Nemotron 3.5 Content Safety
Open weights
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.
API id
nemotron-3.5-content-safetyReleased 4 Jun 2026 (Jun 2026)Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
Jun 2026
4 Jun 2026
Where to run it
1 host serve Nemotron 3.5 Content Safety. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
NVIDIA NIMInference nemotron-3.5-content-safety | - | nemotron-3.5-content-safety |
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
- Text
- Produces
- Text
- Open weights
- License: NVIDIA Open Model LicenseRuns in about 10.3 GB of GPU memoryRuntimes: TGI, vLLM
Similar models
This model has no listed price, so these are current models with similar capabilities.
Smaller NVIDIA models
No similar NVIDIA model keeps its key capabilities.
Other frontier labs
Open-weight picks
Call it
Using NVIDIA NIM's API.
Python
from litellm import completion
response = completion(
model="nvidia_nim/nemotron-3.5-content-safety",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
Which APIs offer Nemotron 3.5 Content Safety?
Nemotron 3.5 Content Safety runs on 1 API: NVIDIA NIM.
Is Nemotron 3.5 Content Safety being retired?
No retirement date is scheduled for it on any API we track.
When was Nemotron 3.5 Content Safety released?
NVIDIA released it on 4 Jun 2026.
What is Nemotron 3.5 Content Safety's API model id?
Use nemotron-3.5-content-safety with NVIDIA NIM.
Sources
Raw catalog entry for nemotron-3.5-content-safety on NVIDIA NIM
{
"litellm_provider": "nvidia_nim",
"mode": "chat",
"source": "https://build.nvidia.com/nvidia/nemotron-3.5-content-safety.md",
"supported_endpoints": [
"/v1/chat/completions"
]
}