Add Groq to provider docs

docs/inference-providers/_toctree.yml

@@ -23,6 +23,8 @@
     title: Featherless AI
   - local: providers/fireworks-ai
     title: Fireworks
+  - local: providers/groq
+    title: Groq
   - local: providers/hyperbolic
     title: Hyperbolic
   - local: providers/hf-inference

docs/inference-providers/index.md

@@ -20,6 +20,7 @@ Here is the complete list of partners integrated with Inference Providers, and t
 | [Fal AI](./providers/fal-ai)             |                       |                       |                    |       ✅       |       ✅       |
 | [Featherless AI](./providers/featherless-ai) |    ✅           |                        |                     |             |                |
 | [Fireworks](./providers/fireworks-ai)    |           ✅           |           ✅           |                    |               |               |
+| [Groq](./providers/groq)                  |           ✅           |                       |                    |               |               |
 | [HF Inference](./providers/hf-inference) |           ✅           |           ✅           |         ✅          |       ✅       |               |
 | [Hyperbolic](./providers/hyperbolic)     |           ✅           |           ✅           |                    |               |               |
 | [Nebius](./providers/nebius)             |           ✅           |           ✅           |         ✅         |       ✅       |               |

docs/inference-providers/providers/cohere.md

@@ -56,6 +56,6 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
     pipeline=image-text-to-text
-    providersMapping={ {"cohere":{"modelId":"CohereLabs/aya-vision-32b","providerModelId":"c4ai-aya-vision-32b"} } }
+    providersMapping={ {"cohere":{"modelId":"CohereLabs/aya-vision-8b","providerModelId":"c4ai-aya-vision-8b"} } }
 conversational />
 

docs/inference-providers/providers/groq.md

@@ -0,0 +1,69 @@
+<!---
+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 groq's description, please edit the template file under `https://github.com/huggingface/hub-docs/tree/main/scripts/inference-providers/templates/providers/groq.handlebars`.
+
+### Logos
+
+If you want to update groq'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 `groq-light.png` and `groq-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.
+--->
+
+# Groq
+
+<div class="flex justify-center">
+    <a href="https://groq.com/" target="_blank">
+        <img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/groq-light.png"/>
+        <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/logos/groq-dark.png"/>
+    </a>
+</div>
+
+<div class="flex">
+    <a href="https://huggingface.co/groq" 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>
+
+Groq is fast AI inference. Their groundbreaking LPU technology delivers record-setting performance and efficiency for GenAI models. With custom chips specifically designed for AI inference workloads and a deterministic, software-first approach, Groq eliminates the bottlenecks of conventional hardware to enable real-time AI applications with predictable latency and exceptional throughput so developers can build fast.
+
+For latest pricing, visit our [pricing page](https://groq.com/pricing/).
+
+## Resources
+ - **Website**: https://groq.com/
+ - **Documentation**: https://console.groq.com/docs
+ - **Community Forum**: https://community.groq.com/
+ - **X**: [@GroqInc](https://x.com/GroqInc)
+ - **LinkedIn**: [Groq](https://www.linkedin.com/company/groq/)
+ - **YouTube**: [Groq](https://www.youtube.com/@GroqInc)
+
+## Supported tasks
+
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+<InferenceSnippet
+    pipeline=text-generation
+    providersMapping={ {"groq":{"modelId":"Qwen/Qwen3-32B","providerModelId":"qwen/qwen3-32b"} } }
+conversational />
+
+
+### Chat Completion (VLM)
+
+Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
+
+<InferenceSnippet
+    pipeline=image-text-to-text
+    providersMapping={ {"groq":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"} } }
+conversational />
+

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

@@ -38,163 +38,146 @@ If you are interested in deploying models to a dedicated and autoscaling infrast
 
 ## Supported tasks
 
-
 ### Automatic Speech Recognition
 
 Find out more about Automatic Speech Recognition [here](../tasks/automatic_speech_recognition).
 
 <InferenceSnippet
-    pipeline=automatic-speech-recognition
-    providersMapping={ {"hf-inference":{"modelId":"openai/whisper-large-v3","providerModelId":"openai/whisper-large-v3"} } }
+pipeline=automatic-speech-recognition
+providersMapping={ {"hf-inference":{"modelId":"openai/whisper-large-v3","providerModelId":"openai/whisper-large-v3"} } }
 />
 
-
 ### Chat Completion (LLM)
 
 Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
-    pipeline=text-generation
-    providersMapping={ {"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"} } }
+pipeline=text-generation
+providersMapping={ {"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"} } }
 conversational />
 
-
 ### Chat Completion (VLM)
 
 Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
-    pipeline=image-text-to-text
-    providersMapping={ {"hf-inference":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"meta-llama/Llama-3.2-11B-Vision-Instruct"} } }
+pipeline=image-text-to-text
+providersMapping={ {"hf-inference":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"meta-llama/Llama-3.2-11B-Vision-Instruct"} } }
 conversational />
 
-
 ### Feature Extraction
 
 Find out more about Feature Extraction [here](../tasks/feature_extraction).
 
 <InferenceSnippet
-    pipeline=feature-extraction
-    providersMapping={ {"hf-inference":{"modelId":"intfloat/multilingual-e5-large-instruct","providerModelId":"intfloat/multilingual-e5-large-instruct"} } }
+pipeline=feature-extraction
+providersMapping={ {"hf-inference":{"modelId":"intfloat/multilingual-e5-large-instruct","providerModelId":"intfloat/multilingual-e5-large-instruct"} } }
 />
 
-
 ### Fill Mask
 
 Find out more about Fill Mask [here](../tasks/fill_mask).
 
 <InferenceSnippet
-    pipeline=fill-mask
-    providersMapping={ {"hf-inference":{"modelId":"google-bert/bert-base-uncased","providerModelId":"google-bert/bert-base-uncased"} } }
+pipeline=fill-mask
+providersMapping={ {"hf-inference":{"modelId":"google-bert/bert-base-uncased","providerModelId":"google-bert/bert-base-uncased"} } }
 />
 
-
 ### Image Classification
 
 Find out more about Image Classification [here](../tasks/image_classification).
 
 <InferenceSnippet
-    pipeline=image-classification
-    providersMapping={ {"hf-inference":{"modelId":"Falconsai/nsfw_image_detection","providerModelId":"Falconsai/nsfw_image_detection"} } }
+pipeline=image-classification
+providersMapping={ {"hf-inference":{"modelId":"Falconsai/nsfw_image_detection","providerModelId":"Falconsai/nsfw_image_detection"} } }
 />
 
-
 ### Image Segmentation
 
 Find out more about Image Segmentation [here](../tasks/image_segmentation).
 
 <InferenceSnippet
-    pipeline=image-segmentation
-    providersMapping={ {"hf-inference":{"modelId":"mattmdjaga/segformer_b2_clothes","providerModelId":"mattmdjaga/segformer_b2_clothes"} } }
+pipeline=image-segmentation
+providersMapping={ {"hf-inference":{"modelId":"mattmdjaga/segformer_b2_clothes","providerModelId":"mattmdjaga/segformer_b2_clothes"} } }
 />
 
-
 ### Object Detection
 
 Find out more about Object Detection [here](../tasks/object_detection).
 
 <InferenceSnippet
-    pipeline=object-detection
-    providersMapping={ {"hf-inference":{"modelId":"facebook/detr-resnet-50","providerModelId":"facebook/detr-resnet-50"} } }
+pipeline=object-detection
+providersMapping={ {"hf-inference":{"modelId":"facebook/detr-resnet-50","providerModelId":"facebook/detr-resnet-50"} } }
 />
 
-
 ### Question Answering
 
 Find out more about Question Answering [here](../tasks/question_answering).
 
 <InferenceSnippet
-    pipeline=question-answering
-    providersMapping={ {"hf-inference":{"modelId":"deepset/roberta-base-squad2","providerModelId":"deepset/roberta-base-squad2"} } }
+pipeline=question-answering
+providersMapping={ {"hf-inference":{"modelId":"deepset/roberta-base-squad2","providerModelId":"deepset/roberta-base-squad2"} } }
 />
 
-
 ### Summarization
 
 Find out more about Summarization [here](../tasks/summarization).
 
 <InferenceSnippet
-    pipeline=summarization
-    providersMapping={ {"hf-inference":{"modelId":"facebook/bart-large-cnn","providerModelId":"facebook/bart-large-cnn"} } }
+pipeline=summarization
+providersMapping={ {"hf-inference":{"modelId":"facebook/bart-large-cnn","providerModelId":"facebook/bart-large-cnn"} } }
 />
 
-
 ### Table Question Answering
 
 Find out more about Table Question Answering [here](../tasks/table_question_answering).
 
 <InferenceSnippet
-    pipeline=table-question-answering
-    providersMapping={ {"hf-inference":{"modelId":"google/tapas-base-finetuned-wtq","providerModelId":"google/tapas-base-finetuned-wtq"} } }
+pipeline=table-question-answering
+providersMapping={ {"hf-inference":{"modelId":"google/tapas-base-finetuned-wtq","providerModelId":"google/tapas-base-finetuned-wtq"} } }
 />
 
-
 ### Text Classification
 
 Find out more about Text Classification [here](../tasks/text_classification).
 
 <InferenceSnippet
-    pipeline=text-classification
-    providersMapping={ {"hf-inference":{"modelId":"tabularisai/multilingual-sentiment-analysis","providerModelId":"tabularisai/multilingual-sentiment-analysis"} } }
+pipeline=text-classification
+providersMapping={ {"hf-inference":{"modelId":"tabularisai/multilingual-sentiment-analysis","providerModelId":"tabularisai/multilingual-sentiment-analysis"} } }
 />
 
-
 ### Text Generation
 
 Find out more about Text Generation [here](../tasks/text_generation).
 
 <InferenceSnippet
-    pipeline=text-generation
-    providersMapping={ {"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"} } }
+pipeline=text-generation
+providersMapping={ {"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"} } }
 />
 
-
 ### Text To Image
 
 Find out more about Text To Image [here](../tasks/text_to_image).
 
 <InferenceSnippet
-    pipeline=text-to-image
-    providersMapping={ {"hf-inference":{"modelId":"black-forest-labs/FLUX.1-dev","providerModelId":"black-forest-labs/FLUX.1-dev"} } }
+pipeline=text-to-image
+providersMapping={ {"hf-inference":{"modelId":"black-forest-labs/FLUX.1-dev","providerModelId":"black-forest-labs/FLUX.1-dev"} } }
 />
 
-
 ### Token Classification
 
 Find out more about Token Classification [here](../tasks/token_classification).
 
 <InferenceSnippet
-    pipeline=token-classification
-    providersMapping={ {"hf-inference":{"modelId":"dslim/bert-base-NER","providerModelId":"dslim/bert-base-NER"} } }
+pipeline=token-classification
+providersMapping={ {"hf-inference":{"modelId":"dslim/bert-base-NER","providerModelId":"dslim/bert-base-NER"} } }
 />
 
-
 ### Translation
 
 Find out more about Translation [here](../tasks/translation).
 
 <InferenceSnippet
-    pipeline=translation
-    providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-base","providerModelId":"google-t5/t5-base"} } }
+pipeline=translation
+providersMapping={ {"hf-inference":{"modelId":"google-t5/t5-base","providerModelId":"google-t5/t5-base"} } }
 />
-

docs/inference-providers/providers/nscale.md

@@ -46,7 +46,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"nscale":{"modelId":"Qwen/Qwen3-235B-A22B","providerModelId":"Qwen/Qwen3-235B-A22B"} } }
+    providersMapping={ {"nscale":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Llama-3.1-8B-Instruct"} } }
 conversational />
 
 

docs/inference-providers/providers/replicate.md

@@ -54,6 +54,6 @@ Find out more about Text To Video [here](../tasks/text_to_video).
 
 <InferenceSnippet
     pipeline=text-to-video
-    providersMapping={ {"replicate":{"modelId":"Wan-AI/Wan2.1-T2V-14B","providerModelId":"wavespeedai/wan-2.1-t2v-480p"} } }
+    providersMapping={ {"replicate":{"modelId":"Lightricks/LTX-Video","providerModelId":"lightricks/ltx-video:8c47da666861d081eeb4d1261853087de23923a268a69b63febdf5dc1dee08e4"} } }
 />
 

docs/inference-providers/providers/together.md

@@ -44,7 +44,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
+    providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
 conversational />
 
 
@@ -64,7 +64,7 @@ Find out more about Text Generation [here](../tasks/text_generation).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
+    providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
 />
 
 

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

@@ -25,6 +25,7 @@ This is a subtask of [`text-generation`](https://huggingface.co/docs/inference-p
 - [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B): Smaller variant of one of the most powerful models.
 - [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct): Very powerful text generation model trained to follow instructions.
 - [microsoft/phi-4](https://huggingface.co/microsoft/phi-4): Powerful text generation model by Microsoft.
+- [Qwen/Qwen2.5-7B-Instruct-1M](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M): Strong conversational model that supports very long instructions.
 - [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct): Text generation model used to write code.
 - [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1): Powerful reasoning based open large language model.
 
@@ -60,7 +61,7 @@ The API supports:
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"cerebras":{"modelId":"Qwen/Qwen3-32B","providerModelId":"qwen-3-32b"},"cohere":{"modelId":"CohereLabs/c4ai-command-r-plus","providerModelId":"command-r-plus-04-2024"},"featherless-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"accounts/fireworks/models/deepseek-r1-0528"},"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"},"hyperbolic":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"nebius":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"novita":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek/deepseek-r1-0528"},"nscale":{"modelId":"Qwen/Qwen3-235B-A22B","providerModelId":"Qwen/Qwen3-235B-A22B"},"sambanova":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"DeepSeek-R1-0528"},"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"}} }
+    providersMapping={ {"cerebras":{"modelId":"Qwen/Qwen3-32B","providerModelId":"qwen-3-32b"},"cohere":{"modelId":"CohereLabs/c4ai-command-r-plus","providerModelId":"command-r-plus-04-2024"},"featherless-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"accounts/fireworks/models/deepseek-r1-0528"},"groq":{"modelId":"Qwen/Qwen3-32B","providerModelId":"qwen/qwen3-32b"},"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"},"hyperbolic":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"nebius":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"novita":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek/deepseek-r1-0528"},"nscale":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Llama-3.1-8B-Instruct"},"sambanova":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"DeepSeek-R1-0528"},"together":{"modelId":"deepseek-ai/DeepSeek-R1","providerModelId":"deepseek-ai/DeepSeek-R1"}} }
 conversational />
 
 
@@ -70,7 +71,7 @@ conversational />
 
 <InferenceSnippet
     pipeline=image-text-to-text
-    providersMapping={ {"cerebras":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"llama-4-scout-17b-16e-instruct"},"cohere":{"modelId":"CohereLabs/aya-vision-32b","providerModelId":"c4ai-aya-vision-32b"},"featherless-ai":{"modelId":"allura-org/Gemma-3-Glitter-27B","providerModelId":"allura-org/Gemma-3-Glitter-27B"},"fireworks-ai":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"accounts/fireworks/models/llama4-scout-instruct-basic"},"hf-inference":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"meta-llama/Llama-3.2-11B-Vision-Instruct"},"hyperbolic":{"modelId":"Qwen/Qwen2.5-VL-7B-Instruct","providerModelId":"Qwen/Qwen2.5-VL-7B-Instruct"},"nebius":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it-fast"},"novita":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"},"nscale":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct"},"sambanova":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"Llama-4-Scout-17B-16E-Instruct"},"together":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct"}} }
+    providersMapping={ {"cerebras":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"llama-4-scout-17b-16e-instruct"},"cohere":{"modelId":"CohereLabs/aya-vision-8b","providerModelId":"c4ai-aya-vision-8b"},"featherless-ai":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it"},"fireworks-ai":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"accounts/fireworks/models/llama4-scout-instruct-basic"},"groq":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"},"hf-inference":{"modelId":"meta-llama/Llama-3.2-11B-Vision-Instruct","providerModelId":"meta-llama/Llama-3.2-11B-Vision-Instruct"},"hyperbolic":{"modelId":"Qwen/Qwen2.5-VL-7B-Instruct","providerModelId":"Qwen/Qwen2.5-VL-7B-Instruct"},"nebius":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it-fast"},"novita":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/llama-4-scout-17b-16e-instruct"},"nscale":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct"},"sambanova":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"Llama-4-Scout-17B-16E-Instruct"},"together":{"modelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","providerModelId":"meta-llama/Llama-4-Scout-17B-16E-Instruct"}} }
 conversational />