AI Model DirectorySearch
Search models, providers, and docs
AI Model DirectorySearch models, providers, and docs
NVIDIA-Nemotron-3-Ultra-550B-A55B is available from 7 providers. The lowest input price is $0.4 per million tokens from Opper. It supports up to 262.1K tokens of context.
| Opper | deepinfra-batch/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.4 | $1.76 | $0.08 | 262.1K | 262.1K |
| Opper | deepinfra:flex/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.4 | $1.76 | $0.08 | 262.1K | 262.1K |
| deepinfra | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.5 | $2.2 | $0.1 | 262.1K | 262.1K |
| Eden AI | deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.5 | $2.2 | $0.1 | 262.1K | - |
| Opper | deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.5 | $2.2 | $0.1 | 262.1K | 262.1K |
| Tetrate Agent Router Service | deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.5 | $2.2 | $0.1 | 262.1K | 16.4K |
| Weights & Biases | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.5 | $2.15 | $0.1 | 262.1K | 262.1K |
| Basten | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.6 | $2.4 | - | 202.8K | 202.8K |
| Venice AI | nvidia-nemotron-3-ultra-550b-a55b | $0.625 | $3.125 | $0.1875 | 256K | 32.8K |
| Opper | deepinfra:priority/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.75 | $3.3 | $0.15 | 262.1K | 262.1K |