Providers / NVIDIA

NVIDIA API Models & Pricing

22 NVIDIA models tracked with official API pricing and benchmark scores, refreshed daily.

Intelligence vs. price

NVIDIA models with a published blended price and an Intelligence Index score (10 of 22). Hover a point for the model name, click to open its page.

08152230$0.01$0.1$1$10Blended API price — USD / 1M tokens (log scale)Intelligence IndexNemotron 3.5 Super VL — NVIDIA — Intelligence 26.5 — $0.313/1M tok blendedNemotron 3 Ultra 550B A55B (Reasoning) — NVIDIA — Intelligence 22.9 — $1.125/1M tok blendedNemotron 3.5 Lightning — NVIDIA — Intelligence 12.9 — $0.095/1M tok blendedNemotron 3 Super 120B A12B (Reasoning) — NVIDIA — Intelligence 12.8 — $0.45/1M tok blendedNemotron 3 Nano Omni 30B A3B Reasoning — NVIDIA — Intelligence 10.3 — $0.641/1M tok blendedNVIDIA Nemotron 3 Nano 30B A3B (Reasoning) — NVIDIA — Intelligence 8.9 — $0.088/1M tok blendedNVIDIA Nemotron Nano 9B V2 (Reasoning) — NVIDIA — Intelligence 7.4 — $0.07/1M tok blendedNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) — NVIDIA — Intelligence 6.8 — $0.088/1M tok blendedNVIDIA Nemotron Nano 9B V2 (Non-reasoning) — NVIDIA — Intelligence 6.8 — $0.086/1M tok blendedNVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) — NVIDIA — Intelligence 5.8 — $0.30/1M tok blended

All NVIDIA models

ModelReleasedIn $/1MOut $/1MBlended IntelligenceCodingTok/s
Nemotron 3.5 Super VLNEW 2026-10-15 0.225 0.575 0.313 26.5 — 436
Nemotron 3 Ultra 550B A55B (Reasoning) 2026-06-04 0.60 2.70 1.125 22.9 49.3 140
Nemotron 3.5 Bolt 74B-A9BNEW 2026-10-15 — — — 21.4 — —
Nemotron 3.5 Lightning 2026-08-11 0.06 0.20 0.095 12.9 26.8 283
Nemotron 3 Super 120B A12B (Reasoning) 2026-03-11 0.30 0.90 0.45 12.8 37.7 —
Nemotron Cascade 2 30B A3B 2026-03-19 — — — 11.7 25.3 —
Nemotron 3 Nano Omni 30B A3B Reasoning 2026-04-29 0.40 1.365 0.641 10.3 13.8 234
Llama Nemotron Super 49B v1.5 (Reasoning) 2025-07-25 — — — 9.0 — —
Llama 3.3 Nemotron Super 49B v1 (Reasoning) 2025-03-18 — — — 8.9 — —
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) 2025-12-15 0.05 0.20 0.088 8.9 14.4 238
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) 2025-04-07 — — — 7.5 — —
NVIDIA Nemotron Nano 12B v2 VL (Reasoning) 2025-10-28 — — — 7.5 — —
Llama Nemotron Super 49B v1.5 (Non-reasoning) 2025-07-25 — — — 7.4 — —
NVIDIA Nemotron Nano 9B V2 (Reasoning) 2025-08-18 0.04 0.16 0.07 7.4 — 108
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) 2025-05-20 — — — 7.3 — —
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) 2025-03-18 — — — 7.3 — —
Llama 3.1 Nemotron Instruct 70B 2024-10-15 — — — 6.9 — —
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) 2025-12-15 0.05 0.20 0.088 6.8 — 229
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) 2025-08-18 0.05 0.195 0.086 6.8 — 164
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) 2025-10-28 0.20 0.60 0.30 5.8 — 202
NVIDIA Nemotron 3 Nano 4B 2026-03-16 — — — 4.8 8.0 —
Nemotron 3.5 Bolt E4B 4GB (Reasoning)NEW 2026-10-23 — — — — — —

Prices are NVIDIA's official list prices in USD per 1M tokens. See third-party resale listings for reseller prices from a public-marketplace snapshot — not official pricing. See the full model directory to compare across all providers.

See official free API tiers by developer