{"models":[{"endpoint_id":"nvidia/nemotron-3-nano-omni","metadata":{"display_name":"Nemotron 3 Nano Omni","category":"llm","description":"Open, efficient reasoning model from NVIDIA. 30B A3B hybrid Transformer-Mamba MoE, built for enterprise agentic workflows.","status":"active","tags":["nemotron","nvidia","reasoning","llm","agentic","agents","instruct","open-weights","hybrid-moe","mamba","30b-a3b","long-context"],"updated_at":"2026-04-30T23:00:40.088Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a97fbd9/If5ov--ixg3WLwZO41VX7_adc5fcfe153c4ff5b57fd501934b4a99.jpg","model_url":"https://fal.run/nvidia/nemotron-3-nano-omni","license_type":"commercial","date":"2026-04-27T21:36:29.130Z","group":{"key":"nemotron-3","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-nano-omni","version":"1.0.0","description":"The OpenAPI schema for the fal-ai/nemotron-3-nano-omni queue.","x-fal-metadata":{"endpointId":"fal-ai/nemotron-3-nano-omni","playgroundUrl":"https://fal.ai/models/fal-ai/nemotron-3-nano-omni","documentationUrl":"https://fal.ai/models/fal-ai/nemotron-3-nano-omni/api","about":"Run Chat"}},"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"]},"Nemotron3NanoOmniInput":{"title":"ChatInput","properties":{"prompt":{"title":"Prompt","minLength":1,"examples":["Summarize the key capabilities of a multimodal agent."],"description":"Text prompt to send to the model. English only.","type":"string"},"max_tokens":{"title":"Max Tokens","description":"Maximum number of tokens to generate.","minimum":1,"maximum":20000,"default":1024,"type":"integer"},"enable_safety_checker":{"title":"Enable Safety Checker","description":"Whether to enable the safety checker.","default":true,"type":"boolean"},"system_prompt":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field.","examples":["You are a concise enterprise assistant."],"title":"System Prompt"},"temperature":{"title":"Temperature","description":"Sampling temperature. Lower is more deterministic.","minimum":0,"maximum":2,"default":0.7,"type":"number"},"reasoning_mode":{"title":"Reasoning Mode","description":"Whether the model should emit an explicit reasoning trace. `no_think` returns a direct answer; `think` returns chain-of-thought followed by the final answer.","enum":["think","no_think"],"default":"no_think","type":"string"},"top_p":{"title":"Top P","description":"Nucleus sampling probability mass.","minimum":0,"maximum":1,"default":0.95,"type":"number"}},"required":["prompt"],"x-fal-order-properties":["prompt","system_prompt","reasoning_mode","max_tokens","temperature","top_p","enable_safety_checker"],"type":"object"},"Nemotron3NanoOmniOutput":{"title":"BaseOutput","properties":{"finish_reason":{"title":"Finish Reason","description":"Reason generation stopped.","examples":["stop","length"],"default":"stop","type":"string"},"output":{"title":"Output","description":"Generated text response.","examples":["The image shows a golden retriever puppy sitting on a wooden floor."],"type":"string"},"usage":{"description":"Token usage for the request.","examples":[{"output_tokens":87,"input_tokens":412}],"$ref":"#/components/schemas/UsageInfo"}},"required":["output","usage"],"x-fal-order-properties":["output","finish_reason","usage"],"type":"object"},"UsageInfo":{"title":"UsageInfo","properties":{"output_tokens":{"title":"Output Tokens","description":"Number of output tokens generated.","type":"integer"},"input_tokens":{"title":"Input Tokens","description":"Number of input tokens processed.","type":"integer"}},"required":["input_tokens","output_tokens"],"x-fal-order-properties":["input_tokens","output_tokens"],"type":"object"}}},"paths":{"/fal-ai/nemotron-3-nano-omni/requests/{request_id}/status":{"get":{"parameters":[{"name":"request_id","in":"path","required":true,"schema":{"type":"string","description":"Request ID"}},{"name":"logs","in":"query","required":false,"schema":{"type":"number","description":"Whether to include logs (`1`) in the response or not (`0`)."}}],"responses":{"200":{"description":"The request status.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/QueueStatus"}}}}}}},"/fal-ai/nemotron-3-nano-omni/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-nano-omni":{"post":{"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/Nemotron3NanoOmniInput"}}}},"responses":{"200":{"description":"The request status.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/QueueStatus"}}}}}}},"/fal-ai/nemotron-3-nano-omni/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/Nemotron3NanoOmniOutput"}}}}}}}},"servers":[{"url":"https://queue.fal.run"}],"security":[{"apiKeyAuth":[]}]}}],"next_cursor":null,"has_more":false}
