NVIDIA
- Models
- 61
- Hosted by a direct provider
- 56
Provider counts exclude gateways.
| Model | Compare | Type | Released | Context | Providers | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|---|
| Nemotron 3.5 Super VL 120B A12B | Chat | 2026-10-15 | 1.05M | 10 +6 | $0.10–$0.30 | $0.40–$1.25 | |
| Switchyard | Chat | 2026-09-21 | 1M | 0 +1 | |||
| Nemotron 3.5 ASR Streaming Multilingual 0.6B | Transcription | 2026-08-13 | 0 +1 | n/a | |||
| Nemotron 3.5 Lightning 30B A3B | Chat | 2026-08-11 | 262K | 9 +9 | $0.025–$0.080 | $0.12–$0.24 | |
| Nemotron 3 Nano Omni 30B TEEunverified | Chat | 2026-07-23 | 131K | 1 | $0.0245 | $0.0978 | |
| Nemotron 3 Embed 1B | Embedding | 2026-07-16 | 32.8K | 0 +1 | Free tier | ||
| Nemotron 3.5 Content Safety | Chat | 2026-06-04 | 128K | 3 +5 | $0.05–$0.20 | $0.15–$0.20 | |
| Nemotron 3 Ultra 550B A55B | Chat | 2026-06-04 | 1M | 10 +14 | $0.50–$1.00 | $2.15–$3.13 | |
| Nemotron 3 Ultraunverified | Chat | 2026-06-01 | 262K | 1 +1 | $0.90 | $1.70 | |
| Parakeet TDT 0.6B v3 | Transcription | 2026-05-27 | 0 +1 | n/a | |||
| nemotron-3-nano-omni | Chat | 2026-05-20 | 300K | 1 +1 | $0.06 | $0.24 | |
| Nemotron 3 Nano Omni | Chat | 2026-04-28 | 256K | 5 +4 | $0.10–$0.50 | $0.25–$1.83 | |
| Active Speaker Detection | Chat | 2026-04-16 | 1 | Free tier | |||
| nemotron-3-content-safety | Chat | 2026-04-16 | 128K | 1 | Free tier | ||
| synthetic-video-detector | Chat | 2026-04-16 | 1 | Free tier | |||
| llama-nemotron-rerank-vl-1b-v2 | Rerank | 2026-03-31 | 128K | 1 +1 | Free tier | n/a | |
| nemotron-voicechat | Realtime | 2026-03-16 | 128K | 1 | Free tier | ||
| Nemotron 3 Super 120B | Chat | 2026-03-11 | 262K | 13 +10 | $0.08–$0.50 | $0.40–$2.50 | |
| gliner-pii | Chat | 2026-03-03 | 128K | 1 | Free tier | ||
| cosmos-transfer2.5-2b | Video generation | 2026-02-26 | 1 | Free tier | n/a | ||
| llama-nemotron-embed-vl-1b-v2 | Embedding | 2026-02-10 | 32.8K | 1 +1 | Free tier | ||
| nemotron-content-safety-reasoning-4b | Chat | 2026-01-22 | 128K | 1 | Free tier | ||
| usdcode | Chat | 2026-01-01 | 128K | 1 | Free tier | ||
| riva-translate-4b-instruct-v1_1 | Chat | 2025-12-12 | 128K | 1 | Free tier | ||
| Cosmos Reason2 8B | Chat | 2025-12-01 | 131K | 1 | Free tier | ||
| streampetr | Chat | 2025-11-13 | 128K | 1 | Free tier | ||
| nemotron-nano-v2-12bunverified | Chat | 2025-10-31 | 128K | 0 +1 | via Cortecs $0.24 | via Cortecs $0.707 | |
| llama-3.1-nemotron-safety-guard-8b-v3 | Chat | 2025-10-28 | 128K | 1 | Free tier | ||
| Nemotron Nano 12B v2 VL | Chat | 2025-10-28 | 131K | 3 +1 | $0.20 | $0.60 | |
| Llama Nemotron Embed 1B v2 | Embedding | 2025-10-16 | 8.2K | 1 | |||
| NVIDIA-Nemotron-Nano-12B-v2 | Chat | 2025-08-18 | 131K | 3 | $0.07–$0.20 | $0.20 | |
| nvidia-nemotron-nano-9b-v2 | Chat | 2025-08-18 | 131K | 5 +2 | $0.04–$0.20 | $0.16–$0.23 | |
| Llama 3.3 Nemotron Super 49B v1.5 | Chat | 2025-07-25 | 131K | 2 | Free tier | ||
| llama-3_2-nemoretriever-300m-embed-v1 | Embedding | 2025-07-24 | 32.8K | 1 | Free tier | ||
| cosmos-transfer1-7b | Video generation | 2025-06-13 | 1 | Free tier | n/a | ||
| mistral-nemotron | Chat | 2025-06-11 | 128K | 1 | Free tier | ||
| magpie-tts-zeroshot | Speech synthesis | 2025-05-22 | 1 | Free tier | n/a | ||
| Llama 3.1 Nemotron 70B Instruct | Chat | 2025-04-15 | 128K | 2 +2 | $0.60 | $0.60 | |
| Llama 3.1 Nemotron Nano VL 8B v1 | Chat | 2025-04-10 | 32.8K | 1 | Free tier | ||
| Llama 3.1 Nemotron Ultra 253B | Chat | 2025-04-07 | 128K | 3 | $0.60 | $1.80 | |
| Llama 3.3 Nemotron Super 49B v1 | Chat | 2025-04-07 | 131K | 2 +1 | $0.10 | $0.40 | |
| bevformer | Chat | 2025-03-18 | 128K | 1 | Free tier | ||
| cosmos-predict1-5b | Video generation | 2025-03-18 | 1 | Free tier | n/a | ||
| Llama 3.1 Nemotron Nano 8B v1 | Chat | 2025-03-18 | 131K | 1 | Free tier | ||
| sparsedrive | Chat | 2025-03-18 | 128K | 1 | Free tier | ||
| nv-embedcode-7b-v1 | Embedding | 2025-03-17 | 32.8K | 1 | Free tier | ||
| nemotron-3-nano-30b-a3b | Chat | 2024-12 | 262K | 10 +9 | $0.050–$0.075 | $0.20–$0.30 | |
| studiovoice | Chat | 2024-10-03 | 128K | 1 | Free tier | ||
| nvidia--llama-3.2-nv-embedqa-1b | Embedding | 2024-09-25 | 8.2K | 1 | $0.07 | ||
| nemotron-mini-4b-instruct | Chat | 2024-08-21 | 128K | 1 | Free tier | ||
| usdvalidate | Chat | 2024-07-24 | 1 | Free tier | |||
| nv-embed-v1 | Embedding | 2024-06-07 | 32.8K | 1 | Free tier | ||
| rerank-qa-mistral-4b | Rerank | 2024-03-17 | 128K | 1 | Free tier | n/a | |
| cosmos3-super-reasoner | Chat | — | 262K | 1 | $0.10 | $0.30 | |
| gemma-4-31b-it | Chat | — | 262K | 1 | $0.14 | $0.40 | |
| llama-3-1-nemotron-70b-instruct-hf | Chat | — | 32.8K | 1 | |||
| llama-3-2-nv-rerankqa-1b-v2 | Rerank | — | 1 | Free tier | n/a | ||
| nemotron-content-safety-3-5 | Chat | — | 131K | 1 | $0.20 | $0.20 | |
| nemotron-lightning-3p5-30b-a3bunverified | Chat | — | 262K | 1 | $0.05 | $0.20 | |
| nemotron-nano-v2-12b-vlunverified | Chat | — | 131K | 1 | $0.10 | $0.10 | |
| nv-rerankqa-mistral-4b-v3 | Rerank | — | 1 | Free tier | n/a |
Providers: direct count, then “+n” gateways. Prices are the range across comparable direct providers (gateways, subscription plans, deprecated endpoints and anything that is not a paid per-token price excluded); models only on gateways show the cheapest gateway list price. Non-token models show their native unit.