GitHub[195K]Try OpenCode

CompareAI models

  1. Llama 4 Scout 17B InstructMeta
  2. GPT-6 Astra (Fast)OpenAI
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Llama 4 Scout 17B Instruct0/100No data73/100100/10033/100No data
GPT-6 Astra (Fast)100/100No data2/10098/10050/100No data
Overview
Author
Context length
3.5M
1.1M
Reasoning
False
True
Input modalities
Text, Image
Text, Image, Pdf
Output modalities
Text
Text
Providers
Pricing
Input
$0.18/ 1M
$20/ 1M
Output
$0.59/ 1M
$100/ 1M
Cached input
Unknown
$2.00/ 1M
MomentumLast 2 mo
Unique users
No usage
No usage
Completed sessions
No usage
No usage
Token share
No usage
No usage
Tokens
No usage
No usage
No trend data
No trend data
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.