Models

NVIDIA-Nemotron-3-Ultra-550B-A55B

deepinfra · 262K ctx · 2 providers · updated 2026-09-12 05:16 UTC

Cheapest
$0.925 Official list · DeepInfra
Avg price
$1.09 /1M
providers
2
(3 × $0.500 + $2.20) ÷ 4 = $0.925/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.500, 3:1 $0.925, 1:1 $1.35, output only $2.20 per 1M.

The board shows this model's cheapest measured offer ($0.925/1M); the smaller figure under it is the mean of the 2 offers listed below ($1.09/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
deepinfra Pricebook (LiteLLM) ↗ $0.500$2.20 — — — Official list
wandb Pricebook (LiteLLM) ↗ $0.750$2.75 — — — Official list

Price trend

Cheapest blended price, last 16 days (USD/1M): $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925 → $0.925

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/nvidia-nemotron-3-ultra-550b-a55b.json. Free reuse requires attribution to tkx.org.

FAQ

How much does NVIDIA-Nemotron-3-Ultra-550B-A55B cost?

Cheapest measured offer right now: $0.5/1M input, $2.2/1M output via deepinfra — across 2 tracked providers, refreshed hourly.

Who serves NVIDIA-Nemotron-3-Ultra-550B-A55B?

2 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

Is the price of NVIDIA-Nemotron-3-Ultra-550B-A55B going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings