{"models":[{"endpoint_id":"nvidia/nemotron-3-5-super/text","metadata":{"display_name":"NVIDIA Nemotron 3.5 Super Text","category":"llm","description":"Chat and reason with NVIDIA Nemotron 3.5 Super, a hybrid Mamba-Transformer mixture-of-experts model with optional step-by-step thinking.","status":"active","tags":["llm","reasoning","chat"],"updated_at":"2026-10-18T16:14:59.295Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aae6a5d/IbP1tgqhRJ9m2mqCmNJIS.jpg","model_url":"https://fal.run/nvidia/nemotron-3-5-super/text","license_type":"commercial","date":"2026-10-15T01:09:00.655Z","group":{"key":"nvidia/nemotron-3-5-super","label":"Text"},"highlighted":false,"kind":"inference","pinned":false},"retires_at":null,"replacement":null,"openapi":{"openapi":"3.1.0","info":{"title":"Queue OpenAPI for fal-ai/nemotron-3-5-super/text","version":"1.0.0","description":"NVIDIA Nemotron 3.5 Super served by fal on Blackwell GPUs (NVFP4, multi-token prediction for fast decoding). Text in, text out: send a prompt and get an answer, with an optional system prompt. Shared options: system_prompt (optional), reasoning_mode no_think (default, direct answer) or think (returns a separate reasoning trace), max_tokens (default 1024), temperature (default 1.0, NVIDIA's recommended value), top_p (default 0.95), safety checker on by default. Returns output text, finish_reason, token usage and, in think mode, the reasoning trace. Billed per 1,000 tokens (input plus output), minimum one unit per request.","x-fal-metadata":{"endpointId":"fal-ai/nemotron-3-5-super/text","category":"llm","thumbnailUrl":"https://v3b.fal.media/files/b/0aae6a22/0RNUP5UNgxOGlWJrWVTmq.jpg","playgroundUrl":"https://fal.ai/models/fal-ai/nemotron-3-5-super/text","documentationUrl":"https://fal.ai/models/fal-ai/nemotron-3-5-super/text/api","about":"Run Text"}},"components":{"securitySchemes":{"apiKeyAuth":{"type":"apiKey","in":"header","name":"Authorization","description":"Fal Key"}},"schemas":{"QueueStatus":{"type":"object","properties":{"status":{"type":"string","enum":["IN_QUEUE","IN_PROGRESS","COMPLETED"]},"request_id":{"type":"string","description":"The request id."},"response_url":{"type":"string","description":"The response url."},"status_url":{"type":"string","description":"The status url."},"cancel_url":{"type":"string","description":"The cancel url."},"logs":{"type":"object","description":"The logs.","additionalProperties":true},"metrics":{"type":"object","description":"The metrics.","additionalProperties":true},"queue_position":{"type":"integer","description":"The queue position."}},"required":["status","request_id"]},"Nemotron35SuperTextInput":{"properties":{"prompt":{"type":"string","title":"Prompt","minLength":1,"examples":["Summarize the key ideas of hybrid Mamba-Transformer models."],"description":"Text prompt to send to the model."},"system_prompt":{"description":"Optional system prompt to steer the model.","title":"System Prompt","examples":["You are a concise assistant."],"anyOf":[{"type":"string"},{"type":"null"}]},"max_tokens":{"default":1024,"description":"Maximum number of tokens to generate.","title":"Max Tokens","minimum":1,"type":"integer","maximum":32000},"temperature":{"default":1,"description":"Sampling temperature. NVIDIA recommends 1.0 for all tasks.","title":"Temperature","minimum":0,"type":"number","maximum":2},"enable_safety_checker":{"description":"Whether to enable the safety checker.","title":"Enable Safety Checker","type":"boolean","default":true},"top_p":{"default":0.95,"description":"Nucleus sampling probability mass.","title":"Top P","exclusiveMinimum":0,"type":"number","maximum":1},"reasoning_mode":{"enum":["think","no_think"],"description":"`think` emits an explicit reasoning trace before the final answer; `no_think` returns a direct answer.","title":"Reasoning Mode","type":"string","default":"no_think"}},"x-fal-order-properties":["prompt","system_prompt","reasoning_mode","max_tokens","temperature","top_p","enable_safety_checker"],"title":"ChatInput","type":"object","required":["prompt"]},"Nemotron35SuperTextOutput":{"properties":{"output":{"title":"Output","type":"string","examples":["Hello! How can I help?"],"description":"Generated text response."},"usage":{"$ref":"#/components/schemas/UsageInfo","examples":[{"input_tokens":24,"output_tokens":87}],"description":"Token usage for the request."},"finish_reason":{"default":"stop","title":"Finish Reason","type":"string","examples":["stop","length"],"description":"Reason generation stopped."},"reasoning":{"description":"Reasoning trace, returned only in `think` mode.","title":"Reasoning","anyOf":[{"type":"string"},{"type":"null"}]}},"x-fal-order-properties":["output","reasoning","finish_reason","usage"],"title":"ChatOutput","type":"object","required":["output","usage"]},"UsageInfo":{"properties":{"input_tokens":{"title":"Input Tokens","type":"integer","description":"Number of input tokens processed."},"output_tokens":{"title":"Output Tokens","type":"integer","description":"Number of output tokens generated."}},"x-fal-order-properties":["input_tokens","output_tokens"],"title":"UsageInfo","type":"object","required":["input_tokens","output_tokens"]}}},"paths":{"/fal-ai/nemotron-3-5-super/text/requests/{request_id}/status":{"get":{"parameters":[{"name":"request_id","in":"path","required":true,"schema":{"type":"string","description":"Request ID"}},{"name":"logs","in":"query","required":false,"schema":{"type":"number","description":"Whether to include logs (`1`) in the response or not (`0`)."}}],"responses":{"200":{"description":"The request status.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/QueueStatus"}}}}}}},"/fal-ai/nemotron-3-5-super/text/requests/{request_id}/cancel":{"put":{"parameters":[{"name":"request_id","in":"path","required":true,"schema":{"type":"string","description":"Request ID"}}],"responses":{"200":{"description":"The request was cancelled.","content":{"application/json":{"schema":{"type":"object","properties":{"success":{"type":"boolean","description":"Whether the request was cancelled successfully."}}}}}}}}},"/fal-ai/nemotron-3-5-super/text":{"post":{"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/Nemotron35SuperTextInput"}}}},"responses":{"200":{"description":"The request status.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/QueueStatus"}}}}}}},"/fal-ai/nemotron-3-5-super/text/requests/{request_id}":{"get":{"parameters":[{"name":"request_id","in":"path","required":true,"schema":{"type":"string","description":"Request ID"}}],"responses":{"200":{"description":"Result of the request.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Nemotron35SuperTextOutput"}}}}}}}},"servers":[{"url":"https://queue.fal.run"}],"security":[{"apiKeyAuth":[]}]}}],"next_cursor":null,"has_more":false}