GitHub[208K]Try OpenCode

CompareAI models

  1. DeepSeek V4.1 FlashDeepSeek
  2. nemotron-3-ultraNvidiaHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4.1 Flash100/100100/10063/10080/10033/10092/100
nemotron-3-ultra50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder50/100 — No data; neutral placeholder
Overview
Author
Context length
1M
Unknown
Reasoning
True
Unknown
Input modalities
Text, Image
Unknown
Output modalities
Text
Unknown
Providers
Pricing
Input
$0.27/ 1M
Unknown
Output
$1.08/ 1M
Unknown
Cached input
$0.0054/ 1M
Unknown
MomentumLast 2 mo
Unique users
1.1M
427K
Completed sessions
18,969,853
6,533,799
Token share
14.9%
2.51%
Tokens
129T+100%
22T+2,928%
AUG 6SEP 30
AUG 6SEP 30
RetentionWeek 1
Returning users
58.4%102K user-weeks
Pending

Related comparisons. Other model pairs to check.