Nemotron 3.5 Super VL 120B A12BOpen weights
NVIDIA · released 2026-10-15
No price from the maker itself is on record for Nemotron 3.5 Super VL 120B A12B. The lowest of 13 providers is Kilo Gateway: $0.06 per 1M input tokens and $0.35 per 1M output tokens (as of 2026-11-12). Context window: 1.05M tokens, up to 8.2K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| NvidiaOfficialnvidia/ | $0 | $0 | — | Official | Official docs |
KKilo GatewayLowestnvidia/ | $0.06 | $0.35 | $0.01 | Lowest | Official docs |
PPioneernvidia/ | $0.08 | $0.45 | $0.04 | Official docs | |
 OpenRouternvidia/ | $0.15 | $0.47 | $0.02 | Official docs | |
 CoreWeavenvidia/ | $0.15 | $0.47 | $0.02 | Official docs | |
NNanoGPTnvidia/ | $0.15 | $0.5 | $0.02 | Official docs | |
 Together AInvidia/ | $0.15 | $0.5 | $0.02 | Official docs | |
 Venice AInvidia-nemotron-3-5-super-vl-120b-a12b | $0.2 | $0.5 | $0.04 | Official docs | |
 Vercel AI Gatewaynvidia/ | $0.2 | $0.5 | $0.04 | Official docs | |
 DigitalOceannemotron-3.5-super-vl | $0.3 | $0.65 | $0.06 | Official docs | |
 Nebius Token Factorynvidia/ | $0.3 | $0.9 | $0.06 | Official docs | |
TThinking Machinesnvidia/ | $0.57 | $1.44 | $0.114 | Official docs |
4 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
TThinking Machinesnvidia/ | $0.57 | $1.44 | $0.114 | Official docs | |
KKilo Gatewaynvidia/ | $0 | $0 | — | Official docs | |
 OpenCodenemotron-3.5-super-vl-free | $0 | $0 | $0 | Official docs | |
| OpenRouternvidia/ | $0 | $0 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use
Description from models.dev.
Specs
- Type
- Text
- Context
- 1.05M
- Max output
- 8.2K
- Input
- Text, Image, Video
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- —
- Open weights
- Yes
- Released
- 2026-10-15
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.