{"id":"nemotron-3-super-120b-a12b","canonicalKey":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron Super","url":"https://www.aimodel.directory/models/nemotron-3-super-120b-a12b","lab":{"id":"nvidia","name":"NVIDIA","url":"https://www.aimodel.directory/labs/nvidia"},"status":"active","releaseDate":"2026-03-11","deprecationDate":null,"knowledgeCutoff":"2026-02","openWeights":true,"license":"nvidia-nemotron-open-model-license","paramsTotal":123611012096,"contextWindow":202800,"maxOutput":202800,"inputModalities":["text"],"outputModalities":["text"],"capabilities":{"reasoning":true,"toolCall":true,"structuredOutput":true},"huggingFace":{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","downloads":59277,"likes":283},"pricing":[{"provider":"openrouter","providerName":"OpenRouter","providerModelId":"nvidia/nemotron-3-super-120b-a12b","currency":"USD","unit":"per 1M tokens","input":0.08,"output":0.45,"cachedInput":null,"contextWindow":262144,"source":"https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b","retrievedAt":"2026-10-04T22:35:46.316Z"},{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerModelId":"nvidia.nemotron-super-3-120b","currency":"USD","unit":"per 1M tokens","input":0.15,"output":0.65,"cachedInput":null,"contextWindow":262144,"source":"https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/nvidia.nemotron-super-3-120b.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"vercel","providerName":"Vercel AI Gateway","providerModelId":"nvidia/nemotron-3-super-120b-a12b","currency":"USD","unit":"per 1M tokens","input":0.15,"output":0.65,"cachedInput":null,"contextWindow":256000,"source":"https://github.com/sst/models.dev/blob/dev/providers/vercel/models/nvidia/nemotron-3-super-120b-a12b.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"nvidia","providerName":"NVIDIA NIM","providerModelId":"nvidia/nemotron-3-super-120b-a12b","currency":"USD","unit":"per 1M tokens","input":0.2,"output":0.8,"cachedInput":null,"contextWindow":262144,"source":"https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/nemotron-3-super-120b-a12b.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"nebius","providerName":"Nebius AI Studio","providerModelId":"nvidia/nemotron-3-super-120b-a12b","currency":"USD","unit":"per 1M tokens","input":0.3,"output":0.9,"cachedInput":null,"contextWindow":262144,"source":"https://github.com/sst/models.dev/blob/dev/providers/nebius/models/nvidia/nemotron-3-super-120b-a12b.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"baseten","providerName":"Baseten","providerModelId":"nvidia/Nemotron-120B-A12B","currency":"USD","unit":"per 1M tokens","input":0.3,"output":0.75,"cachedInput":0.06,"contextWindow":202800,"source":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml","retrievedAt":"2026-10-04T22:35:42.329Z"},{"provider":"cloudflare-workers-ai","providerName":"Cloudflare Workers AI","providerModelId":"@cf/nvidia/nemotron-3-120b-a12b","currency":"USD","unit":"per 1M tokens","input":0.5,"output":1.5,"cachedInput":null,"contextWindow":256000,"source":"https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/nvidia/nemotron-3-120b-a12b.toml","retrievedAt":"2026-10-04T22:35:42.329Z"}],"factSources":{"hfId":{"url":"https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b","source":"openrouter","retrievedAt":"2026-10-04T14:53:49.358Z"},"name":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.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/Nemotron-120B-A12B.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/Nemotron-120B-A12B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"license":{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","source":"huggingface","retrievedAt":"2026-10-04T22:35:48.927Z"},"toolCall":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.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/Nemotron-120B-A12B.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/Nemotron-120B-A12B.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/Nemotron-120B-A12B.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/Nemotron-120B-A12B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"hfDownloads":{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","source":"huggingface","retrievedAt":"2026-10-04T22:35:48.927Z"},"lastUpdated":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml","source":"models.dev","retrievedAt":"2026-10-04T22:35:42.329Z"},"openWeights":{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","source":"huggingface","retrievedAt":"2026-10-04T22:35:48.927Z"},"paramsTotal":{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","source":"huggingface","retrievedAt":"2026-10-04T22:35:48.927Z"},"releaseDate":{"url":"https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.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/Nemotron-120B-A12B.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/Nemotron-120B-A12B.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/Nemotron-120B-A12B.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/Nemotron-120B-A12B.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/Nemotron-120B-A12B.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-super-120b-a12b)"}}