GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V4 ProDeepSeek
  2. GPT-6 AstraOpenAI
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/10087/10036/10081/1000/10044/100
GPT-6 Astra100/100No data4/10098/10050/100No data
Overview
Author
Context length
1M
1.1M
Reasoning
True
True
Input modalities
Text
Text, Image, Pdf
Output modalities
Text
Text
Providers
Pricing
Input
$1.32/ 1M
$10/ 1M
Output
$3.96/ 1M
$50/ 1M
Cached input
$0.04/ 1M
$1.00/ 1M
MomentumLast 2 mo
Unique users
1.5M
No usage
Completed sessions
2,839,428
No usage
Token share
6%
No usage
Tokens
29T+18%
No usage
JUL 11SEP 4
No trend data
RetentionWeek 1
Returning users
65.2%137K user-weeks
Pending

Related comparisons. Other model pairs to check.