{"data":{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA Nemotron 3.5 Super VL","created":1755815280,"released":1792022400,"description":"NVIDIA Nemotron 3.5 Super VL is a vision-language model for reasoning, coding, tool use, and document understanding. Its hybrid Mamba-2, attention, and Mixture-of-Experts architecture has 120B total parameters with 12B active per token. Baseten serves text and image inputs with up to one million tokens of context for long conversations and agent workflows.","architecture":{"tokenizer":null,"instruct_type":null,"modality":"text+image→text","input_modalities":["text","image"],"output_modalities":["text"]},"reasoning":{"mandatory":false,"supported_efforts":["none","low","medium","high"]},"endpoints":[{"name":"baseten | nvidia/nemotron-3.5-super-vl","model_name":"NVIDIA Nemotron 3.5 Super VL","context_length":1048576,"pricing":{"prompt":"0.0000002","completion":"0.0000005","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000004","discount":0},"provider_name":"baseten","has_zdr":true,"has_no_training":true,"headquarters_country":"US","tags":["implicit-caching","reasoning","structured-output","tool-use","vision","open-weights"],"inference_regions":[{"scope":"zone","geo_region":"us","pricing":{"prompt":"0.0000002","completion":"0.0000005","input_cache_read":"0.00000004"}}],"quantization":null,"max_completion_tokens":1048576,"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":99.9943,"latency_last_1h":{"p50":613,"p95":2353.9999999999977},"throughput_last_1h":{"p50":689,"p95":763.5},"supports_implicit_caching":true},{"name":"deepinfra | nvidia/nemotron-3.5-super-vl","model_name":"NVIDIA Nemotron 3.5 Super VL","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000005","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000002","discount":0},"provider_name":"deepinfra","has_zdr":false,"has_no_training":true,"headquarters_country":"US","tags":["implicit-caching","reasoning","structured-output","tool-use","video-input","vision","open-weights"],"quantization":null,"max_completion_tokens":262144,"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":100,"latency_last_1h":{"p50":588,"p95":1071.4999999999993},"throughput_last_1h":{"p50":114,"p95":123.8},"supports_implicit_caching":true},{"name":"togetherai | nvidia/nemotron-3.5-super-vl","model_name":"NVIDIA Nemotron 3.5 Super VL","context_length":262144,"pricing":{"prompt":"0.00000015","completion":"0.0000005","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000002","discount":0},"provider_name":"togetherai","has_zdr":true,"has_no_training":true,"headquarters_country":"US","tags":["implicit-caching","reasoning","structured-output","tool-use","video-input","vision","open-weights"],"quantization":null,"max_completion_tokens":262144,"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":99.8839,"latency_last_1h":{"p50":186.5,"p95":279.94999999999993},"throughput_last_1h":{"p50":337,"p95":337},"supports_implicit_caching":true}]}}