NVIDIA API pricing
Live API prices for every NVIDIA model SF·SIX tracks: per 1M tokens at the standard tier from the cheapest provider, or per image, second or character in the provider’s own unit.
NVIDIA has 16 models with live API prices on SF·SIX, 6 models priced per 1M tokens and 10 models in native units (per image, second or character). The cheapest is Nemotron 3.5 Lightning at $0.025 per 1M input and $0.12 per 1M output tokens, via Darkbloom (int4). The most used on OpenRouter is Nemotron 3.5 Super VL (287.58B tokens on 2026-10-16).
- Models with live prices
- 16 (6 per token, 10 per native unit)
- Cheapest language model
- Nemotron 3.5 Lightning$0.025 / $0.12 per 1M tokens
- Most used on OpenRouter (2026-10-16)
- Nemotron 3.5 Super VL287.58B tokens
- Newest model
- Nemotron 3.5 Super VL2026-10-15
- Providers serving these models
- 12
NVIDIA token prices (USD per 1M tokens)
| Model | Input / 1M | Output / 1M | Blended 3:1 | Cheapest standard provider | Providers | Context (tokens) | OpenRouter tokens / day |
|---|---|---|---|---|---|---|---|
| Nemotron 3.5 Lightning | $0.025 | $0.12 | $0.0488 | Darkbloomint4 | 4 | 262,144 | 90.07B |
| Nemotron 3.5 Super VL | $0.10 | $0.40 | $0.175 | DeepInfrafp4 | 3 | 1,048,576 | 287.58B |
| Nemotron 3 Ultra | $0.50 | $2.20 | $0.925 | DeepInfrafp4 | 3 | 262,144 | 83.11B |
| Nemotron 3 Super | $0.085 | $0.40 | $0.1638 | DeepInfrabf16 | 3 | 262,144 | 105.18B |
| Nemotron 3 Nano 30B A3B | $0.05 | $0.20 | $0.0875 | Novita AIfp4 | 2 | 262,144 | Not in named rows |
| Nemotron 3.5 Content Safety | $0.20 | $0.20 | $0.20 | DeepInfrabf16 | 1 | 131,072 | Not in named rows |
Each model’s headline price: the cheapest qualifying provider at the standard tier in the default region. Most widely served first.
NVIDIA prices in native units
| Model | Price | Billing unit | Provider |
|---|---|---|---|
| NVIDIA Nemotron 3.5 Super Video | $0.01 | 1000 tokens | fal |
| NVIDIA Nemotron 3.5 Super Vision | $0.01 | 1000 tokens | fal |
| NVIDIA Nemotron 3.5 Super Text | $0.01 | 1000 tokens | fal |
| Cosmos 3 Super Image to Video | $0.05 | second | fal |
| Cosmos 3 Super | $0.04 | image | fal |
| Nemotron Asr Multilingual | $0.008 | minute | fal |
| Nemotron 3 Nano Omni (vision) | $0.006 | 1000 tokens | fal |
| Nemotron 3 Nano Omni (video) | $0.006 | 1000 tokens | fal |
| Nemotron 3 Nano Omni (audio) | $0.01 | 1000 tokens | fal |
| Nemotron 3 Nano Omni | $0.01 | 1000 tokens | fal |
Image, video, audio and other endpoints priced in the provider’s own unit; never converted with assumptions. Most widely served first.
Method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Missing prices are unknown, not free. OpenRouter tokens per day are the latest full UTC day of OpenRouter’s public rankings (named rows only). Prices move: see AI API price changes for recent cuts and increases.