NVIDIA NIM
NVIDIA NIM (nvidia, Inference host, headquartered in US) serves 9 models through the Autonomous Relay Agents API. Prices are the provider's list prices, per million tokens.
| Model | Model id | Context | Input | Output |
|---|---|---|---|---|
| NVIDIA: Nemotron 3 Nano Omni (free) | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | 256,000 | $0.00 per M | $0.00 per M |
| NVIDIA: Nemotron 3 Super | nvidia/nemotron-3-super-120b-a12b | 1,000,000 | $0.085 per M | $0.40 per M |
| NVIDIA: Nemotron 3 Super (free) | nvidia/nemotron-3-super-120b-a12b:free | 262,144 | $0.00 per M | $0.00 per M |
| NVIDIA: Nemotron 3 Ultra | nvidia/nemotron-3-ultra-550b-a55b | 262,144 | $0.625 per M | $3.125 per M |
| NVIDIA: Nemotron 3 Ultra (free) | nvidia/nemotron-3-ultra-550b-a55b:free | 1,000,000 | $0.00 per M | $0.00 per M |
| NVIDIA: Nemotron 3.5 Content Safety | nvidia/nemotron-3.5-content-safety | 131,072 | $0.20 per M | $0.20 per M |
| NVIDIA: Nemotron 3.5 Content Safety (free) | nvidia/nemotron-3.5-content-safety:free | 128,000 | $0.00 per M | $0.00 per M |
| NVIDIA: Nemotron 3.5 Lightning | nvidia/nemotron-3.5-lightning | 262,144 | $0.08 per M | $0.20 per M |
| NVIDIA: Nemotron 3.5 Lightning (free) | nvidia/nemotron-3.5-lightning:free | 1,000,000 | $0.00 per M | $0.00 per M |