GitHub[208K]Try OpenCode

CompareAI models

  1. Command A TranslateCohereHollow points use fallbacks · hover for details
  2. Grok 4.6xAIHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Command A Translate0/100 — Reasoning not supported50/100 — No data; neutral placeholder19/1004/1000/10050/100 — Tool calling supported; no comparable benchmark
Grok 4.650/100 — Reasoning supported; no comparable benchmark38/10030/10072/10033/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
8K
500K
Reasoning
False
True
Input modalities
Text
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$2.50/ 1M
$2.00/ 1M
Output
$10/ 1M
$6.00/ 1M
Cached input
Unknown
$0.50/ 1M
MomentumLast 2 mo
Unique users
No usage
48K
Completed sessions
No usage
99,959
Token share
No usage
0.01%
Tokens
No usage
71B+100%
No trend data
AUG 2SEP 26
RetentionWeek 1
Returning users
Pending
51.8%1.8K user-weeks

Related comparisons. Other model pairs to check.