厂商 · 2026-11-12
NVIDIA
| 模型 | 输入 / 1M | 输出 / 1M | 上下文 | 服务商 | 标签 |
|---|---|---|---|---|---|
| Nemotron 3.5 Lightning 30B A3B | $0.025 | $0.120 | 262K | 5 | tools · json · reasoning · open-weights |
| Nemotron 3.5 Lightning 30B A3B | $0.050 | $0.150 | 262K | 7 | tools · json · reasoning · open-weights |
| Nemotron 3.5 Content Safety | $0.050 | $0.150 | 128K | 6 | reasoning · vision · open-weights |
| nemotron-3-ultra | $0.100 | $0.100 | 262K | 3 | tools · reasoning · open-weights |
| Nemotron 3 Nano 30B A3B | $0.050 | $0.200 | 262K | 14 | tools · json · reasoning · open-weights |
| NVIDIA Nemotron Nano 9B v2 | $0.060 | $0.230 | 131K | 3 | tools · json · open-weights |
| Nemotron 3 Super 120B A12B | $0.050 | $0.250 | 262K | 14 | tools · json · reasoning · open-weights |
| Nemotron 3 Nano Omni | $0.100 | $0.250 | 256K | 4 | tools · json · reasoning · vision · open-weights |
| Nemotron 3.5 Super VL | $0.060 | $0.350 | 1.05M | 7 | tools · json · reasoning · vision · open-weights |
| Nemotron 3.5 Super VL 120B A12B | $0.150 | $0.470 | 1.05M | 4 | tools · reasoning · vision · open-weights |
| Llama 3.1 Nemotron 70B Instruct | $0.600 | $0.600 | 128K | 2 | tools · open-weights |
| Nemotron 3 Ultra 550B A55B | $0.400 | $1.76 | 1M | 17 | tools · json · reasoning · open-weights |
| Nemotron 3 Ultra 550B (DeepInfra) | $0.900 | $1.70 | 262K | 3 | tools · vision |
| Active Speaker Detection | 未公开 | 未公开 | Unknown | 1 | open-weights |
| bevformer | 未公开 | 未公开 | 128K | 1 | open-weights |
| Cosmos Reason2 8B | 未公开 | 未公开 | 131K | 1 | tools · reasoning · vision · open-weights |
| cosmos-transfer2.5-2b | 未公开 | 未公开 | Unknown | 1 | vision · open-weights |
| FLUX.1-dev | 未公开 | 未公开 | Unknown | 1 | open-weights |
| FLUX.1-Kontext-dev | 未公开 | 未公开 | Unknown | 1 | vision · open-weights |
| FLUX.1-schnell | 未公开 | 未公开 | Unknown | 1 | open-weights |
| FLUX.2 Klein 4B | 未公开 | 未公开 | Unknown | 1 | vision · open-weights |
| Laguna XS 2.1 | 未公开 | 未公开 | 262K | 1 | tools · reasoning · open-weights |
| Llama 3.1 Nemotron Ultra 253B | 未公开 | 未公开 | 128K | 1 | tools · reasoning · open-weights |
| llama-3.1-nemotron-safety-guard-8b-v3 | 未公开 | 未公开 | 128K | 1 | open-weights |
| llama-nemotron-embed-vl-1b-v2 | 未公开 | 未公开 | 8K | 1 | vision · open-weights |
| llama-nemotron-rerank-vl-1b-v2 | 未公开 | 未公开 | 10K | 1 | vision · open-weights |
| magpie-tts-zeroshot | 未公开 | 未公开 | Unknown | 1 | open-weights |
| Nemotron 3 Nano Omni (free) | 未公开 | 未公开 | 256K | 3 | tools · reasoning · vision · open-weights |
| Nemotron 3 Ultra (free) | 未公开 | 未公开 | 1M | 5 | tools · reasoning · open-weights |
| Nemotron 3.5 Lightning (free) | 未公开 | 未公开 | 1M | 5 | tools · reasoning · open-weights |
| Nemotron 3.5 Super VL (free) | 未公开 | 未公开 | 1M | 3 | tools · json · reasoning · vision · open-weights |
| nemotron-voicechat | 未公开 | 未公开 | 128K | 1 | tools · open-weights |
| rerank-qa-mistral-4b | 未公开 | 未公开 | 128K | 1 | open-weights |
| riva-translate-4b-instruct-v1_1 | 未公开 | 未公开 | 128K | 1 | open-weights |
| sparsedrive | 未公开 | 未公开 | 128K | 1 | open-weights |
| streampetr | 未公开 | 未公开 | 128K | 1 | open-weights |
| studiovoice | 未公开 | 未公开 | Unknown | 1 | open-weights |
| synthetic-video-detector | 未公开 | 未公开 | Unknown | 1 | open-weights |
| usdcode | 未公开 | 未公开 | 128K | 1 | — |
| usdvalidate | 未公开 | 未公开 | Unknown | 1 | open-weights |
| DiffusionGemma 26B A4B IT衍生 | 未公开 | 未公开 | 250K | 1 | tools · reasoning · vision · open-weights |
| Magistral Small 2506衍生 | 未公开 | 未公开 | 33K | 1 | open-weights |
| Mistral Medium 3衍生 | 未公开 | 未公开 | 131K | 1 | vision |
| Mistral-7B-Instruct-v0.3衍生 | 未公开 | 未公开 | 66K | 1 | tools · json · open-weights |
| paligemma衍生 | 未公开 | 未公开 | 128K | 1 | vision · open-weights |
| Qwen Image衍生 | 未公开 | 未公开 | Unknown | 1 | — |
| Qwen Image Edit衍生 | 未公开 | 未公开 | Unknown | 1 | vision |
Frequently asked questions
How many AI models does NVIDIA offer?
We track 40 canonical NVIDIA models plus 7 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.
Which NVIDIA model is the cheapest?
Nemotron 3.5 Lightning 30B A3B is currently the lowest-priced NVIDIA model, at $0.025 per 1M input tokens and $0.120 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which NVIDIA model has the largest context window?
Nemotron 3.5 Super VL leads at 1.05M tokens. This is the total of prompt + completion.
Which NVIDIA models support tool calling?
Multiple NVIDIA models support tool calling, with Nemotron 3.5 Lightning 30B A3B being a popular pick. The capability column in the table above marks every model with NVIDIA tool-calling support.
Which NVIDIA models accept image input?
Nemotron 3.5 Content Safety accepts image input. Other vision-capable NVIDIA models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.
What are the best alternatives to NVIDIA?
Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.
How fresh is this NVIDIA pricing data?
Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.
Explore more
Top NVIDIA models
- Nemotron 3 Ultra 550B A55B$0.40 in / $1.76 out
- Nemotron 3 Nano 30B A3B$0.05 in / $0.20 out
- Nemotron 3 Super 120B A12B$0.05 in / $0.25 out
- Nemotron 3.5 Lightning 30B A3B$0.05 in / $0.15 out
- Nemotron 3.5 Super VL$0.06 in / $0.35 out
Browse by use case
Browse by capability
最近更新：
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.