[Inference Providers] add Public AI

docs/inference-providers/_toctree.yml

@@ -97,6 +97,8 @@
     title: Novita
   - local: providers/nscale
     title: Nscale
+  - local: providers/publicai
+    title: Public AI
   - local: providers/replicate
     title: Replicate
   - local: providers/sambanova

docs/inference-providers/index.md

@@ -24,6 +24,7 @@ Our platform integrates with leading AI infrastructure providers, giving you acc
 | [Nebius](./providers/nebius)                 |          ✅           |          ✅           |         ✅         |      ✅       |               |                |
 | [Novita](./providers/novita)                 |          ✅           |          ✅           |                    |               |      ✅       |                |
 | [Nscale](./providers/nscale)                 |          ✅           |          ✅           |                    |      ✅       |               |                |
+| [Public AI](./providers/publicai)             |          ✅           |                       |                    |               |               |                |
 | [Replicate](./providers/replicate)           |                       |                       |                    |      ✅       |      ✅       |       ✅       |
 | [SambaNova](./providers/sambanova)           |          ✅           |                       |         ✅         |               |               |                |
 | [Scaleway](./providers/scaleway)           |          ✅           |                       |         ✅         |               |               |                |

docs/inference-providers/providers/hf-inference.md

@@ -193,7 +193,7 @@ Find out more about Translation [here](../tasks/translation).
 
 <InferenceSnippet
     pipeline=translation
-    providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-base","providerModelId":"google-t5/t5-base"} } }
+    providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-small","providerModelId":"google-t5/t5-small"} } }
 />
 
 

docs/inference-providers/providers/publicai.md

@@ -0,0 +1,57 @@
+<!---
+WARNING
+
+This markdown file has been generated from a script. Please do not edit it directly.
+
+### Template
+
+If you want to update the content related to publicai's description, please edit the template file under `https://github.com/huggingface/hub-docs/tree/main/scripts/inference-providers/templates/providers/publicai.handlebars`.
+
+### Logos
+
+If you want to update publicai's logo, upload a file by opening a PR on https://huggingface.co/datasets/huggingface/documentation-images/tree/main/inference-providers/logos. Ping @wauplin and @celinah on the PR to let them know you uploaded a new logo.
+Logos must be in .png format and be named `publicai-light.png` and `publicai-dark.png`. Visit https://huggingface.co/settings/theme to switch between light and dark mode and check that the logos are displayed correctly.
+
+### Generation script
+
+For more details, check out the `generate.ts` script: https://github.com/huggingface/hub-docs/blob/main/scripts/inference-providers/scripts/generate.ts.
+--->
+
+# PublicAI
+
+<Tip>
+
+All models supported by the PublicAI Inference Utility can be found [here](https://huggingface.co/models?inference_provider=publicai&sort=trending)
+
+</Tip>
+
+<div class="flex justify-center">
+    <a href="https://publicai.co/" target="_blank">
+        <img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/publicai-light.png"/>
+        <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/publicai-dark.png"/>
+    </a>
+</div>
+
+<div class="flex">
+    <a href="https://huggingface.co/publicai" target="_blank">
+        <img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-us-on-hf-lg.svg"/>
+        <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/follow-us-on-hf-lg-dark.svg"/>
+    </a>
+</div>
+
+The Public AI Inference Utility is a nonprofit, open-source project. Their team builds products and organizes advocacy to support the work of public AI model builders like the Swiss AI Initiative, AI Singapore, AI Sweden, and the Barcelona Supercomputing Center.
+
+They believe in public AI — AI as public infrastructure like highways, water, or electricity. Think of a BBC for AI, a public utility for AI, or public libraries for AI.
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+<InferenceSnippet
+    pipeline=text-generation
+    providersMapping={ {"publicai":{"modelId":"swiss-ai/Apertus-8B-Instruct-2509","providerModelId":"swiss-ai/apertus-8b-instruct"} } }
+conversational />
+

docs/inference-providers/tasks/chat-completion.md

@@ -64,7 +64,7 @@ The API supports:
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"cerebras":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"cohere":{"modelId":"CohereLabs/command-a-reasoning-08-2025","providerModelId":"command-a-reasoning-08-2025"},"featherless-ai":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"accounts/fireworks/models/deepseek-v3p1"},"groq":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"hf-inference":{"modelId":"HuggingFaceTB/SmolLM3-3B","providerModelId":"HuggingFaceTB/SmolLM3-3B"},"hyperbolic":{"modelId":"Qwen/Qwen3-Next-80B-A3B-Instruct","providerModelId":"Qwen/Qwen3-Next-80B-A3B-Instruct"},"nebius":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"novita":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"deepseek/deepseek-v3.1"},"nscale":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"sambanova":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"Meta-Llama-3.1-8B-Instruct"},"scaleway":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"together":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"deepseek-ai/DeepSeek-V3.1"}} }
+    providersMapping={ {"cerebras":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"cohere":{"modelId":"CohereLabs/command-a-reasoning-08-2025","providerModelId":"command-a-reasoning-08-2025"},"featherless-ai":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"accounts/fireworks/models/deepseek-v3p1"},"groq":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"hf-inference":{"modelId":"HuggingFaceTB/SmolLM3-3B","providerModelId":"HuggingFaceTB/SmolLM3-3B"},"hyperbolic":{"modelId":"Qwen/Qwen3-Next-80B-A3B-Instruct","providerModelId":"Qwen/Qwen3-Next-80B-A3B-Instruct"},"nebius":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"novita":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"deepseek/deepseek-v3.1"},"nscale":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"},"publicai":{"modelId":"swiss-ai/Apertus-8B-Instruct-2509","providerModelId":"swiss-ai/apertus-8b-instruct"},"sambanova":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"Meta-Llama-3.1-8B-Instruct"},"scaleway":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"together":{"modelId":"deepseek-ai/DeepSeek-V3.1","providerModelId":"deepseek-ai/DeepSeek-V3.1"}} }
 conversational />
 
 

docs/inference-providers/tasks/image-segmentation.md

@@ -24,7 +24,6 @@ For more details about the `image-segmentation` task, check out its [dedicated p
 
 ### Recommended models
 
-- [facebook/mask2former-swin-large-coco-panoptic](https://huggingface.co/facebook/mask2former-swin-large-coco-panoptic): Panoptic segmentation model trained on the COCO (common objects) dataset.
 
 Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=image-segmentation&sort=trending).
 

docs/inference-providers/tasks/text-classification.md

@@ -26,6 +26,9 @@ For more details about the `text-classification` task, check out its [dedicated
 
 - [distilbert/distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english): A robust model trained for sentiment analysis.
 - [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert): A sentiment analysis model specialized in financial sentiment.
+- [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest): A sentiment analysis model specialized in analyzing tweets.
+- [papluca/xlm-roberta-base-language-detection](https://huggingface.co/papluca/xlm-roberta-base-language-detection): A model that can classify languages.
+- [meta-llama/Prompt-Guard-86M](https://huggingface.co/meta-llama/Prompt-Guard-86M): A model that can classify text generation attacks.
 
 Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=text-classification&sort=trending).
 

docs/inference-providers/tasks/translation.md

@@ -33,7 +33,7 @@ Explore all available models and find the one that suits you best [here](https:/
 
 <InferenceSnippet
     pipeline=translation
-    providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-base","providerModelId":"google-t5/t5-base"}} }
+    providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-small","providerModelId":"google-t5/t5-small"}} }
 />
 
 

docs/inference-providers/tasks/zero-shot-classification.md

@@ -25,6 +25,7 @@ For more details about the `zero-shot-classification` task, check out its [dedic
 ### Recommended models
 
 - [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli): Powerful zero-shot text classification model.
+- [MoritzLaurer/ModernBERT-large-zeroshot-v2.0](https://huggingface.co/MoritzLaurer/ModernBERT-large-zeroshot-v2.0): Cutting-edge zero-shot multilingual text classification model.
 
 Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=zero-shot-classification&sort=trending).
 

scripts/inference-providers/scripts/generate.ts

@@ -44,6 +44,7 @@ const PROVIDERS_HUB_ORGS: Record<string, string> = {
   nebius: "nebius",
   novita: "novita",
   nscale: "nscale",
+  publicai: "publicai",
   replicate: "replicate",
   sambanova: "sambanovasystems",
   scaleway: "scaleway",
@@ -62,6 +63,7 @@ const PROVIDERS_URLS: Record<string, string> = {
   nebius: "https://nebius.com/",
   novita: "https://novita.ai/",
   nscale: "https://www.nscale.com/",
+  publicai: "https://publicai.co/",
   replicate: "https://replicate.com/",
   sambanova: "https://sambanova.ai/",
   scaleway: "https://www.scaleway.com",

scripts/inference-providers/templates/providers/publicai.handlebars

@@ -0,0 +1,17 @@
+# PublicAI
+
+<Tip>
+
+All models supported by the PublicAI Inference Utility can be found [here](https://huggingface.co/models?inference_provider=publicai&sort=trending)
+
+</Tip>
+
+{{{logoSection}}}
+
+{{{followUsSection}}}
+
+The Public AI Inference Utility is a nonprofit, open-source project. Their team builds products and organizes advocacy to support the work of public AI model builders like the Swiss AI Initiative, AI Singapore, AI Sweden, and the Barcelona Supercomputing Center.
+
+They believe in public AI — AI as public infrastructure like highways, water, or electricity. Think of a BBC for AI, a public utility for AI, or public libraries for AI.
+
+{{{tasksSection}}}