# About the modelFLUX.1-dev

**URL:** <https://discuss.huggingface.co/t/about-the-modelflux-1-dev/179954>\
**Category:** Models\
**Created:** [September 6, 2026, 7:39am UTC](https://discuss.huggingface.co/t/about-the-modelflux-1-dev/179954 "2026-09-06T07:39:09Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Komal-01Artic](https://avatars.discourse-cdn.com/v4/letter/k/3da27b/32.png) [@Komal-01Artic](https://discuss.huggingface.co/u/Komal-01Artic)\
**Post date:** [September 6, 2026, 7:39am UTC](https://discuss.huggingface.co/t/about-the-modelflux-1-dev/179954/1 "2026-09-06T07:39:09Z")

</div>

I am trying to call the above model to generate premium image thorugh [https://router.huggingface.co/hf-inference/models/black-forest-labs/FLUX.1-dev](https://router.huggingface.co/hf-inference/models/black-forest-labs/FLUX.1-dev)

but i am getting 410 gone as error saying The requested model is deprecated and no longer supported by provider hf-inference.

I am using this in angular project

can anyone help me here to solve this

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [September 6, 2026, 11:35pm UTC](https://discuss.huggingface.co/t/about-the-modelflux-1-dev/179954/2 "2026-09-06T23:35:24Z")

</div>

Hmm… I think this is because **the way the service works has changed quite a bit** :

* * *

The `410 Gone` here does **not** appear to mean that `black-forest-labs/FLUX.1-dev` itself has been removed.

The important part of the error is:

> `no longer supported by provider hf-inference`

Your URL is explicitly pinning the request to the **`hf-inference` provider** :

```plaintext
https://router.huggingface.co/hf-inference/models/black-forest-labs/FLUX.1-dev
                                  ^^^^^^^^^^^^

```

`FLUX.1-dev` still exists on the Hub, and at the moment its [model page](https://huggingface.co/black-forest-labs/FLUX.1-dev) shows **fal** as a Text-to-Image Inference Provider. Hugging Face’s current [Fal provider documentation](https://huggingface.co/docs/inference-providers/providers/fal-ai) also uses `black-forest-labs/FLUX.1-dev` directly in its text-to-image example.

So I would not try to repair this by changing Angular-specific code around the old `/hf-inference/` request. I would move to the current Inference Providers client and stop hard-coding `hf-inference`.

For example, on a **server/backend** :

```ts
import { InferenceClient } from "@huggingface/inference";

const client = new InferenceClient(process.env.HF_TOKEN);

const imageBlob = await client.textToImage({
  model: "black-forest-labs/FLUX.1-dev",
  inputs: "A cinematic photograph of a mountain lake at sunrise",
});

```

The current JavaScript client uses automatic provider selection by default, so this lets Hugging Face choose an available provider instead of forcing the request through `hf-inference`. The official [Inference Providers documentation](https://huggingface.co/docs/inference-providers/) currently shows essentially this same `FLUX.1-dev` JavaScript example.

If you specifically want to pin the currently listed Fal route, you can also make that explicit:

```ts
const imageBlob = await client.textToImage({
  provider: "fal-ai",
  model: "black-forest-labs/FLUX.1-dev",
  inputs: "A cinematic photograph of a mountain lake at sunrise",
});

```

I would prefer the first form unless you have a reason to require a particular provider.

One important difference from the old Serverless Inference API model: **Inference Providers are pay-as-you-go beyond the included monthly credits.** At the time of writing, the [pricing documentation](https://huggingface.co/docs/inference-providers/pricing) lists $0.10/month of Inference Providers credits for Free accounts (explicitly marked as subject to change), $2/month for PRO, and PAYG after the included credits are exhausted. So changing providers restores a serving route, but it should not be understood as a drop-in replacement for unlimited/free old-style serverless inference.

Also, because you mentioned Angular: if your Hugging Face token is currently stored in the Angular application itself, I would change that separately. This is **not the cause of the 410** , but tokens embedded in an Angular frontend are visible to the browser user. Both the [Hugging Face JavaScript documentation](https://huggingface.co/docs/huggingface.js/inference/README) and [Angular’s environment documentation](https://angular.dev/tools/cli/environments) recommend keeping secrets server-side and using a proxy/backend.

A safer layout is therefore roughly:

```plaintext
Angular application
        |
        | POST { prompt: ... }
        v
your backend / serverless function
        |
        | HF_TOKEN stays here
        v
@huggingface/inference
        |
        v
Hugging Face Inference Providers
        |
        v
currently available provider

```

> **Why this changed / why \`hf-inference\` is different now**
>
> `hf-inference` still exists; this is not simply “HF Inference was deleted”.
> 
> However, Hugging Face now describes it as the service that **used to be called “Inference API (serverless)”**, and says that [as of July 2025 it focuses mostly on CPU inference](https://huggingface.co/docs/inference-providers/providers/hf-inference), such as embeddings, ranking, classification, and smaller historically important models.
> 
> That is a substantially different model from the older expectation that an arbitrary model on the Hub could necessarily be sent to the Serverless Inference API and cold-started.
> 
> The current architecture is closer to:
> 
> ```plaintext
> HF model
> +
> task
> +
> provider currently serving that model/task
> |
> v
> Inference Providers
> 
> ```
> 
> rather than:
> 
> ```plaintext
> any HF model
> |
> v
> one universal Serverless Inference API
> 
> ```
> 
> This is why the distinction in your error message matters: it says that this **model/provider combination** is deprecated, not that the model repository has disappeared.
> 
> I would avoid inferring the exact internal reason or date on which FLUX.1-dev was removed from the `hf-inference` catalog; I have not found a public source establishing that specific internal decision.

> **How to check which provider currently serves a model**
>
> Provider availability can change, so for future troubleshooting it is useful to query the current mapping rather than assuming a provider name from an old example.
> 
> Hugging Face exposes this through the [Hub API / `inferenceProviderMapping`](https://huggingface.co/docs/inference-providers/hub-api).
> 
> For example:
> 
> ```python
> from huggingface_hub import model_info
> 
> info = model_info(
> "black-forest-labs/FLUX.1-dev",
> expand="inferenceProviderMapping",
> )
> 
> print(info.inference_provider_mapping)
> 
> ```
> 
> That mapping reports the providers serving the model, their status (`live` / `staging`), the task, and the provider-side model ID.
> 
> The same Hub API documentation currently gives this example for listing Fal text-to-image models, and `FLUX.1-dev` is among the returned models.
> 
> This distinction is useful in general:
> 
> ```plaintext
> "The provider supports text-to-image"
> 
> ```
> 
> does not necessarily imply:
> 
> ```plaintext
> "This exact model is currently mapped to text-to-image on that provider"
> 
> ```
> 
> The exact **model × task × provider** mapping is what matters.
> 
> Provider mappings are also dynamic. Hugging Face’s [provider registration documentation](https://huggingface.co/docs/inference-providers/register-as-a-provider) says mapped models are automatically tested periodically; mappings that fail validation can be temporarily removed from the active-provider list and retested later.
> 
> So I would phrase Fal as a provider that is **currently** available for FLUX.1-dev, rather than assuming it will permanently be the one provider for this model.

> **If the next request fails with a different error**
>
> Once you stop forcing `hf-inference`, the next error—if there is one—may reveal a different layer:
> 
> ```plaintext
> New request
> |
> +-- works
> | -> done
> |
> +-- 401 / 403
> | -> check the token and its Inference Providers permission
> | -> also check access to the gated FLUX.1-dev model if relevant
> |
> +-- model/provider/task availability error
> | -> check the current inferenceProviderMapping
> |
> +-- credit / billing error
> | -> check Inference Providers credits / PAYG settings
> |
> +-- token is inside the Angular bundle
> -> move the actual HF request behind your own backend/proxy
> 
> ```
> 
> `FLUX.1-dev` is also a gated model whose files require accepting its access conditions, so that is worth checking **if the provider issue is fixed and the error changes to an authorization/access error**. I would not treat that as the explanation for the current `410`, because the current response is specifically about `hf-inference` no longer supporting the model.
> 
> If this is eventually for commercial/production use, I would also check the terms for the particular hosted provider/API route you choose. The `FLUX.1-dev` model repository itself is published under the FLUX.1-dev non-commercial license, while hosted-provider terms can be a separate layer.

So, for this particular error, my default path would be:

```plaintext
stop pinning /hf-inference/
        ->
use @huggingface/inference
        ->
let provider selection be automatic
        ->
or explicitly use a currently supported provider such as fal-ai
        ->
check the PAYG implications before relying on it in the application

```

That should separate the actual serving change from the Angular integration, rather than treating the 410 as a problem with FLUX.1-dev itself.