{"data":{"id":"inception/mercury-2.5","name":"Inception: Mercury 2.5","created":1788892137,"description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"endpoints":[{"name":"Inception | inception/mercury-2.5-20260908","model_id":"inception/mercury-2.5","model_name":"Inception: Mercury 2.5","context_length":260000,"pricing":{"prompt":"0.00000004","completion":"0.00000015","input_cache_read":"0.000000004","discount":0.8},"provider_name":"Inception","tag":"inception","quantization":"unknown","max_completion_tokens":65536,"max_prompt_tokens":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","temperature","tools","tool_choice","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":99.88897935015913,"uptime_last_5m":99.85528219971056,"uptime_last_1d":99.90766508072893,"supports_implicit_caching":false,"supports_voice_cloning":false,"latency_last_30m":null,"throughput_last_30m":null}]}}