huggingface · HuggingFaceInfra · Jun 7, 2026 · Jun 7, 2026
diff --git a/docs/inference-providers/providers/cohere.md b/docs/inference-providers/providers/cohere.md
@@ -49,7 +49,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"cohere":{"modelId":"CohereLabs/tiny-aya-global","providerModelId":"tiny-aya-global"} } }
+    providersMapping={ {"cohere":{"modelId":"CohereLabs/tiny-aya-earth","providerModelId":"tiny-aya-earth"} } }
 conversational />
 
 

diff --git a/docs/inference-providers/providers/hf-inference.md b/docs/inference-providers/providers/hf-inference.md
@@ -70,7 +70,7 @@ Find out more about Feature Extraction [here](../tasks/feature-extraction).
 
 <InferenceSnippet
     pipeline=feature-extraction
-    providersMapping={ {"hf-inference":{"modelId":"ibm-granite/granite-embedding-97m-multilingual-r2","providerModelId":"ibm-granite/granite-embedding-97m-multilingual-r2"} } }
+    providersMapping={ {"hf-inference":{"modelId":"microsoft/harrier-oss-v1-0.6b","providerModelId":"microsoft/harrier-oss-v1-0.6b"} } }
 />
 
 

diff --git a/docs/inference-providers/providers/publicai.md b/docs/inference-providers/providers/publicai.md
@@ -49,6 +49,6 @@ 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"} } }
+    providersMapping={ {"publicai":{"modelId":"utter-project/EuroLLM-22B-Instruct-2512","providerModelId":"utter-project/EuroLLM-22B-Instruct-2512"} } }
 conversational />
 
diff --git a/docs/inference-providers/providers/sambanova.md b/docs/inference-providers/providers/sambanova.md
@@ -41,3 +41,13 @@ Customers are turning to SambaNova to quickly deploy state-of-the-art AI and dee
 
 ## Supported tasks
 
+
+### Chat Completion (LLM)
+
+Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
+
+<InferenceSnippet
+    pipeline=text-generation
+    providersMapping={ {"sambanova":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"} } }
+conversational />
+
diff --git a/docs/inference-providers/tasks/chat-completion.md b/docs/inference-providers/tasks/chat-completion.md
@@ -33,7 +33,6 @@ This is a subtask of [`text-generation`](https://huggingface.co/docs/inference-p
 #### Conversational Vision-Language Models (VLMs)
 
 - [zai-org/GLM-4.5V](https://huggingface.co/zai-org/GLM-4.5V): Cutting-edge reasoning vision language model.
-- [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct): Small yet powerful model.
 
 Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=image-text-to-text&sort=trending).
 
@@ -65,7 +64,7 @@ The API supports:
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"cerebras":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"cohere":{"modelId":"CohereLabs/tiny-aya-global","providerModelId":"tiny-aya-global"},"deepinfra":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek-ai/DeepSeek-V4-Pro"},"featherless-ai":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek-ai/DeepSeek-V4-Pro"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"accounts/fireworks/models/deepseek-v4-pro"},"groq":{"modelId":"openai/gpt-oss-120b","providerModelId":"openai/gpt-oss-120b"},"hf-inference":{"modelId":"katanemo/Arch-Router-1.5B","providerModelId":"katanemo/Arch-Router-1.5B"},"hyperbolic":{"modelId":"meta-llama/Llama-3.3-70B-Instruct","providerModelId":"meta-llama/Llama-3.3-70B-Instruct"},"novita":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek/deepseek-v4-pro"},"nscale":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Llama-3.1-8B-Instruct"},"ovhcloud":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"publicai":{"modelId":"swiss-ai/Apertus-8B-Instruct-2509","providerModelId":"swiss-ai/apertus-8b-instruct"},"scaleway":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"llama-3.1-8b-instruct"},"together":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek-ai/DeepSeek-V4-Pro"},"zai-org":{"modelId":"zai-org/GLM-5.1","providerModelId":"glm-5.1"}} }
+    providersMapping={ {"cerebras":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"cohere":{"modelId":"CohereLabs/tiny-aya-earth","providerModelId":"tiny-aya-earth"},"deepinfra":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek-ai/DeepSeek-V4-Pro"},"featherless-ai":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek-ai/DeepSeek-V4-Pro"},"fireworks-ai":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"accounts/fireworks/models/deepseek-v4-pro"},"groq":{"modelId":"openai/gpt-oss-120b","providerModelId":"openai/gpt-oss-120b"},"hf-inference":{"modelId":"katanemo/Arch-Router-1.5B","providerModelId":"katanemo/Arch-Router-1.5B"},"hyperbolic":{"modelId":"meta-llama/Llama-3.3-70B-Instruct","providerModelId":"meta-llama/Llama-3.3-70B-Instruct"},"novita":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek/deepseek-v4-pro"},"nscale":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Llama-3.1-8B-Instruct"},"ovhcloud":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"publicai":{"modelId":"utter-project/EuroLLM-22B-Instruct-2512","providerModelId":"utter-project/EuroLLM-22B-Instruct-2512"},"sambanova":{"modelId":"openai/gpt-oss-120b","providerModelId":"gpt-oss-120b"},"scaleway":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"llama-3.1-8b-instruct"},"together":{"modelId":"deepseek-ai/DeepSeek-V4-Pro","providerModelId":"deepseek-ai/DeepSeek-V4-Pro"},"zai-org":{"modelId":"zai-org/GLM-5.1","providerModelId":"glm-5.1"}} }
 conversational />
 
 

diff --git a/docs/inference-providers/tasks/feature-extraction.md b/docs/inference-providers/tasks/feature-extraction.md
@@ -36,7 +36,7 @@ Explore all available models and find the one that suits you best [here](https:/
 
 <InferenceSnippet
     pipeline=feature-extraction
-    providersMapping={ {"hf-inference":{"modelId":"ibm-granite/granite-embedding-97m-multilingual-r2","providerModelId":"ibm-granite/granite-embedding-97m-multilingual-r2"},"scaleway":{"modelId":"Qwen/Qwen3-Embedding-8B","providerModelId":"qwen3-embedding-8b"},"together":{"modelId":"intfloat/multilingual-e5-large-instruct","providerModelId":"intfloat/multilingual-e5-large-instruct"}} }
+    providersMapping={ {"hf-inference":{"modelId":"microsoft/harrier-oss-v1-0.6b","providerModelId":"microsoft/harrier-oss-v1-0.6b"},"scaleway":{"modelId":"Qwen/Qwen3-Embedding-8B","providerModelId":"qwen3-embedding-8b"},"together":{"modelId":"intfloat/multilingual-e5-large-instruct","providerModelId":"intfloat/multilingual-e5-large-instruct"}} }
 />
 
 

diff --git a/docs/inference-providers/tasks/image-text-to-text.md b/docs/inference-providers/tasks/image-text-to-text.md
@@ -23,7 +23,6 @@ Image-text-to-text models take in an image and text prompt and output text. Thes
 ### Recommended models
 
 - [zai-org/GLM-4.5V](https://huggingface.co/zai-org/GLM-4.5V): Cutting-edge reasoning vision language model.
-- [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct): Small yet powerful model.
 
 Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=image-text-to-text&sort=trending).