NVIDIA models
9 NVIDIA models you can call through MartLLM’s OpenAI-compatible API. The cheapest is NVIDIA Nemotron Nano 9B v2 at $0.00060/1M input tokens, as of November 20, 2026. Every request is routed to the cheapest healthy seller; the price shown has no MartLLM fee added.
- NVIDIA: Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl$0.0225 in$0.0750 out−85%
- NVIDIA Nemotron 3 Super 120Bnvidia/nemotron-3-super-120b$0.00075 in$0.0040 out−99%
- NVIDIA Nemotron 3 Ultra 550Bnvidia/nemotron-3-ultra-550b-a55b$0.0875 in$0.4375 out−86%
- NVIDIA Nemotron 3 Nano 30Bnvidia/nemotron-3-nano-30b-a3b$0.00074 in$0.0030 out−99%
- NVIDIA Nemotron Nano 12B v2 VL BF16nvidia/nemotron-nano-12b-v2$0.0020 in$0.0060 out−99%
- NVIDIA Nemotron Nano 9B v2nvidia/nemotron-nano-9b-v2$0.00060 in$0.0023 out−99%
- NVIDIA Nemotron 3.5 Lightning 30Bnvidia/nemotron-3-5-lightning-30b-a3b$0.0640 in$0.1600 out
- NVIDIA Nemotron Cascade 2 30Bnvidia/nemotron-cascade-2-30b-a3b
- Cosmos Predict (image-to-video)nvidia/cosmos-predict-image-to-video$0.56 per video−30%
| Model | Price (from) | Context | Type | Capabilities |
|---|---|---|---|---|
| NVIDIA: Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | $0.0225 in$0.0750 out−85% | 262K | Text | ToolsReasoningVisionJSON |
| NVIDIA Nemotron 3 Super 120B nvidia/nemotron-3-super-120b | $0.00075 in$0.0040 out−99% | 256K | Text | ToolsJSON |
| NVIDIA Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b | $0.0875 in$0.4375 out−86% | 1000K | Text | ToolsReasoningJSON |
| NVIDIA Nemotron 3 Nano 30B nvidia/nemotron-3-nano-30b-a3b | $0.00074 in$0.0030 out−99% | 128K | Text | Tools |
| NVIDIA Nemotron Nano 12B v2 VL BF16 nvidia/nemotron-nano-12b-v2 | $0.0020 in$0.0060 out−99% | 128K | Text | ToolsVisionJSON |
| NVIDIA Nemotron Nano 9B v2 nvidia/nemotron-nano-9b-v2 | $0.00060 in$0.0023 out−99% | 128K | Text | ToolsJSON |
| NVIDIA Nemotron 3.5 Lightning 30B nvidia/nemotron-3-5-lightning-30b-a3b | $0.0640 in$0.1600 out | 1000K | Text | ToolsReasoningJSON |
| NVIDIA Nemotron Cascade 2 30B nvidia/nemotron-cascade-2-30b-a3b | 256K | Text | ToolsReasoningJSON | |
| Cosmos Predict (image-to-video) nvidia/cosmos-predict-image-to-video | $0.56 per video−30% | Video | Vision |
NVIDIA models — FAQ
What is the cheapest NVIDIA model?
NVIDIA Nemotron Nano 9B v2 is the cheapest NVIDIA model on MartLLM right now, at $0.00060/1M input tokens. MartLLM routes each request to the cheapest healthy seller and bills the price shown, with no MartLLM fee added.
How many NVIDIA models can I use through MartLLM?
9 NVIDIA models are on the MartLLM marketplace today. One OpenAI-compatible API key and base URL (https://api.martllm.com/v1) calls every one of them — no per-provider contracts.
How do I call a NVIDIA model with the API?
Use any OpenAI-compatible SDK: set the base URL to https://api.martllm.com/v1, your MartLLM key, and the model id (for example "nvidia/nemotron-3.5-super-vl"). Anthropic SDKs work against https://api.martllm.com/v1/messages.