Nemotron 3.5 Super VL pricing & price history
Nemotron 3.5 Super VL by NVIDIA costs $0.15 per 1M input tokens and $0.50 per 1M output tokens, with a 1M token context window. The cheapest provider currently charges $0.06 input / $0.35 output.
Price history
| Date | Input | Output |
|---|---|---|
| 2026-10-20 | $0.10 → $0.15 +50% | $0.40 → $0.50 +25% |
| 2026-10-17 | $0.15 → $0.10 -33% | $0.50 → $0.40 -20% |
No real-traffic data for NVIDIA's own API on this model (it may not be served directly); the table below covers third-party hosts and says nothing about the official API.
Which platform runs Nemotron 3.5 Super VL most reliably
10 platformsBy 30-day real-traffic success rate, PrimeIntellect is the most stable; Darkbloom is the cheapest.
| Platform | Last 30 days | Stability | 24 h | 30 min | |
|---|---|---|---|---|---|
| PrimeIntellect most stable | Collecting data | 99.2% | 100% | ||
| Venice | Often unstable (3 d)avg 98.38% | 99.8% | 100% | ||
| Together | Often unstable (3 d)avg 98.03% | 99.9% | 100% | ||
| BaseTen | Often unstable (2 d)avg 97.96% | 100% | 100% | ||
| DeepInfra | Often unstable (6 d)avg 97.92% | 100% | 100% | ||
| Nebius | Often unstable (4 d)avg 97.43% | 99% | 100% | ||
| Crusoe | Often unstable (8 d)avg 96.90% | 99.2% | 100% | ||
| CoreWeave | Often unstable (9 d)avg 96.56% | 99.8% | 100% | ||
| Darkbloom | Often unstable (5 d)avg 95.60% | 98% | 100% | ||
| Io Net | Often unstable (7 d)avg 93.77% | 99.2% | 100% |
Success rates come from real API traffic routed to each platform (public OpenRouter data), not our probes; each daily bar is the average of that day's samples. Green ≥ 99.5 %, yellow ≥ 97 %, orange ≥ 90 %, red < 90 %. Updated 4m ago.
Cost calculator
Cheaper alternatives to Nemotron 3.5 Super VL
| Model | Input | Output | Context | Intel. | |
|---|---|---|---|---|---|
GLM 5.3 Flash Z.ai (Zhipu) | $0.0163 | $0.14 | 1M | 27.8 | compare |
MiMo-V2.6-Flash Xiaomi | $0.14 | $0.28 | 1.1M | 26.7 | compare |
Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | 36.2 | compare |
GPT-6 Luna OpenAI | $0.10 | $0.50 | 1.1M | 27.8 | compare |
About 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...
FAQ
How much does Nemotron 3.5 Super VL cost?
Nemotron 3.5 Super VL by NVIDIA costs $0.15 per 1M input tokens and $0.50 per 1M output tokens, with a 1M token context window. The cheapest provider currently charges $0.06 input / $0.35 output. A typical request with 2,000 input and 500 output tokens costs about $0.0006.
What is the context window of Nemotron 3.5 Super VL?
Nemotron 3.5 Super VL supports up to 1,048,576 tokens of context and up to 235,929 output tokens per request.
Has Nemotron 3.5 Super VL’s price changed?
Yes. ModelBank recorded 2 price changes; the latest on 2026-10-20.
Is Nemotron 3.5 Super VL being deprecated?
No retirement date has been announced for Nemotron 3.5 Super VL as of 2026-10-31.
What are cheaper alternatives to Nemotron 3.5 Super VL?
Cheaper options include GLM 5.3 Flash ($0.0163/$0.14), MiMo-V2.6-Flash ($0.14/$0.28), Claude Haiku 5.5 ($0.10/$0.50), GPT-6 Luna ($0.10/$0.50).