NVIDIA
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. It takes text, images, documents, GUI screenshots, and video...
Cost / 1M tokens
Very low usage$0.15
input
$0.02
cached input
$0.47
output
Context Window
1M
Up to 944K max output
Modalities
text, image, video → text
Other tokenizer
Quickstart & API
nvidia/nemotron-3.5-super-vlBest for & Strengths
Key Strengths
Recommended Workloads in ChatOSS
- Coding agents
- Complex reasoning & debugging
- Screenshot-to-code workflows
Verified Evaluations
Benchmarks & Frontier Comparison
How Nemotron 3.5 Super VL compares against leading open-weight and proprietary frontier models across independent agentic coding and reasoning suites.
| Benchmark (Metric) | Nemotron 3.5 Super VL | DeepSeek V4.1 Flash | GLM 5.3 | Kimi K3.1 Pro | Claude Opus 5.5 |
|---|---|---|---|---|---|
| Agentic & Software Engineering | |||||
| ChatOSS Agentic Coding Index (%) | — | 63.2% | 58.3% | 65% | 74.1% |
| SWE-Bench Verified (%) | — | 91.5% | 95.4% | 94.8% | 97% |
| DeepSWE v1.1 (Pass@1 %) | — | 77% | 69% | 73.5% | 74.2% |
| Vibe Code Bench v1.1 (%) | — | 87.7% | 78.1% | 88.4% | 90.3% |
| Terminal-Bench 4.0 (%) | — | 42.3% | 42% | 46.2% | 65.2% |
| Code Migration (%) | — | 45.6% | 44.2% | 52% | 66.7% |
| Intelligence & Token Economics | |||||
| Artificial Analysis Intelligence Index (0–100) | 13.6 | 39.5 | 44.8 | 55.1 | 57.6 |
| Input Price (/ 1M tokens) | $0.15 | $0.15 | $1.40 | $2.00 | $4.00 |
| Output Price (/ 1M tokens) | $0.47 | $0.60 | $4.40 | $10.00 | $20.00 |
Artificial Analysis Intelligence Index
Artificial Analysis
Design Arena: 3D
Design Arena · Rank #85 (30.4% win)
Design Arena: Code Generation
Design Arena · Rank #88 (33.5% win)
Design Arena: Data Visualization
Design Arena · Rank #101 (27.4% win)
Design Arena: Game Dev
Design Arena · Rank #98 (29.5% win)
Active Provider Endpoints (10)
Upstream inference providers serving Nemotron 3.5 Super VL, with per-provider pricing, context limits, quantization, and 24-hour uptime.
| Provider | Input / 1M | Output / 1M | Cache Read / 1M | Context | Max Output | Quantization | Uptime (24h) |
|---|---|---|---|---|---|---|---|
Darkbloomcache darkbloom/nvfp4 | $0.06 | $0.35 | $0.01 | 262K | 131K | nvfp4 | 99.3% |
Io Netcache io-net/nvfp4 | $0.09 | $0.30 | $0.012 | 262K | 131K | nvfp4 | 99.8% |
Crusoecache crusoe/bf16 | $0.10 | $0.40 | $0.08 | 1M | 262K | bf16 | 98.5% |
CoreWeavecache coreweave/nvfp4 | $0.15 | $0.47 | $0.02 | 1M | 944K | nvfp4 | 99.7% |
PrimeIntellectcache primeintellect/nvfp4 | $0.15 | $0.50 | $0.02 | 1M | 131K | nvfp4 | 99.4% |
Togethercache together | $0.15 | $0.50 | $0.02 | 262K | 236K | — | 99.7% |
DeepInfracache deepinfra/fp4 | $0.15 | $0.50 | $0.02 | 262K | 236K | fp4 | 100.0% |
Venicecache venice/fp4 | $0.20 | $0.50 | $0.04 | 262K | 102K | fp4 | 99.2% |
BaseTencache baseten/fp4 | $0.20 | $0.50 | $0.04 | 1M | 944K | fp4 | 96.0% |
Nebiuscache nebius/bf16 | $0.30 | $0.90 | $0.06 | 1M | 944K | bf16 | 93.5% |
Supported API Parameters
Parameters accepted by this model when called through ChatOSS or OpenRouter.
Compare Similar Models
Browse all models →NVIDIA
Nemotron 3.5 Lightning
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
NVIDIA
Nemotron 3.5 Content Safety
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
NVIDIA
Nemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
NVIDIA
Nemotron 3 Super
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
Anthropic
Claude Opus 5.5
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
Moonshot AI
Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...