← Model list

Nemotron 3 Ultra 550B (DeepInfra)

nvidia·nvidia/nemotron-3-ultra-550b·GA·Closed·nemotron series·NEW

Nemotron multimodal model for visual reasoning and agentic AI workflows

At a glance
Reference price$0.50 / $2.20 per 1M
Cache read $0.10 · LLM Gateway
Lowest paid$0.50 / $2.20
LLM Gateway Gateway
Context262,144
Output limit262,144
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
TextImage
Knowledge cutoff
Released / updated2026-06-01 / 2026-06-01

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
LLM GatewayGateway$0.50$2.20$0.10262,144262,144

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

1LLM Gateway$162.00
The cheapest paid channel is the only channel.

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.75$02026-08-132026-08-212026-08-13 · Input list $0.752026-08-21 · Input list $0.502026-08-13 · Output list $2.752026-08-21 · Output list $2.202026-08-13 · Min blended $1.052026-08-21 · Min blended $0.925