Nemotron 3.5 Super VL
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
Nemotron-3.5-Super-VLReleased 15 Oct 2026 (5 weeks ago)Pricing
List prices at Nebius AI Studio, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.30 | $0.90 | |
| Cached input 80% off input | $0.06 | 80% off input |
What it costs a month
At Nebius AI Studio list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$136
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$119
- Coding agent1,000 requests a day, 40K in / 2K out, cached$212
- Overnight batch20,000 requests a day, 4K in / 0.4K out$936
Where to run it
2 hosts serve Nemotron 3.5 Super VL. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Kyma APICloud nemotron-3.5-super-vl | $0.081 / $0.472 −60% vs headline | nemotron-3.5-super-vl | |
Nebius AI StudioInference Nemotron-3.5-Super-VL | $0.30 / $0.90 | Nemotron-3.5-Super-VL |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImagesVideo
- Produces
- Text
- Features
- Video input
- Open weights
- License: NVIDIA Open Model LicenseRuns in about 298.7 GB of GPU memoryRuntimes: TGI, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
- Kyma API60% lessnemotron-3.5-super-vl$0.081 / $0.472
Smaller NVIDIA models
No cheaper NVIDIA model keeps its key capabilities.
Other frontier labs
- 56% less
- 56% less
- 42% less
Open-weight picks
- 3% less
- 12% less
- 18% less
- 22% less
Call it
Using Nebius AI Studio's API.
from litellm import completion
response = completion(
model="nebius/Nemotron-3.5-Super-VL",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Nemotron 3.5 Super VL cost?
On Nebius AI Studio, Nemotron 3.5 Super VL costs $0.30 per million input tokens and $0.90 per million output tokens. Cached input costs $0.06 per million tokens. The cheapest host is Kyma API, at $0.081 per million input tokens and $0.472 per million output tokens.
Which APIs offer Nemotron 3.5 Super VL?
Nemotron 3.5 Super VL runs on 2 APIs: Kyma API and Nebius AI Studio.
What is Nemotron 3.5 Super VL's context window?
1M tokens, with up to 236K tokens in one reply.
Is Nemotron 3.5 Super VL being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Nemotron 3.5 Super VL?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (56% less), GPT-6 Luna on OpenAI (56% less) and MiMo V2.6 Pro on GMI Cloud (3% less). Nemotron 3.5 Super VL itself costs 60% less on Kyma API. Savings are on a mix of 3 input tokens to 1 output token.
When was Nemotron 3.5 Super VL released?
NVIDIA released it on 15 Oct 2026.
What is Nemotron 3.5 Super VL's API model id?
Use Nemotron-3.5-Super-VL with Nebius AI Studio. Other hosts use their own ids: nemotron-3.5-super-vl on Kyma API.
Sources
Raw catalog entry for Nemotron-3.5-Super-VL on Nebius AI Studio
{
"max_input_tokens": 1048576,
"input_cost_per_token": 3e-7,
"cache_read_input_token_cost": 6e-8,
"output_cost_per_token": 9e-7,
"litellm_provider": "nebius",
"mode": "chat",
"supports_vision": true,
"supports_video_input": true,
"supports_reasoning": true,
"supports_function_calling": true,
"source": "https://tokenfactory.nebius.com/api/public/models_info"
}