diff --git a/docs/inference-providers/_toctree.yml b/docs/inference-providers/_toctree.yml
index 7b355a554..6d97ff7a2 100644
--- a/docs/inference-providers/_toctree.yml
+++ b/docs/inference-providers/_toctree.yml
@@ -6,10 +6,33 @@
title: Pricing and Billing
- local: hub-integration
title: Hub integration
- - local: security
- title: Security
- local: register-as-a-provider
title: Register as an Inference Provider
+ - local: security
+ title: Security
+
+- title: Providers
+ sections:
+ - local: providers/cerebras
+ title: Cerebras
+ - local: providers/fal-ai
+ title: Fal AI
+ - local: providers/fireworks-ai
+ title: Fireworks
+ - local: providers/hyperbolic
+ title: Hyperbolic
+ - local: providers/hf-inference
+ title: HF Inference
+ - local: providers/nebius
+ title: Nebius
+ - local: providers/novita
+ title: Novita
+ - local: providers/replicate
+ title: Replicate
+ - local: providers/sambanova
+ title: SambaNova
+ - local: providers/together
+ title: Together
- title: API Reference
sections:
- local: tasks/index
diff --git a/docs/inference-providers/index.md b/docs/inference-providers/index.md
index 1c8d59966..cb2619ea5 100644
--- a/docs/inference-providers/index.md
+++ b/docs/inference-providers/index.md
@@ -9,6 +9,23 @@ Hugging Face Inference Providers simplify and unify how developers access and ru
To learn more about the launch of Inference Providers, check out our [announcement blog post](https://huggingface.co/blog/inference-providers).
+## Partners
+
+Here is the complete list of partners integrated with Inference Providers, and the supported tasks for each of them:
+
+| Provider | Chat completion (LLM) | Chat completion (VLM) | Feature Extraction | Text to Image | Text to video |
+| ---------------------------------------- | :-------------------: | :-------------------: | :----------------: | :-----------: | :-----------: |
+| [Cerebras](./providers/cerebras) | ✅ | | | | |
+| [Fal AI](./providers/fal-ai) | | | | ✅ | ✅ |
+| [Fireworks](./providers/fireworks-ai) | ✅ | ✅ | | | |
+| [HF Inference](./providers/hf-inference) | ✅ | ✅ | ✅ | ✅ | |
+| [Hyperbolic](./providers/hyperbolic) | ✅ | ✅ | | | |
+| [Nebius](./providers/nebius) | ✅ | ✅ | | ✅ | |
+| [Novita](./providers/novita) | ✅ | ✅ | | | ✅ |
+| [Replicate](./providers/replicate) | | | | ✅ | ✅ |
+| [SambaNova](./providers/sambanova) | ✅ | | ✅ | | |
+| [Together](./providers/together) | ✅ | ✅ | | ✅ | |
+
## Why use Inference Providers?
Inference Providers offers a fast and simple way to explore thousands of models for a variety of tasks. Whether you're experimenting with ML capabilities or building a new application, this API gives you instant access to high-performing models across multiple domains:
@@ -28,7 +45,6 @@ Inference Providers offers a fast and simple way to explore thousands of models
- **🔧 Developer-Friendly**: Simple requests, fast responses, and a consistent developer experience across Python and JavaScript clients.
- **💰 Cost-Effective**: No extra markup on provider rates.
-
## Inference Playground
To get started quickly with [Chat Completion models](http://huggingface.co/models?inference_provider=all&sort=trending&other=conversational), use the [Inference Playground](https://huggingface.co/playground) to easily test and compare models with your prompts.
diff --git a/docs/inference-providers/providers/cerebras.md b/docs/inference-providers/providers/cerebras.md
new file mode 100644
index 000000000..60bd55a57
--- /dev/null
+++ b/docs/inference-providers/providers/cerebras.md
@@ -0,0 +1,30 @@
+
+
+# Cerebras
+
+[](https://www.cerebras.ai/)
+
+[](https://huggingface.co/cerebras)
+
+Cerebras stands alone as the world’s fastest AI inference and training platform. Organizations across fields like medical research, cryptography, energy, and agentic AI use our CS-2 and CS-3 systems to build on-premise supercomputers, while developers and enterprises everywhere can access the power of Cerebras through our pay-as-you-go cloud offerings.
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+
+
diff --git a/docs/inference-providers/providers/fal-ai.md b/docs/inference-providers/providers/fal-ai.md
new file mode 100644
index 000000000..8cb9d5629
--- /dev/null
+++ b/docs/inference-providers/providers/fal-ai.md
@@ -0,0 +1,50 @@
+
+
+# Fal
+
+[](https://fal.ai/)
+
+[](https://huggingface.co/fal)
+
+Founded in 2021 by [Burkay Gur](https://huggingface.co/burkaygur) and [Gorkem Yurtseven](https://huggingface.co/gorkemyurt), fal.ai was born out of a shared passion for AI and a desire to address the challenges in AI infrastructure observed during their tenures at Coinbase and Amazon.
+
+## Supported tasks
+
+
+### Automatic Speech Recognition
+
+Find out more about Automatic Speech Recognition [here](../tasks/automatic_speech_recognition).
+
+
+
+
+### Text To Image
+
+Find out more about Text To Image [here](../tasks/text_to_image).
+
+
+
+
+### Text To Video
+
+Find out more about Text To Video [here](../tasks/text_to_video).
+
+
+
diff --git a/docs/inference-providers/providers/fireworks-ai.md b/docs/inference-providers/providers/fireworks-ai.md
new file mode 100644
index 000000000..89b5cda45
--- /dev/null
+++ b/docs/inference-providers/providers/fireworks-ai.md
@@ -0,0 +1,39 @@
+
+
+# Fireworks AI
+
+[](https://fireworks.ai/)
+
+[](https://huggingface.co/fireworks-ai)
+
+Fireworks AI is a developer-centric platform that delivers high-performance generative AI solutions, enabling efficient deployment and fine-tuning of large language models (LLMs) and image models.
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+
+
diff --git a/docs/inference-providers/providers/hf-inference.md b/docs/inference-providers/providers/hf-inference.md
new file mode 100644
index 000000000..b82149800
--- /dev/null
+++ b/docs/inference-providers/providers/hf-inference.md
@@ -0,0 +1,201 @@
+
+
+# HF Inference
+
+[](https://huggingface.co/)
+
+[](https://huggingface.co/hf-inference)
+
+HF Inference is the serverless Inference API powered by Hugging Face. This service used to be called "Inference API (serverless)" prior to Inference Providers.
+If you are interested in deploying models to a dedicated and autoscaling infrastructure managed by Hugging Face, check out [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index) instead.
+
+## Supported tasks
+
+
+### Audio Classification
+
+Find out more about Audio Classification [here](../tasks/audio_classification).
+
+
+
+
+### Automatic Speech Recognition
+
+Find out more about Automatic Speech Recognition [here](../tasks/automatic_speech_recognition).
+
+
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+
+
+
+### Feature Extraction
+
+Find out more about Feature Extraction [here](../tasks/feature_extraction).
+
+
+
+
+### Fill Mask
+
+Find out more about Fill Mask [here](../tasks/fill_mask).
+
+
+
+
+### Image Classification
+
+Find out more about Image Classification [here](../tasks/image_classification).
+
+
+
+
+### Image To Image
+
+Find out more about Image To Image [here](../tasks/image_to_image).
+
+
+
+
+### Object Detection
+
+Find out more about Object Detection [here](../tasks/object_detection).
+
+
+
+
+### Question Answering
+
+Find out more about Question Answering [here](../tasks/question_answering).
+
+
+
+
+### Summarization
+
+Find out more about Summarization [here](../tasks/summarization).
+
+
+
+
+### Text Classification
+
+Find out more about Text Classification [here](../tasks/text_classification).
+
+
+
+
+### Text Generation
+
+Find out more about Text Generation [here](../tasks/text_generation).
+
+
+
+
+### Text To Image
+
+Find out more about Text To Image [here](../tasks/text_to_image).
+
+
+
+
+### Text To Video
+
+Find out more about Text To Video [here](../tasks/text_to_video).
+
+
+
+
+### Token Classification
+
+Find out more about Token Classification [here](../tasks/token_classification).
+
+
+
+
+### Translation
+
+Find out more about Translation [here](../tasks/translation).
+
+
+
+
+### Zero Shot Classification
+
+Find out more about Zero Shot Classification [here](../tasks/zero_shot_classification).
+
+
+
diff --git a/docs/inference-providers/providers/hyperbolic.md b/docs/inference-providers/providers/hyperbolic.md
new file mode 100644
index 000000000..18a3ed0bc
--- /dev/null
+++ b/docs/inference-providers/providers/hyperbolic.md
@@ -0,0 +1,40 @@
+
+
+# Hyperbolic
+
+[](https://hyperbolic.xyz/)
+
+[](https://huggingface.co/hyperbolic)
+
+Hyperbolic is building an open-access platform for AI development by aggregating idle computing resources and making it seamlessly simple to use them.
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+
+
diff --git a/docs/inference-providers/providers/nebius.md b/docs/inference-providers/providers/nebius.md
new file mode 100644
index 000000000..995b607d0
--- /dev/null
+++ b/docs/inference-providers/providers/nebius.md
@@ -0,0 +1,50 @@
+
+
+# Nebius
+
+[](https://nebius.com/)
+
+[](https://huggingface.co/nebius)
+
+Nebius AI is a technology company specializing in AI-centric cloud platforms, offering scalable GPU clusters, managed services, and developer tools designed for intensive AI workloads. Headquartered in Amsterdam, Nebius provides flexible architecture and high-performance infrastructure to support AI model training and inference at any scale.
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+
+
+
+### Text To Image
+
+Find out more about Text To Image [here](../tasks/text_to_image).
+
+
+
diff --git a/docs/inference-providers/providers/novita.md b/docs/inference-providers/providers/novita.md
new file mode 100644
index 000000000..1dd142e6f
--- /dev/null
+++ b/docs/inference-providers/providers/novita.md
@@ -0,0 +1,50 @@
+
+
+# Novita
+
+[](https://novita.ai/)
+
+[](https://huggingface.co/novita)
+
+Novita AI is a comprehensive AI cloud platform that provides developers and businesses with access to over 200 APIs for tasks such as image generation, video processing, audio synthesis, and large language models.
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+
+
+
+### Text To Video
+
+Find out more about Text To Video [here](../tasks/text_to_video).
+
+
+
diff --git a/docs/inference-providers/providers/replicate.md b/docs/inference-providers/providers/replicate.md
new file mode 100644
index 000000000..64536159f
--- /dev/null
+++ b/docs/inference-providers/providers/replicate.md
@@ -0,0 +1,40 @@
+
+
+# Replicate
+
+[](https://replicate.com/)
+
+[](https://huggingface.co/replicate)
+
+Replicate is building tools so all software engineers can use AI as if it were normal software. You should be able to import an image generator the same way you import an npm package. You should be able to customize a model as easily as you can fork something on GitHub.
+
+## Supported tasks
+
+
+### Text To Image
+
+Find out more about Text To Image [here](../tasks/text_to_image).
+
+
+
+
+### Text To Video
+
+Find out more about Text To Video [here](../tasks/text_to_video).
+
+
+
diff --git a/docs/inference-providers/providers/sambanova.md b/docs/inference-providers/providers/sambanova.md
new file mode 100644
index 000000000..1a2923e7f
--- /dev/null
+++ b/docs/inference-providers/providers/sambanova.md
@@ -0,0 +1,51 @@
+
+
+# SambaNova
+
+[](https://sambanova.ai/)
+
+[](https://huggingface.co/sambanovasystems)
+
+SambaNova's AI platform is the technology backbone for the next decade of AI innovation.
+Customers are turning to SambaNova to quickly deploy state-of-the-art AI and deep learning capabilities that help them outcompete their peers.
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+
+
+
+### Feature Extraction
+
+Find out more about Feature Extraction [here](../tasks/feature_extraction).
+
+
+
diff --git a/docs/inference-providers/providers/together.md b/docs/inference-providers/providers/together.md
new file mode 100644
index 000000000..24e3389f9
--- /dev/null
+++ b/docs/inference-providers/providers/together.md
@@ -0,0 +1,60 @@
+
+
+# Together
+
+[](https://www.together.ai/)
+
+[](https://huggingface.co/togethercomputer)
+
+Together decentralized cloud services empower developers and researchers at organizations of all sizes to train, fine-tune, and deploy generative AI models.
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+
+
+
+### Text Generation
+
+Find out more about Text Generation [here](../tasks/text_generation).
+
+
+
+
+### Text To Image
+
+Find out more about Text To Image [here](../tasks/text_to_image).
+
+
+
diff --git a/scripts/inference-providers/scripts/generate.ts b/scripts/inference-providers/scripts/generate.ts
index 24a937b8e..2daa03096 100644
--- a/scripts/inference-providers/scripts/generate.ts
+++ b/scripts/inference-providers/scripts/generate.ts
@@ -107,6 +107,11 @@ const ROOT_DIR = path
const TEMPLATE_DIR = path.join(ROOT_DIR, "templates");
const DOCS_DIR = path.join(ROOT_DIR, "..", "..", "docs");
const TASKS_DOCS_DIR = path.join(DOCS_DIR, "inference-providers", "tasks");
+const PROVIDERS_DOCS_DIR = path.join(
+ DOCS_DIR,
+ "inference-providers",
+ "providers"
+);
const NBSP = " "; // non-breaking space
const TABLE_INDENT = NBSP.repeat(8);
@@ -136,6 +141,21 @@ function writeTaskDoc(templateName: string, content: string): Promise {
);
}
+function writeProviderDoc(
+ templateName: string,
+ content: string
+): Promise {
+ const providerDocPath = path.join(PROVIDERS_DOCS_DIR, `${templateName}.md`);
+ console.log(` 💾 Saving to ${providerDocPath}`);
+ const header = PROVIDER_PAGE_HEADER({ provider: templateName });
+ const contentWithHeader = `\n\n${content}`;
+ return fs
+ .mkdir(TASKS_DOCS_DIR, { recursive: true })
+ .then(() =>
+ fs.writeFile(providerDocPath, contentWithHeader, { encoding: "utf-8" })
+ );
+}
+
/////////////////////////
//// Task page utils ////
/////////////////////////
@@ -336,6 +356,9 @@ const SPECS_HEADERS = await readTemplate("specs-headers", "common");
const PAGE_HEADER = Handlebars.compile(
await readTemplate("page-header", "common")
);
+const PROVIDER_PAGE_HEADER = Handlebars.compile(
+ await readTemplate("provider-header", "common")
+);
const SNIPPETS_TEMPLATE = Handlebars.compile(
await readTemplate("snippets-template", "common")
);
@@ -345,6 +368,9 @@ const SPECS_PAYLOAD_TEMPLATE = Handlebars.compile(
const SPECS_OUTPUT_TEMPLATE = Handlebars.compile(
await readTemplate("specs-output", "common")
);
+const PROVIDER_TASKS_TEMPLATE = Handlebars.compile(
+ await readTemplate("provider-tasks", "common")
+);
////////////////////
//// Data utils ////
@@ -355,7 +381,7 @@ const DATA: {
specsHeaders: string;
};
recommendedModels: Record<
- string,
+ string, // task
{
id: string;
description: string;
@@ -364,7 +390,7 @@ const DATA: {
}[]
>;
perProviderWarmModels: Record<
- string,
+ string, // task
{
modelId: string;
provider: string;
@@ -574,8 +600,12 @@ async function fetchChatCompletion() {
"text-generation"
].filter((model) => model.tags?.includes("conversational"));
+ DATA.perProviderWarmModels["chat-completion"] = await fetchWarmModels(
+ "text-generation",
+ true
+ );
const providersMappingChatCompletion = buildProviderMapping(
- await fetchWarmModels("text-generation", true)
+ DATA.perProviderWarmModels["chat-completion"]
);
DATA.snippets["chat-completion"] = SNIPPETS_TEMPLATE({
task: "text-generation",
@@ -594,8 +624,12 @@ async function fetchChatCompletion() {
DATA.recommendedModels["image-text-to-text"].filter((model) =>
model.tags?.includes("conversational")
);
+ DATA.perProviderWarmModels["image-text-to-text"] = await fetchWarmModels(
+ "image-text-to-text",
+ true
+ );
const providersMappingImageTextToText = buildProviderMapping(
- await fetchWarmModels("image-text-to-text", true)
+ DATA.perProviderWarmModels["image-text-to-text"]
);
DATA.snippets["conversational-image-text-to-text"] = SNIPPETS_TEMPLATE({
@@ -610,16 +644,82 @@ async function fetchChatCompletion() {
await fetchChatCompletion();
+///////////////////////////////
+//// Providers pages utils ////
+///////////////////////////////
+
+const PER_PROVIDER_TASKS: Record<
+ string, // provider
+ {
+ provider: string;
+ pipelineTag: string;
+ title: string;
+ linkAnchor: string;
+ modelId: string;
+ providerModelId: string;
+ conversational: boolean;
+ }[]
+> = {};
+
+// Populate PER_PROVIDER_TASKS based on DATA.perProviderWarmModels
+Object.entries(DATA.perProviderWarmModels).forEach(([task, models]) => {
+ models.forEach((model) => {
+ if (!PER_PROVIDER_TASKS[model.provider]) {
+ PER_PROVIDER_TASKS[model.provider] = [];
+ }
+ let conversational = ["chat-completion", "image-text-to-text"].includes(
+ task
+ );
+ let title = conversational
+ ? task == "image-text-to-text"
+ ? "Chat Completion (VLM)"
+ : "Chat Completion (LLM)"
+ : task
+ .replaceAll("-", " ")
+ .split(" ")
+ .map((word) => word[0].toUpperCase() + word.slice(1))
+ .join(" ");
+
+ let linkAnchor = conversational
+ ? "chat-completion"
+ : task.replaceAll("-", "_");
+
+ let pipelineTag = task === "chat-completion" ? "text-generation" : task;
+
+ PER_PROVIDER_TASKS[model.provider].push({
+ provider: model.provider,
+ pipelineTag,
+ title,
+ linkAnchor,
+ modelId: model.modelId,
+ providerModelId: model.providerModelId,
+ conversational,
+ });
+ });
+});
+
+// sort tasks by title
+Object.entries(PER_PROVIDER_TASKS).forEach(([provider, tasks]) => {
+ PER_PROVIDER_TASKS[provider] = tasks.sort((a, b) =>
+ a.title.localeCompare(b.title)
+ );
+});
+
+console.log(PER_PROVIDER_TASKS);
+
/////////////////////////
//// Rendering utils ////
/////////////////////////
async function renderTemplate(
templateName: string,
+ namespace: string,
data: JsonObject
): Promise {
- console.log(`🎨 Rendering ${templateName}`);
- const template = Handlebars.compile(await readTemplate(templateName, "task"));
+ console.log(`🎨 Rendering ${templateName} (${namespace})`);
+ const template = Handlebars.compile(
+ await readTemplate(templateName, namespace)
+ );
return template(data);
}
@@ -629,9 +729,18 @@ await Promise.all(
return; // not generated -> merged with chat-completion
}
// @ts-ignore
- const rendered = await renderTemplate(task, DATA);
+ const rendered = await renderTemplate(task, "task", DATA);
await writeTaskDoc(task, rendered);
})
);
+await Promise.all(
+ Object.entries(PER_PROVIDER_TASKS).map(async ([provider, tasks]) => {
+ const rendered = await renderTemplate(provider, "providers", {
+ tasksSection: PROVIDER_TASKS_TEMPLATE({ tasks }),
+ });
+ await writeProviderDoc(provider, rendered);
+ })
+);
+
console.log("✅ All done!");
diff --git a/scripts/inference-providers/templates/common/provider-header.handlebars b/scripts/inference-providers/templates/common/provider-header.handlebars
new file mode 100644
index 000000000..f2cf9dabc
--- /dev/null
+++ b/scripts/inference-providers/templates/common/provider-header.handlebars
@@ -0,0 +1,7 @@
+WARNING
+
+This markdown file has been generated from a script. Please do not edit it directly.
+
+If you want to update the content related to {{provider}}'s description, please edit the template file under `https://github.com/huggingface/hub-docs/tree/main/scripts/inference-providers/templates/providers/{{provider}}.handlebars`.
+
+For more details, check out the `generate.ts` script: https://github.com/huggingface/hub-docs/blob/main/scripts/inference-providers/scripts/generate.ts.
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/common/provider-tasks.handlebars b/scripts/inference-providers/templates/common/provider-tasks.handlebars
new file mode 100644
index 000000000..e24ebd8ec
--- /dev/null
+++ b/scripts/inference-providers/templates/common/provider-tasks.handlebars
@@ -0,0 +1,14 @@
+## Supported tasks
+
+{{#each tasks}}
+
+### {{title}}
+
+Find out more about {{title}} [here](../tasks/{{linkAnchor}}).
+
+
+
+{{/each}}
diff --git a/scripts/inference-providers/templates/providers/cerebras.handlebars b/scripts/inference-providers/templates/providers/cerebras.handlebars
new file mode 100644
index 000000000..7c07778fa
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/cerebras.handlebars
@@ -0,0 +1,9 @@
+# Cerebras
+
+[](https://www.cerebras.ai/)
+
+[](https://huggingface.co/cerebras)
+
+Cerebras stands alone as the world’s fastest AI inference and training platform. Organizations across fields like medical research, cryptography, energy, and agentic AI use our CS-2 and CS-3 systems to build on-premise supercomputers, while developers and enterprises everywhere can access the power of Cerebras through our pay-as-you-go cloud offerings.
+
+{{{tasksSection}}}
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/providers/fal-ai.handlebars b/scripts/inference-providers/templates/providers/fal-ai.handlebars
new file mode 100644
index 000000000..f568dbe43
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/fal-ai.handlebars
@@ -0,0 +1,9 @@
+# Fal
+
+[](https://fal.ai/)
+
+[](https://huggingface.co/fal)
+
+Founded in 2021 by [Burkay Gur](https://huggingface.co/burkaygur) and [Gorkem Yurtseven](https://huggingface.co/gorkemyurt), fal.ai was born out of a shared passion for AI and a desire to address the challenges in AI infrastructure observed during their tenures at Coinbase and Amazon.
+
+{{{tasksSection}}}
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/providers/fireworks-ai.handlebars b/scripts/inference-providers/templates/providers/fireworks-ai.handlebars
new file mode 100644
index 000000000..25e118d06
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/fireworks-ai.handlebars
@@ -0,0 +1,8 @@
+# Fireworks AI
+
+[](https://fireworks.ai/)
+
+[](https://huggingface.co/fireworks-ai)
+
+Fireworks AI is a developer-centric platform that delivers high-performance generative AI solutions, enabling efficient deployment and fine-tuning of large language models (LLMs) and image models.
+{{{tasksSection}}}
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/providers/hf-inference.handlebars b/scripts/inference-providers/templates/providers/hf-inference.handlebars
new file mode 100644
index 000000000..8fb73e0aa
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/hf-inference.handlebars
@@ -0,0 +1,10 @@
+# HF Inference
+
+[](https://huggingface.co/)
+
+[](https://huggingface.co/hf-inference)
+
+HF Inference is the serverless Inference API powered by Hugging Face. This service used to be called "Inference API (serverless)" prior to Inference Providers.
+If you are interested in deploying models to a dedicated and autoscaling infrastructure managed by Hugging Face, check out [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index) instead.
+
+{{{tasksSection}}}
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/providers/hyperbolic.handlebars b/scripts/inference-providers/templates/providers/hyperbolic.handlebars
new file mode 100644
index 000000000..f7fedc288
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/hyperbolic.handlebars
@@ -0,0 +1,9 @@
+# Hyperbolic
+
+[](https://hyperbolic.xyz/)
+
+[](https://huggingface.co/hyperbolic)
+
+Hyperbolic is building an open-access platform for AI development by aggregating idle computing resources and making it seamlessly simple to use them.
+
+{{{tasksSection}}}
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/providers/nebius.handlebars b/scripts/inference-providers/templates/providers/nebius.handlebars
new file mode 100644
index 000000000..2135e00b8
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/nebius.handlebars
@@ -0,0 +1,9 @@
+# Nebius
+
+[](https://nebius.com/)
+
+[](https://huggingface.co/nebius)
+
+Nebius AI is a technology company specializing in AI-centric cloud platforms, offering scalable GPU clusters, managed services, and developer tools designed for intensive AI workloads. Headquartered in Amsterdam, Nebius provides flexible architecture and high-performance infrastructure to support AI model training and inference at any scale.
+
+{{{tasksSection}}}
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/providers/novita.handlebars b/scripts/inference-providers/templates/providers/novita.handlebars
new file mode 100644
index 000000000..2ef3872ef
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/novita.handlebars
@@ -0,0 +1,9 @@
+# Novita
+
+[](https://novita.ai/)
+
+[](https://huggingface.co/novita)
+
+Novita AI is a comprehensive AI cloud platform that provides developers and businesses with access to over 200 APIs for tasks such as image generation, video processing, audio synthesis, and large language models.
+
+{{{tasksSection}}}
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/providers/replicate.handlebars b/scripts/inference-providers/templates/providers/replicate.handlebars
new file mode 100644
index 000000000..c1f31c73c
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/replicate.handlebars
@@ -0,0 +1,9 @@
+# Replicate
+
+[](https://replicate.com/)
+
+[](https://huggingface.co/replicate)
+
+Replicate is building tools so all software engineers can use AI as if it were normal software. You should be able to import an image generator the same way you import an npm package. You should be able to customize a model as easily as you can fork something on GitHub.
+
+{{{tasksSection}}}
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/providers/sambanova.handlebars b/scripts/inference-providers/templates/providers/sambanova.handlebars
new file mode 100644
index 000000000..7f7b4b4ca
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/sambanova.handlebars
@@ -0,0 +1,10 @@
+# SambaNova
+
+[](https://sambanova.ai/)
+
+[](https://huggingface.co/sambanovasystems)
+
+SambaNova's AI platform is the technology backbone for the next decade of AI innovation.
+Customers are turning to SambaNova to quickly deploy state-of-the-art AI and deep learning capabilities that help them outcompete their peers.
+
+{{{tasksSection}}}
\ No newline at end of file
diff --git a/scripts/inference-providers/templates/providers/together.handlebars b/scripts/inference-providers/templates/providers/together.handlebars
new file mode 100644
index 000000000..910309e71
--- /dev/null
+++ b/scripts/inference-providers/templates/providers/together.handlebars
@@ -0,0 +1,9 @@
+# Together
+
+[](https://www.together.ai/)
+
+[](https://huggingface.co/togethercomputer)
+
+Together decentralized cloud services empower developers and researchers at organizations of all sizes to train, fine-tune, and deploy generative AI models.
+
+{{{tasksSection}}}
\ No newline at end of file