NVIDIA · Updated 4 November 2026

Nemotron 3 Ultra 550B A55B

Intelligence
12 · 43rd of 54
Coding
Not scored yet
Price per 1M tokens
$1.13 blended · $0.60 input · $2.70 output
Output speed
161 tok/s
Time to first token
0.9 s
Context window
262K tokens
Open weights
Yes
Released
4 June 2026

How it compares

#ModelIntelligenceCodingPrice / 1M tokensSpeedContext
1Nemotron 3 Ultra 550B A55B NVIDIA · open weights12—$1.13161 tok/s262K
2Gemini 4 Carbon Google60—$8.0092 tok/s—
3Inkling Small Thinking Machines · open weights13—$0.53201 tok/s524K
4Inkling Thinking Machines · open weights13—$1.76196 tok/s524K
5Gemini 3.5 Flash-Lite Google12—$0.85374 tok/s1M
6MiMo-V2.6-Flash Xiaomi · open weights27—$0.1730 tok/s1.1M

Cheaper alternative within 3 points: MiMo-V2.6-Flash at $0.17 per million tokens.

Data: Artificial Analysis (intelligence and coding indexes, prices, speed) and OpenRouter (open weights, context windows). Updated 4 November 2026; refreshed every 6 hours.

More rankings