LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Nemotron 3 Nano Omni 30B A3B Reasoning

nvidia·nvidia/nemotron-3-nano-omni-30b-a3b-reasoning·Deprecated·Open weights·nemotron series
Open Nemotron omni model combining reasoning with text, vision, and audio

Nemotron 3 Nano Omni 30B A3B Reasoning by nvidia is offered by 5 providers on this page. Public prices are shown for 4 of them. Its reference price is $0.30 per 1M input tokens and $1.83 per 1M output tokens. The lowest paid channel is NanoGPT at $0.105 / $0.42 per 1M, about 2.9× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 15 on the Intelligence Index, with 13.8 for coding. Against its lowest blended price of $0.184 per 1M, that is roughly 82 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 328 tokens per second, with 1.01s to the first token.

The context window is 256,000 tokens at the reference host, but hosts report different limits, from 131,072 to 262,144, so the usable window depends on the provider you pick. It supports reasoning and tool use. Accepted input modalities are Text, Image, Video, and Audio. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-05.

Specs & pricing

Input / output per 1M tokens
Reference price·Crusoe
$0.30 / $1.83
Blended $0.682 · Cache read $0.30
Lowest paid·NanoGPTGateway
$0.105 / $0.42
Blended $0.184 · 2.9× spread
1 more $0 channels
Context
256,000
Output limit
65,536
Knowledge cutoff
2025-05
Released / updated
2026-04-28 / 2026-04-28
Capabilities
✓ Reasoning✓ Tool useStructured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoAudio

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence15
Value82
Coding13.8
Agentic—
Output speed328 tok/s
TTFT1.01 s
Value formulaIQ 15 ÷ min blended $0.184 = 82

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 5 providers4 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
RequestyGatewayFree——131,072 ⚠20,480
NanoGPTGateway$0.105$0.42$0.052—256,00065,536
Vultr
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Cloud$0.13$0.38——262,144 ⚠131,072
Deep Infra
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Cloud$0.20$0.80——262,144 ⚠65,536deprecated
Crusoe
nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B
Gateway$0.30$1.83$0.30—256,00065,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1NanoGPT$35.70
2Vultr$45.00
3Deep Infra$80.00
4Crusoe$151.50

1 more channels offer $0 (Requesty); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokensToggle (on / off)

3 / 5 providers expose no reasoning control (reasoning_options: []).

Related models

nemotron-lightning-3.5-30b-a3bsame series$0.05 / $0.20Nemotron 3.5 Lightning 30B A3Bsame series$0 / $0Nemotron 3.5 Lightning Freesame series$0 / $0DeepSeek V4 Flashcheaper alternative$0.14 / $0.28GLM-5.3-Flashcheaper alternative$0.075 / $0.25GPT-5 Nanocheaper alternative$0.05 / $0.40MiMo-V2.5cheaper alternative$0.14 / $0.28

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.83$02026-08-052026-09-082026-08-05 · Input list $0.132026-08-06 · Input list $0.132026-08-07 · Input list $0.132026-08-08 · Input list $0.132026-08-09 · Input list $0.132026-08-10 · Input list $0.132026-08-11 · Input list $0.132026-08-12 · Input list $0.132026-08-13 · Input list $0.202026-08-14 · Input list $0.302026-09-05 · Input list $0.302026-09-08 · Input list $0.302026-08-05 · Output list $0.382026-08-06 · Output list $0.382026-08-07 · Output list $0.382026-08-08 · Output list $0.382026-08-09 · Output list $0.382026-08-10 · Output list $0.382026-08-11 · Output list $0.382026-08-12 · Output list $0.382026-08-13 · Output list $0.802026-08-14 · Output list $1.832026-09-05 · Output list $1.832026-09-08 · Output list $1.832026-08-05 · Min blended $0.1842026-08-06 · Min blended $0.1842026-08-07 · Min blended $0.1842026-08-08 · Min blended $0.1842026-08-09 · Min blended $0.1032026-08-10 · Min blended $0.1032026-08-11 · Min blended $0.1032026-08-12 · Min blended $0.1032026-08-13 · Min blended $0.352026-08-14 · Min blended $0.352026-09-05 · Min blended $0.1032026-09-08 · Min blended $0.184
Data partly from models.dev (MIT) · Crusoe official docs ↗