{"data":{"id":"heygen/avatar-iv","name":"HeyGen: Avatar IV","created":1787595728,"description":"HeyGen: Avatar IV is an image-to-video model that animates a single photo into an expressive, lip-synced talking-head video. Rather than only matching mouth shapes to words, it interprets the vocal...","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"text+image+audio->video","input_modalities":["text","image","audio"],"output_modalities":["video"]},"endpoints":[{"name":"HeyGen | heygen/avatar-iv-20260625","model_id":"heygen/avatar-iv","model_name":"HeyGen: Avatar IV","context_length":0,"pricing":{"prompt":"0","completion":"0","discount":0},"provider_name":"HeyGen","tag":"heygen","service_tier":null,"quantization":"unknown","max_completion_tokens":0,"max_prompt_tokens":null,"supported_parameters":[],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"native_tools":{},"supports_voice_cloning":false,"supports_multiple_audio_references":false,"supports_image_reference":false,"supports_diarization":false,"latency_last_30m":null,"throughput_last_30m":null}]}}