Grok 4 20 Non Reasoning vs Grok 4.3

API pricing, context window and capabilities for Grok 4 20 Non Reasoning and Grok 4.3, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

Grok 4 20 Non Reasoning wins on context window. Grok 4.3 wins on price and on intelligence. Benchmark data is unavailable for one or both models.

Price
Grok 4.3
Coding
Not called
Intelligence
Grok 4.3
Context window
Grok 4 20 Non Reasoning

Key takeaways

who wins on what, from the published numbers

Grok 4 20 Non Reasoning wins

  • Larger context window (2M vs 1M)
  • Higher max output (2M vs 1M)

Grok 4.3 wins

  • Cheaper input ($2.00 vs $1.25 /1M)
  • Cheaper output ($6.00 vs $2.50 /1M)
  • Has reasoning mode
  • Supports prompt caching
Cheaper overall
Grok 4.3
$1.25 + $2.50 /1M
Larger context
Grok 4 20 Non Reasoning
2M
More providers
Tied

Pricing & specs

cheapest serving route · per 1M tokens
Grok 4 20 Non ReasoningGrok 4.3
Input $/1M$2.00 $1.25 best
Output $/1M$6.00 $2.50 best
Context window2M best1M
Max output2M best1M
Serving providers1 1
Released2026-03-09 2026-04-18

Benchmarks

Artificial Analysis indices, side by side
Grok 4 20 Non ReasoningGrok 4.3
Intelligence21.8 37.6 best
CodingNot available 42.3
GPQA Diamond78% 90% best
Output speed163 t/s best113 t/s
Latency (TTFT)4.54s best17.26s

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Grok 4 20 Non Reasoning
via Vertex AI
$16
Grok 4.3
via xAI
$8.75

Capabilities

feature support, side by side
FeatureGrok 4 20 Non ReasoningGrok 4.3
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Grok 4 20 Non Reasoning or Grok 4.3?
Grok 4.3 is cheaper for input ($2.00 vs $1.25 per 1M tokens). Grok 4.3 is cheaper for output ($6.00 vs $2.50 per 1M tokens).
What is the context window difference between Grok 4 20 Non Reasoning and Grok 4.3?
Grok 4 20 Non Reasoning has a 2M-token context window and Grok 4.3 has 1M tokens, so Grok 4 20 Non Reasoning can take a larger prompt.
How do Grok 4 20 Non Reasoning and Grok 4.3 compare on benchmarks?
On the tracked Artificial Analysis indices, Grok 4.3 leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI