廠商 · 2026-06-29
NVIDIA
| 模型 | 輸入 / 1M | 輸出 / 1M | 上下文 | 服務商 | 標籤 |
|---|---|---|---|---|---|
| llama-3.1-nemotron-safety-guard-8b-v3 | $0.010 | $0.010 | 128K | 2 | open-weights |
| nvidia-nemotron-nano-9b-v2 | $0.040 | $0.160 | 131K | 5 | tools · reasoning · open-weights |
| nemotron-3-nano-30b-a3b | $0.050 | $0.200 | 131K | 7 | tools · reasoning · open-weights |
| Llama 3.3 Nemotron Super 49B v1.5 | $0.050 | $0.250 | 131K | 3 | tools · reasoning · open-weights |
| Nemotron 3 Nano Omni | $0.130 | $0.380 | 256K | 3 | tools · json · reasoning · vision · open-weights |
| Nemotron 3 Super | $0.200 | $0.800 | 262K | 9 | tools · reasoning · open-weights |
| Nemotron 3 Ultra 550B A55B | $0.500 | $2.50 | 1M | 6 | tools · json · reasoning · open-weights |
| Active Speaker Detection | 未公開 | 未公開 | Unknown | 1 | open-weights |
| bevformer | 未公開 | 未公開 | 128K | 1 | open-weights |
| BGE M3 | 未公開 | 未公開 | 8K | 1 | open-weights |
| cosmos-predict1-5b | 未公開 | 未公開 | Unknown | 1 | vision · open-weights |
| cosmos-transfer1-7b | 未公開 | 未公開 | Unknown | 1 | vision · open-weights |
| cosmos-transfer2.5-2b | 未公開 | 未公開 | Unknown | 1 | vision · open-weights |
| FLUX.1-dev | 未公開 | 未公開 | 4K | 1 | — |
| FLUX.1-Kontext-dev | 未公開 | 未公開 | 41K | 1 | vision · open-weights |
| FLUX.1-schnell | 未公開 | 未公開 | 77 | 1 | open-weights |
| FLUX.2 Klein 4B | 未公開 | 未公開 | 41K | 1 | vision · open-weights |
| gliner-pii | 未公開 | 未公開 | 128K | 1 | open-weights |
| llama-3_2-nemoretriever-300m-embed-v1 | 未公開 | 未公開 | 33K | 1 | open-weights |
| llama-nemotron-embed-vl-1b-v2 | 未公開 | 未公開 | 33K | 1 | vision · open-weights |
| llama-nemotron-rerank-vl-1b-v2 | 未公開 | 未公開 | 128K | 1 | vision · open-weights |
| magpie-tts-zeroshot | 未公開 | 未公開 | Unknown | 1 | open-weights |
| nemotron-3-content-safety | 未公開 | 未公開 | 128K | 1 | open-weights |
| nemotron-content-safety-reasoning-4b | 未公開 | 未公開 | 128K | 1 | reasoning · open-weights |
| nemotron-mini-4b-instruct | 未公開 | 未公開 | 128K | 1 | tools · open-weights |
| nemotron-voicechat | 未公開 | 未公開 | 128K | 1 | tools · open-weights |
| nv-embed-v1 | 未公開 | 未公開 | 33K | 1 | open-weights |
| nv-embedcode-7b-v1 | 未公開 | 未公開 | 33K | 1 | open-weights |
| rerank-qa-mistral-4b | 未公開 | 未公開 | 128K | 1 | open-weights |
| riva-translate-4b-instruct-v1_1 | 未公開 | 未公開 | 128K | 1 | open-weights |
| sarvam-m | 未公開 | 未公開 | 128K | 1 | tools · open-weights |
| sparsedrive | 未公開 | 未公開 | 128K | 1 | open-weights |
| streampetr | 未公開 | 未公開 | 128K | 1 | open-weights |
| studiovoice | 未公開 | 未公開 | 128K | 1 | open-weights |
| synthetic-video-detector | 未公開 | 未公開 | Unknown | 1 | open-weights |
| usdcode | 未公開 | 未公開 | 128K | 1 | — |
| usdvalidate | 未公開 | 未公開 | Unknown | 1 | open-weights |
| ByteDance-Seed/Seed-OSS-36B-Instruct衍生 | 未公開 | 未公開 | 262K | 1 | tools · json |
| Gemma 2 2b It衍生 | 未公開 | 未公開 | 128K | 1 | tools · json · open-weights |
| Gemma 3n E2b It衍生 | 未公開 | 未公開 | 128K | 1 | tools · json · vision · open-weights |
| Magistral Small 2506衍生 | 未公開 | 未公開 | 33K | 1 | — |
| Mistral Large 3 675B Instruct 2512衍生 | 未公開 | 未公開 | 262K | 1 | tools · json · vision · open-weights |
| Mistral Medium 3衍生 | 未公開 | 未公開 | 131K | 1 | vision |
| Mistral-7B-Instruct-v0.3衍生 | 未公開 | 未公開 | 66K | 1 | tools · json · open-weights |
| mistral-nemotron衍生 | 未公開 | 未公開 | 128K | 1 | tools · open-weights |
| mistral-small-4-119b-2603衍生 | 未公開 | 未公開 | 128K | 1 | tools · json · reasoning · vision · open-weights |
| Mistral: Mixtral 8x7B Instruct衍生 | 未公開 | 未公開 | 33K | 1 | tools · open-weights |
| paligemma衍生 | 未公開 | 未公開 | 128K | 1 | vision · open-weights |
| Phi 4 Multimodal衍生 | 未公開 | 未公開 | 128K | 1 | — |
| Qwen Image衍生 | 未公開 | 未公開 | Unknown | 1 | vision |
| Qwen Image Edit衍生 | 未公開 | 未公開 | Unknown | 1 | vision |
| solar-10.7b-instruct衍生 | 未公開 | 未公開 | 128K | 1 | tools · open-weights |
Frequently asked questions
How many AI models does NVIDIA offer?
We track 37 canonical NVIDIA models plus 15 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.
Which NVIDIA model is the cheapest?
llama-3.1-nemotron-safety-guard-8b-v3 is currently the lowest-priced NVIDIA model, at $0.010 per 1M input tokens and $0.010 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 Ultra 550B A55B leads at 1M tokens. This is the total of prompt + completion.
Which NVIDIA models support tool calling?
Multiple NVIDIA models support tool calling, with nvidia-nemotron-nano-9b-v2 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 Nano Omni 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 Super$0.20 in / $0.80 out
- nemotron-3-nano-30b-a3b$0.05 in / $0.20 out
- Nemotron 3 Ultra 550B A55B$0.50 in / $2.50 out
- nvidia-nemotron-nano-9b-v2$0.04 in / $0.16 out
- Llama 3.3 Nemotron Super 49B v1.5$0.05 in / $0.25 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.