From 192799915b53197983ef0e8d06d2b6bcb9d4025c Mon Sep 17 00:00:00 2001
From: SBrandeis <simon@huggingface.co>
Date: Mon, 16 Jun 2025 21:41:26 +0200
Subject: [PATCH] update docs

---
 .../providers/featherless-ai.md               |   2 +-
 .../providers/hf-inference.md                 |  81 ++++---
 .../inference-providers/providers/together.md |   4 +-
 .../tasks/chat-completion.md                  |   2 +-
 .../tasks/text-classification.md              |  36 ++--
 .../tasks/text-generation.md                  | 204 +++++++++---------
 6 files changed, 180 insertions(+), 149 deletions(-)

diff --git a/docs/inference-providers/providers/featherless-ai.md b/docs/inference-providers/providers/featherless-ai.md
index 7deb14344..18d1f377e 100644
--- a/docs/inference-providers/providers/featherless-ai.md
+++ b/docs/inference-providers/providers/featherless-ai.md
@@ -56,7 +56,7 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
     pipeline=image-text-to-text
-    providersMapping={ {"featherless-ai":{"modelId":"allura-org/Gemma-3-Glitter-27B","providerModelId":"allura-org/Gemma-3-Glitter-27B"} } }
+    providersMapping={ {"featherless-ai":{"modelId":"google/gemma-3-27b-it","providerModelId":"google/gemma-3-27b-it"} } }
 conversational />
 
 
diff --git a/docs/inference-providers/providers/hf-inference.md b/docs/inference-providers/providers/hf-inference.md
index ee240d0b6..4ec33aae0 100644
--- a/docs/inference-providers/providers/hf-inference.md
+++ b/docs/inference-providers/providers/hf-inference.md
@@ -38,146 +38,163 @@ 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":"distilbert/distilbert-base-uncased-finetuned-sst-2-english","providerModelId":"distilbert/distilbert-base-uncased-finetuned-sst-2-english"} } }
 />
 
+
 ### 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"} } }
 />
+
diff --git a/docs/inference-providers/providers/together.md b/docs/inference-providers/providers/together.md
index 426de4744..8ccce4cfa 100644
--- a/docs/inference-providers/providers/together.md
+++ b/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","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
+    providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","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","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
+    providersMapping={ {"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"} } }
 />
 
 
diff --git a/docs/inference-providers/tasks/chat-completion.md b/docs/inference-providers/tasks/chat-completion.md
index 4f20bfefc..bc4ed7f70 100644
--- a/docs/inference-providers/tasks/chat-completion.md
+++ b/docs/inference-providers/tasks/chat-completion.md
@@ -61,7 +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"},"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"}} }
+    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-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"}} }
 conversational />
 
 
diff --git a/docs/inference-providers/tasks/text-classification.md b/docs/inference-providers/tasks/text-classification.md
index 63f6551d7..fd2827abb 100644
--- a/docs/inference-providers/tasks/text-classification.md
+++ b/docs/inference-providers/tasks/text-classification.md
@@ -31,30 +31,36 @@ Explore all available models and find the one that suits you best [here](https:/
 
 ### Using the API
 
+
 <InferenceSnippet
-pipeline=text-classification
-providersMapping={ {"hf-inference":{"modelId":"tabularisai/multilingual-sentiment-analysis","providerModelId":"tabularisai/multilingual-sentiment-analysis"}} }
+    pipeline=text-classification
+    providersMapping={ {"hf-inference":{"modelId":"distilbert/distilbert-base-uncased-finetuned-sst-2-english","providerModelId":"distilbert/distilbert-base-uncased-finetuned-sst-2-english"}} }
 />
 
+
+
 ### API specification
 
 #### Request
 
-| Headers           |          |                                                                                                                                                                                                                                                                                                             |
-| :---------------- | :------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Headers |   |    |
+| :--- | :--- | :--- |
 | **authorization** | _string_ | Authentication header in the form `'Bearer: hf_****'` when `hf_****` is a personal user access token with "Inference Providers" permission. You can generate one from [your settings page](https://huggingface.co/settings/tokens/new?ownUserPermissions=inference.serverless.write&tokenType=fineGrained). |
 
-| Payload                                                               |           |                                                                       |
-| :-------------------------------------------------------------------- | :-------- | :-------------------------------------------------------------------- |
-| **inputs\***                                                          | _string_  | The text to classify                                                  |
-| **parameters**                                                        | _object_  |                                                                       |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;function_to_apply** | _enum_    | Possible values: sigmoid, softmax, none.                              |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_k**             | _integer_ | When specified, limits the output to the top K most probable classes. |
+
+| Payload |  |  |
+| :--- | :--- | :--- |
+| **inputs*** | _string_ | The text to classify |
+| **parameters** | _object_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;function_to_apply** | _enum_ | Possible values: sigmoid, softmax, none. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_k** | _integer_ | When specified, limits the output to the top K most probable classes. |
+
 
 #### Response
 
-| Body                                                      |            |
-| :-------------------------------------------------------- | :--------- | :----------------------------- |
-| **(array)**                                               | _object[]_ | Output is an array of objects. |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;label** | _string_   | The predicted class label.     |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;score** | _number_   | The corresponding probability. |
+| Body |  |
+| :--- | :--- | :--- |
+| **(array)** | _object[]_ | Output is an array of objects. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;label** | _string_ | The predicted class label. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;score** | _number_ | The corresponding probability. |
+
diff --git a/docs/inference-providers/tasks/text-generation.md b/docs/inference-providers/tasks/text-generation.md
index 224f27bb9..145eb357d 100644
--- a/docs/inference-providers/tasks/text-generation.md
+++ b/docs/inference-providers/tasks/text-generation.md
@@ -30,6 +30,7 @@ For more details about the `text-generation` task, check out its [dedicated page
 - [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.
 
@@ -37,120 +38,127 @@ Explore all available models and find the one that suits you best [here](https:/
 
 ### Using the API
 
+
 <InferenceSnippet
-pipeline=text-generation
-providersMapping={ {"featherless-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"},"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"}} }
+    pipeline=text-generation
+    providersMapping={ {"featherless-ai":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1-0528"},"hf-inference":{"modelId":"sarvamai/sarvam-m","providerModelId":"sarvamai/sarvam-m"},"together":{"modelId":"deepseek-ai/DeepSeek-R1-0528","providerModelId":"deepseek-ai/DeepSeek-R1"}} }
 />
 
+
+
 ### API specification
 
 #### Request
 
-| Headers           |          |                                                                                                                                                                                                                                                                                                             |
-| :---------------- | :------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Headers |   |    |
+| :--- | :--- | :--- |
 | **authorization** | _string_ | Authentication header in the form `'Bearer: hf_****'` when `hf_****` is a personal user access token with "Inference Providers" permission. You can generate one from [your settings page](https://huggingface.co/settings/tokens/new?ownUserPermissions=inference.serverless.write&tokenType=fineGrained). |
 
-| Payload                                                                                                                                                                                                      |            |                                                                                                                                                                                                         |
-| :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :--------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **inputs\***                                                                                                                                                                                                 | _string_   |                                                                                                                                                                                                         |
-| **parameters**                                                                                                                                                                                               | _object_   |                                                                                                                                                                                                         |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;adapter_id**                                                                                                                                               | _string_   | Lora adapter id                                                                                                                                                                                         |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;best_of**                                                                                                                                                  | _integer_  | Generate best_of sequences and return the one if the highest token logprobs.                                                                                                                            |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;decoder_input_details**                                                                                                                                    | _boolean_  | Whether to return decoder input token logprobs and ids.                                                                                                                                                 |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;details**                                                                                                                                                  | _boolean_  | Whether to return generation details.                                                                                                                                                                   |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;do_sample**                                                                                                                                                | _boolean_  | Activate logits sampling.                                                                                                                                                                               |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;frequency_penalty**                                                                                                                                        | _number_   | The parameter for frequency penalty. 1.0 means no penalty Penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;grammar**                                                                                                                                                  | _unknown_  | One of the following:                                                                                                                                                                                   |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;(#1)**                                                                                               | _object_   |                                                                                                                                                                                                         |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;type\***                                                   | _enum_     | Possible values: json.                                                                                                                                                                                  |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;value\***                                                  | _unknown_  | A string that represents a [JSON Schema](https://json-schema.org/). JSON Schema is a declarative language that allows to annotate JSON documents with types and descriptions.                           |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;(#2)**                                                                                               | _object_   |                                                                                                                                                                                                         |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;type\***                                                   | _enum_     | Possible values: regex.                                                                                                                                                                                 |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;value\***                                                  | _string_   |                                                                                                                                                                                                         |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;(#3)**                                                                                               | _object_   |                                                                                                                                                                                                         |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;type\***                                                   | _enum_     | Possible values: json_schema.                                                                                                                                                                           |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;value\***                                                  | _object_   |                                                                                                                                                                                                         |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;name**     | _string_   | Optional name identifier for the schema                                                                                                                                                                 |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;schema\*** | _unknown_  | The actual JSON schema definition                                                                                                                                                                       |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;max_new_tokens**                                                                                                                                           | _integer_  | Maximum number of tokens to generate.                                                                                                                                                                   |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;repetition_penalty**                                                                                                                                       | _number_   | The parameter for repetition penalty. 1.0 means no penalty. See [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details.                                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;return_full_text**                                                                                                                                         | _boolean_  | Whether to prepend the prompt to the generated text                                                                                                                                                     |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;seed**                                                                                                                                                     | _integer_  | Random sampling seed.                                                                                                                                                                                   |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;stop**                                                                                                                                                     | _string[]_ | Stop generating tokens if a member of `stop` is generated.                                                                                                                                              |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;temperature**                                                                                                                                              | _number_   | The value used to module the logits distribution.                                                                                                                                                       |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_k**                                                                                                                                                    | _integer_  | The number of highest probability vocabulary tokens to keep for top-k-filtering.                                                                                                                        |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_n_tokens**                                                                                                                                             | _integer_  | The number of highest probability vocabulary tokens to keep for top-n-filtering.                                                                                                                        |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_p**                                                                                                                                                    | _number_   | Top-p value for nucleus sampling.                                                                                                                                                                       |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;truncate**                                                                                                                                                 | _integer_  | Truncate inputs tokens to the given size.                                                                                                                                                               |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;typical_p**                                                                                                                                                | _number_   | Typical Decoding mass See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information.                                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;watermark**                                                                                                                                                | _boolean_  | Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226).                                                                                                            |
-| **stream**                                                                                                                                                                                                   | _boolean_  |                                                                                                                                                                                                         |
+
+| Payload |  |  |
+| :--- | :--- | :--- |
+| **inputs*** | _string_ |  |
+| **parameters** | _object_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;adapter_id** | _string_ | Lora adapter id |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;best_of** | _integer_ | Generate best_of sequences and return the one if the highest token logprobs. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;decoder_input_details** | _boolean_ | Whether to return decoder input token logprobs and ids. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;details** | _boolean_ | Whether to return generation details. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;do_sample** | _boolean_ | Activate logits sampling. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;frequency_penalty** | _number_ | The parameter for frequency penalty. 1.0 means no penalty Penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;grammar** | _unknown_ | One of the following: |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;(#1)** | _object_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;type*** | _enum_ | Possible values: json. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;value*** | _unknown_ | A string that represents a [JSON Schema](https://json-schema.org/).  JSON Schema is a declarative language that allows to annotate JSON documents with types and descriptions. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;(#2)** | _object_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;type*** | _enum_ | Possible values: regex. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;value*** | _string_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;(#3)** | _object_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;type*** | _enum_ | Possible values: json_schema. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;value*** | _object_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;name** | _string_ | Optional name identifier for the schema |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;schema*** | _unknown_ | The actual JSON schema definition |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;max_new_tokens** | _integer_ | Maximum number of tokens to generate. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;repetition_penalty** | _number_ | The parameter for repetition penalty. 1.0 means no penalty. See [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;return_full_text** | _boolean_ | Whether to prepend the prompt to the generated text |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;seed** | _integer_ | Random sampling seed. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;stop** | _string[]_ | Stop generating tokens if a member of `stop` is generated. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;temperature** | _number_ | The value used to module the logits distribution. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_k** | _integer_ | The number of highest probability vocabulary tokens to keep for top-k-filtering. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_n_tokens** | _integer_ | The number of highest probability vocabulary tokens to keep for top-n-filtering. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_p** | _number_ | Top-p value for nucleus sampling. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;truncate** | _integer_ | Truncate inputs tokens to the given size. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;typical_p** | _number_ | Typical Decoding mass See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;watermark** | _boolean_ | Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226). |
+| **stream** | _boolean_ |  |
+
 
 #### Response
 
 Output type depends on the `stream` input parameter.
 If `stream` is `false` (default), the response will be a JSON object with the following fields:
 
-| Body                                                                                                                                                        |            |
-| :---------------------------------------------------------------------------------------------------------------------------------------------------------- | :--------- | :------------------------------------------------- |
-| **details**                                                                                                                                                 | _object_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;best_of_sequences**                                                                                       | _object[]_ |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;finish_reason**                                           | _enum_     | Possible values: length, eos_token, stop_sequence. |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generated_text**                                          | _string_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generated_tokens**                                        | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;prefill**                                                 | _object[]_ |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id**      | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text**    | _string_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;seed**                                                    | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;tokens**                                                  | _object[]_ |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id**      | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special** | _boolean_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text**    | _string_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_tokens**                                              | _array[]_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id**      | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special** | _boolean_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text**    | _string_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;finish_reason**                                                                                           | _enum_     | Possible values: length, eos_token, stop_sequence. |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generated_tokens**                                                                                        | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;prefill**                                                                                                 | _object[]_ |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id**                                                      | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob**                                                 | _number_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text**                                                    | _string_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;seed**                                                                                                    | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;tokens**                                                                                                  | _object[]_ |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id**                                                      | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob**                                                 | _number_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special**                                                 | _boolean_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text**                                                    | _string_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_tokens**                                                                                              | _array[]_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id**                                                      | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob**                                                 | _number_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special**                                                 | _boolean_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text**                                                    | _string_   |                                                    |
-| **generated_text**                                                                                                                                          | _string_   |                                                    |
+| Body |  |
+| :--- | :--- | :--- |
+| **details** | _object_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;best_of_sequences** | _object[]_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;finish_reason** | _enum_ | Possible values: length, eos_token, stop_sequence. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generated_text** | _string_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generated_tokens** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;prefill** | _object[]_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text** | _string_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;seed** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;tokens** | _object[]_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special** | _boolean_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text** | _string_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_tokens** | _array[]_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special** | _boolean_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text** | _string_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;finish_reason** | _enum_ | Possible values: length, eos_token, stop_sequence. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generated_tokens** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;prefill** | _object[]_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text** | _string_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;seed** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;tokens** | _object[]_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special** | _boolean_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text** | _string_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_tokens** | _array[]_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special** | _boolean_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text** | _string_ |  |
+| **generated_text** | _string_ |  |
+
 
 If `stream` is `true`, generated tokens are returned as a stream, using Server-Sent Events (SSE).
 For more information about streaming, check out [this guide](https://huggingface.co/docs/text-generation-inference/conceptual/streaming).
 
-| Body                                                                 |            |
-| :------------------------------------------------------------------- | :--------- | :------------------------------------------------- |
-| **details**                                                          | _object_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;finish_reason**    | _enum_     | Possible values: length, eos_token, stop_sequence. |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generated_tokens** | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;input_length**     | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;seed**             | _integer_  |                                                    |
-| **generated_text**                                                   | _string_   |                                                    |
-| **index**                                                            | _integer_  |                                                    |
-| **token**                                                            | _object_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id**               | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob**          | _number_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special**          | _boolean_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text**             | _string_   |                                                    |
-| **top_tokens**                                                       | _object[]_ |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id**               | _integer_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob**          | _number_   |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special**          | _boolean_  |                                                    |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text**             | _string_   |                                                    |
+| Body |  |
+| :--- | :--- | :--- |
+| **details** | _object_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;finish_reason** | _enum_ | Possible values: length, eos_token, stop_sequence. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generated_tokens** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;input_length** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;seed** | _integer_ |  |
+| **generated_text** | _string_ |  |
+| **index** | _integer_ |  |
+| **token** | _object_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special** | _boolean_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text** | _string_ |  |
+| **top_tokens** | _object[]_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;id** | _integer_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;logprob** | _number_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;special** | _boolean_ |  |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;text** | _string_ |  |
+