{"id":"nemotron-3-ultra-550b-a55b","canonicalKey":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron Ultra","url":"https://www.aimodel.directory/models/nemotron-3-ultra-550b-a55b","lab":{"id":"nvidia","name":"NVIDIA","url":"https://www.aimodel.directory/labs/nvidia"},"status":"active","releaseDate":"2026-06-04","deprecationDate":null,"knowledgeCutoff":"2026-02","openWeights":true,"license":"openmdw-1.1","paramsTotal":560524578816,"contextWindow":202800,"maxOutput":202800,"inputModalities":["text"],"outputModalities":["text"],"capabilities":{"reasoning":true,"toolCall":true,"structuredOutput":true},"huggingFace":{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","downloads":401157,"likes":359},"pricing":[{"provider":"nvidia","providerName":"NVIDIA NIM","providerModelId":"nvidia/nemotron-3-ultra-550b-a55b","currency":"USD","unit":"per 1M tokens","input":0.5,"output":2.5,"cachedInput":0.15,"contextWindow":1000000,"source":"https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/nemotron-3-ultra-550b-a55b.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"openrouter","providerName":"OpenRouter","providerModelId":"nvidia/nemotron-3-ultra-550b-a55b","currency":"USD","unit":"per 1M tokens","input":0.5,"output":2.2,"cachedInput":0.1,"contextWindow":262144,"source":"https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b","retrievedAt":"2026-10-04T22:35:46.316Z"},{"provider":"fireworks-ai","providerName":"Fireworks AI","providerModelId":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","currency":"USD","unit":"per 1M tokens","input":0.6,"output":2.4,"cachedInput":0.12,"contextWindow":262144,"source":"https://github.com/sst/models.dev/blob/dev/providers/fireworks-ai/models/accounts/fireworks/models/nemotron-3-ultra-nvfp4.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"baseten","providerName":"Baseten","providerModelId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","currency":"USD","unit":"per 1M tokens","input":0.6,"output":2.4,"cachedInput":0.12,"contextWindow":202800,"source":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"togetherai","providerName":"Together AI","providerModelId":"nvidia/nemotron-3-ultra-550b-a55b","currency":"USD","unit":"per 1M tokens","input":0.6,"output":3.6,"cachedInput":0.2,"contextWindow":512300,"source":"https://github.com/sst/models.dev/blob/dev/providers/togetherai/models/nvidia/nemotron-3-ultra-550b-a55b.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"vercel","providerName":"Vercel AI Gateway","providerModelId":"nvidia/nemotron-3-ultra-550b-a55b","currency":"USD","unit":"per 1M tokens","input":0.6,"output":2.4,"cachedInput":0.12,"contextWindow":1000000,"source":"https://github.com/sst/models.dev/blob/dev/providers/vercel/models/nvidia/nemotron-3-ultra-550b-a55b.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"nebius","providerName":"Nebius AI Studio","providerModelId":"nvidia/Nemotron-3-Ultra-550b-a55b","currency":"USD","unit":"per 1M tokens","input":1,"output":3,"cachedInput":1,"contextWindow":1048576,"source":"https://github.com/sst/models.dev/blob/dev/providers/nebius/models/nvidia/Nemotron-3-Ultra-550b-a55b.toml","retrievedAt":"2026-10-04T22:35:42.329Z"}],"factSources":{"hfId":{"url":"https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b","source":"openrouter","retrievedAt":"2026-10-04T14:53:49.358Z"},"name":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"family":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"status":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"license":{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","source":"huggingface","retrievedAt":"2026-10-04T22:35:48.927Z"},"toolCall":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"maxOutput":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"reasoning":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"attachment":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"description":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"hfDownloads":{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","source":"huggingface","retrievedAt":"2026-10-04T22:35:48.927Z"},"lastUpdated":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"openWeights":{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","source":"huggingface","retrievedAt":"2026-10-04T22:35:48.927Z"},"paramsTotal":{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","source":"huggingface","retrievedAt":"2026-10-04T22:35:48.927Z"},"releaseDate":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"contextWindow":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"inputModalities":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"knowledgeCutoff":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"outputModalities":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"structuredOutput":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"}},"lastVerified":"2026-10-04T22:35:48.927Z","dataLicense":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"AI Model Directory (https://www.aimodel.directory/models/nemotron-3-ultra-550b-a55b)"}}