NVIDIA: Nemotron 3.5 Super VL
nvidia/nemotron-3.5-super-vl
Nemotron 3.5 Super VL (NVIDIA) is a low-cost open-weight model priced near the bottom of the board, at $0.15/$0.5 per million input/output tokens, served by 4 independent hosts. For the money it delivers #122 of 260 on the TryAii Score. Its best showing is #64 on HLE. It's among the fastest models we track, at roughly 152-381 tokens/sec.
Prompt $/1M
$0.150
Completion $/1M
$0.500
Context
1,048,576 tok
Best provider
436 tok/s · DeepInfra
Specs
- Model id
- nvidia/nemotron-3.5-super-vl
- Display name
- NVIDIA: Nemotron 3.5 Super VL
- Modality
- text+image+video->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 1,048,576
- Max completion
- 235,929
- Prompt $/1M
- $0.150
- Completion $/1M
- $0.500
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| DeepInfrafastest | 436 |
| CoreWeave | 363 |
| Crusoe | 165 |
| Together | 113 |
| nvidiafastest | — |