tokevenGrokvsGrok
Grok 4.3 vs Grok 4.20 Non-Reasoning
Side-by-side comparison of pricing, task quality, and projected cost at higher scale.
Pricing
Side-by-side pricing
Grok 4.3
Mid-tierGrok 4.20 Non-Reasoning
Mid-tierInput $/MTok
$1.25
$1.25
Output $/MTok
$2.50
$2.50
Cache discount
84% off
84% off
Context
1,000K
1,000K
Quality
Task confidence comparison
Confidence score from zero to one hundred by task type, where higher is better.
Code Generation
0
vs
0
Code Review
0
vs
0
Summarization
0
vs
0
Q&A
0
vs
0
Extraction
0
vs
0
Reasoning
0
vs
0
Classification
0
vs
0
Creative Writing
0
vs
0
Grok 4.3
Grok 4.20 Non-Reasoning
Guidance
When to use Grok 4.3 vs Grok 4.20 Non-Reasoning
Choose Grok 4.3 when...
- Similar performance; consider provider preference or ecosystem fit.
Choose Grok 4.20 Non-Reasoning when...
- Similar performance; consider provider preference or ecosystem fit.
At scale
Cost at scale
Estimated cost assuming a seventy percent input and thirty percent output token split.
Grok 4.3
Grok 4.20 Non-Reasoning
100K tokens
$0.16
$0.16
1M tokens
$3.25
$3.25
10M tokens
$32.50
$32.50
FAQ
When should I use Grok 4.3 instead of Grok 4.20 Non-Reasoning?
Grok 4.3 and Grok 4.20 Non-Reasoning perform similarly across all tracked tasks. Pick based on pricing and provider preference.
Is Grok 4.20 Non-Reasoning cheaper than Grok 4.3?
Both models have the same input pricing at $1.25/MTok. Compare output pricing: $2.50 vs $2.50/MTok.
What are the context window sizes for Grok 4.3 and Grok 4.20 Non-Reasoning?
Grok 4.3 has a 1,000K token context window. Grok 4.20 Non-Reasoning has a 1,000K token context window.
Go deeper on either model
Per-call cost calculators, provider lineups, and price history for both models on this page.
Other comparisons
How Grok 4.3 and Grok 4.20 Non-Reasoning stack up against the rest of the field.
Track your real costs
Comparisons show estimated costs at list price. The dashboard reveals your real spend and savings.