LLM Leaderboard
Nemotron 3 Ultra
by NVIDIA Reasoning
RunFree Score
—
insufficient data
Blended price
$0.93
per 1M tokens
Context
1M
tokens
Max output
16K
tokens
Output speed
—
tokens / sec
Latency (TTFT)
—
first token
Uptime
95.9%
last 24h
Providers
3
serving this model
Capability profile
Not enough categorised benchmark data to chart a profile yet.
Compare Nemotron 3 Ultra
See it side by side with any other model — benchmarks, price and specs.
Benchmark results
We don't have verified public benchmark results for Nemotron 3 Ultra yet. We only publish scores with a primary source — no estimates.
Every score links to its original source. See our methodology for how the RunFree Score is computed.
API pricing
- Input
- $0.50 / 1M
- Output
- $2.20 / 1M
- Cached input
- $0.10 / 1M
- Blended (3:1)
- $0.93 / 1M
Specifications
- Provider
- NVIDIA
- Context window
- 1M
- Max output
- 16K
- Reasoning model
- Yes
- Modality
- text
- Released
- Jun 4, 2026