GitHub[208K]Try OpenCode

CompareAI models

  1. DeepSeek V4 ProDeepSeek
  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 Pro100/100100/10037/10080/1000/10068/100
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
$1.74/ 1M
$0.05/ 1M
Output
$3.48/ 1M
$0.20/ 1M
Cached input
$0.20/ 1M
$0.01/ 1M
MomentumLast 2 mo
Unique users
1.1M
257K
Completed sessions
1,743,388
4,619,932
Token share
2.47%
0.51%
Tokens
20T-32%
4T+100%
AUG 1SEP 25
AUG 1SEP 25
RetentionWeek 1
Returning users
60.7%104K user-weeks
Pending

Related comparisons. Other model pairs to check.