{"data":{"id":"tencent/hy4-flash","name":"Tencent Hy4 Flash","created":1755815280,"released":1794787200,"description":"Tencent Hy4 Flash is a lower-cost model in the Hy4 family for coding, reasoning, and agentic workflows. It supports deep reasoning with preserved thinking, tool calling, structured outputs, prompt caching, and image understanding, with a 1M-token context window.","architecture":{"tokenizer":null,"instruct_type":null,"modality":"text+image→text","input_modalities":["text","image"],"output_modalities":["text"]},"reasoning":{"mandatory":false,"supported_efforts":["none","high"]},"endpoints":[{"name":"tencent | tencent/hy4-flash","model_name":"Tencent Hy4 Flash","context_length":1024000,"pricing":{"prompt":"0.000000035","completion":"0.0000001405","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000000015","discount":0},"provider_name":"tencent","has_zdr":false,"has_no_training":false,"headquarters_country":"CN","tags":["implicit-caching","reasoning","structured-output","tool-use","vision","open-weights"],"quantization":null,"max_completion_tokens":64000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"status":0,"uptime_last_15m":100,"uptime_last_1h":100,"uptime_last_1d":99.9734,"latency_last_1h":{"p50":4381,"p95":9083},"throughput_last_1h":{"p50":148,"p95":160.75},"supports_implicit_caching":true}]}}