router API knows no serving provider for the requested model id, so there is nothing to dispatch to.

Solutions

1. Verify the exact model id at huggingface.co — copy the repo name precisely
2. Pick a model that shows Inference Providers on its model page
3. Update g4f in case the mapping endpoint handling changed
4. List supported models via cls.get_models() and choose from those

Example fix

# before
model = 'black-forest-labs/flux-dev-typo'
# after
model = 'black-forest-labs/FLUX.1-dev'

supported = set(HuggingFaceMedia.get_models())
if model not in supported:
    raise ValueError(f'{model} not served; choose from {sorted(supported)[:5]}...')

from g4f.errors import ModelNotFoundError
try:
    ...
except ModelNotFoundError:
    model = HuggingFaceMedia.get_models()[0]
    ...

When it happens

Trigger: Requesting a HuggingFaceMedia model id that does not exist or has no inference providers registered (get_mapping returns {} or only unsupported providers).

Common situations: Typo'd or outdated model id; model delisted from the inference router; new model not yet registered for inference; region/account restrictions removing all providers.

Related errors

• Add a "api_key"
• Model is not supported
• Model ' ' is not supported by LMArena provider.
• Model not found
• (await response.json()), data

AI-assisted analysis of xtekky/gpt4free@973504e177 (2026-08-14). Data as JSON: /api/errors/4f21528c77e0166b. Report an issue: GitHub.

Appendix: source

Thrown at g4f/Provider/needs_auth/hf/HuggingFaceMedia.py:163

        if model and ":" in model:
            model, selected_provider = model.split(":", 1)
        elif not model:
            model = cls.get_models()[0]
        prompt = format_media_prompt(messages, prompt)
        provider_mapping = await cls.get_mapping(model, api_key)
        headers = {
            "Accept-Encoding": "gzip, deflate",
            "Content-Type": "application/json",
            "Prefer": "wait",
        }
        new_mapping = {
            "hf-free" if key == "hf-inference" else key: value
            for key, value in provider_mapping.items()
            if key in ["replicate", "together", "hf-inference"]
        }
        provider_mapping = {**new_mapping, **provider_mapping}
        if not provider_mapping:
            raise ModelNotFoundError(
                f"Model is not supported: {model} in: {cls.__name__}"
            )

        async def generate(extra_body: dict, aspect_ratio: str = None):
            last_response = None
            for provider_key, provider in provider_mapping.items():
                if selected_provider is not None and selected_provider != provider_key:
                    continue
                provider_info = ProviderInfo(
                    **{
                        **cls.get_dict(),
                        "label": f"HuggingFace ({provider_key})",
                        "url": f"{cls.url}/{model}",
                    }
                )

                base_url = f"https://router.huggingface.co/{provider_key}"
                task = provider["task"]

View on GitHub (pinned to 973504e177)