Operations quick access
POST /_inference/chat_completion/{inference_id}/_stream POST /_inference/completion/{inference_id} GET /_inference/{inference_id} PUT /_inference/{inference_id} POST /_inference/{inference_id} DELETE /_inference/{inference_id} GET /_inference/{task_type}/{inference_id} PUT /_inference/{task_type}/{inference_id} POST /_inference/{task_type}/{inference_id} DELETE /_inference/{task_type}/{inference_id} POST /_inference/embedding/{inference_id} GET /_inference GET /_inference/{task_type}/_all PUT /_inference/{task_type}/{ai21_inference_id} PUT /_inference/{task_type}/{alibabacloud_inference_id} PUT /_inference/{task_type}/{amazonbedrock_inference_id} PUT /_inference/{task_type}/{amazonsagemaker_inference_id} PUT /_inference/{task_type}/{anthropic_inference_id} PUT /_inference/{task_type}/{azureaistudio_inference_id} PUT /_inference/{task_type}/{azureopenai_inference_id} PUT /_inference/{task_type}/{cohere_inference_id} PUT /_inference/{task_type}/{contextualai_inference_id} PUT /_inference/{task_type}/{custom_inference_id} PUT /_inference/{task_type}/{deepseek_inference_id} PUT /_inference/{task_type}/{elasticsearch_inference_id} PUT /_inference/{task_type}/{elser_inference_id} PUT /_inference/{task_type}/{fireworksai_inference_id} PUT /_inference/{task_type}/{googleaistudio_inference_id} PUT /_inference/{task_type}/{googlevertexai_inference_id} PUT /_inference/{task_type}/{groq_inference_id} PUT /_inference/{task_type}/{huggingface_inference_id} PUT /_inference/{task_type}/{jinaai_inference_id} PUT /_inference/{task_type}/{llama_inference_id} PUT /_inference/{task_type}/{mistral_inference_id} PUT /_inference/{task_type}/{nvidia_inference_id} PUT /_inference/{task_type}/{openai_inference_id} PUT /_inference/{task_type}/{openshiftai_inference_id} PUT /_inference/{task_type}/{voyageai_inference_id} PUT /_inference/{task_type}/{watsonx_inference_id} POST /_inference/rerank/{inference_id} POST /_inference/sparse_embedding/{inference_id} POST /_inference/completion/{inference_id}/_stream POST /_inference/text_embedding/{inference_id} PUT /_inference/{inference_id}/_update PUT /_inference/{task_type}/{inference_id}/_update