diff --git a/src/huggingface_hub/inference/_client.py b/src/huggingface_hub/inference/_client.py
index e6bed1af67..5cbdc758c9 100644
--- a/src/huggingface_hub/inference/_client.py
+++ b/src/huggingface_hub/inference/_client.py
@@ -132,7 +132,7 @@ class InferenceClient:
             Note: for better compatibility with OpenAI's client, `model` has been aliased as `base_url`. Those 2
             arguments are mutually exclusive. If a URL is passed as `model` or `base_url` for chat completion, the `(/v1)/chat/completions` suffix path will be appended to the URL.
         provider (`str`, *optional*):
-            Name of the provider to use for inference. Can be `"black-forest-labs"`, `"cerebras"`, `"cohere"`, `"fal-ai"`, `"featherless-ai"`, `"fireworks-ai"`, `"groq"`, `"hf-inference"`, `"hyperbolic"`, `"nebius"`, `"novita"`, `"nscale"`, `"openai"`, `"replicate"`, "sambanova"` or `"together"`.
+            Name of the provider to use for inference. Can be `"black-forest-labs"`, `"cerebras"`, `"cohere"`, `"fal-ai"`, `"featherless-ai"`, `"fireworks-ai"`, `"groq"`, `"hf-inference"`, `"hyperbolic"`, `"hyperfusion"`, `"nebius"`, `"novita"`, `"nscale"`, `"openai"`, `"replicate"`, "sambanova"` or `"together"`.
             Defaults to "auto" i.e. the first of the providers available for the model, sorted by the user's order in https://hf.co/settings/inference-providers.
             If model is a URL or `base_url` is passed, then `provider` is not used.
         token (`str`, *optional*):
diff --git a/src/huggingface_hub/inference/_providers/__init__.py b/src/huggingface_hub/inference/_providers/__init__.py
index 405087d485..1a7c25a420 100644
--- a/src/huggingface_hub/inference/_providers/__init__.py
+++ b/src/huggingface_hub/inference/_providers/__init__.py
@@ -26,6 +26,7 @@
     HFInferenceTask,
 )
 from .hyperbolic import HyperbolicTextGenerationTask, HyperbolicTextToImageTask
+from .hyperfusion import HyperfusionConversationalTask
 from .nebius import (
     NebiusConversationalTask,
     NebiusFeatureExtractionTask,
@@ -53,6 +54,7 @@
     "groq",
     "hf-inference",
     "hyperbolic",
+    "hyperfusion",
     "nebius",
     "novita",
     "nscale",
@@ -124,6 +126,9 @@
         "conversational": HyperbolicTextGenerationTask("conversational"),
         "text-generation": HyperbolicTextGenerationTask("text-generation"),
     },
+    "hyperfusion": {
+        "conversational": HyperfusionConversationalTask(),
+    },
     "nebius": {
         "text-to-image": NebiusTextToImageTask(),
         "conversational": NebiusConversationalTask(),
diff --git a/src/huggingface_hub/inference/_providers/hyperfusion.py b/src/huggingface_hub/inference/_providers/hyperfusion.py
new file mode 100644
index 0000000000..4b7026fec1
--- /dev/null
+++ b/src/huggingface_hub/inference/_providers/hyperfusion.py
@@ -0,0 +1,27 @@
+from typing import Optional
+
+from huggingface_hub.hf_api import InferenceProviderMapping
+from huggingface_hub.inference._providers._common import BaseConversationalTask
+
+
+_PROVIDER = "hyperfusion"
+_BASE_URL = "https://api.hyperfusion.io"
+
+
+class HyperfusionConversationalTask(BaseConversationalTask):
+    def __init__(self):
+        super().__init__(provider=_PROVIDER, base_url=_BASE_URL)
+
+    def _prepare_api_key(self, api_key: Optional[str]) -> str:
+        if api_key is None:
+            raise ValueError(
+                "You must provide an api_key to work with Hyperfusion API."
+            )
+        return api_key
+
+    def _prepare_mapping_info(self, model: Optional[str]) -> InferenceProviderMapping:
+        if model is None:
+            raise ValueError("Please provide an Hyperfusion model ID, e.g. `llm-en`.")
+        return InferenceProviderMapping(
+            providerId=model, task="conversational", status="live", hf_model_id=model
+        )
diff --git a/tests/test_inference_providers.py b/tests/test_inference_providers.py
index eea23ed5f4..ab15cb6c0b 100644
--- a/tests/test_inference_providers.py
+++ b/tests/test_inference_providers.py
@@ -39,6 +39,7 @@
     HFInferenceTask,
 )
 from huggingface_hub.inference._providers.hyperbolic import HyperbolicTextGenerationTask, HyperbolicTextToImageTask
+from huggingface_hub.inference._providers.hyperfusion import HyperfusionConversationalTask
 from huggingface_hub.inference._providers.nebius import NebiusFeatureExtractionTask, NebiusTextToImageTask
 from huggingface_hub.inference._providers.novita import NovitaConversationalTask, NovitaTextGenerationTask
 from huggingface_hub.inference._providers.nscale import NscaleConversationalTask, NscaleTextToImageTask
@@ -910,6 +911,10 @@ def test_text_to_image_get_response(self):
         response = helper.get_response({"images": [{"image": base64.b64encode(dummy_image).decode()}]})
         assert response == dummy_image
 
+class TestHyperfusionProvider:
+    def test_prepare_url(self):
+        helper = HyperfusionConversationalTask()
+        assert helper._prepare_url("sk-XXXXXX", "llm-en") == "https://api.hyperfusion.io/v1/chat/completions"
 
 class TestNebiusProvider:
     def test_prepare_route_text_to_image(self):