GitHub[208K]Try OpenCode

CompareAI models

  1. DeepSeek V4 FlashDeepSeek
  2. Nemotron 3.5 Lightning 30B A3BNvidiaHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash26/10075/10063/10080/1000/1000/100
Nemotron 3.5 Lightning 30B A3B0/10037/10087/10061/1000/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
1M
262K
Reasoning
True
True
Input modalities
Text
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.27/ 1M
$0.05/ 1M
Output
$1.08/ 1M
$0.20/ 1M
Cached input
$0.0054/ 1M
$0.01/ 1M
MomentumLast 2 mo
Unique users
4.4M
260K
Completed sessions
38,167,084
4,725,981
Token share
37.2%
0.5%
Tokens
301T+162%
4T+100%
AUG 2SEP 26
AUG 2SEP 26
RetentionWeek 1
Returning users
67.6%486K user-weeks
Pending

Related comparisons. Other model pairs to check.