{"data":{"id":"microsoft-phi-4-multimodal-instruct","name":"phi-4-multimodal-instruct","display_name":"Phi-4 Multimodal Instruct","description":"A multimodal instruction-tuned variant of Phi-4 capable of processing both text and visual inputs for a compact yet capable small language model.","creator":"microsoft","family":"phi","tier":"","version":"4","type":"language","size_in_bn":null,"modalities":{"input":["audio","image"],"output":["text"]},"context_window":131072,"max_output_tokens":4096,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["azure_ai/Phi-4-multimodal-instruct","microsoft-phi-4-multimodal-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-21 08:03:17"},"meta":{"updated_at":"2026-06-21","request_id":"6f7d5b93-0ce0-4299-a62b-99922028ccc8","execution_ms":8}}