CtrlAltDebrief

Grok 4.3 vs Mercury 2

API pricing, context window and capabilities for Grok 4.3 and Mercury 2, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

Grok 4.3 wins on coding, on intelligence and on context window. Mercury 2 wins on price.

Price
Mercury 2
Coding
Grok 4.3
Intelligence
Grok 4.3
Context window
Grok 4.3

Key takeaways

who wins on what, from the published numbers

Grok 4.3 wins

  • Larger context window (1M vs 128K)
  • Higher max output (1M vs 50K)
  • More serving providers (3 vs 2)
  • Supports vision
  • Has reasoning mode
  • Has web search

Mercury 2 wins

  • Cheaper input ($1.25 vs $0.25 /1M)
  • Cheaper output ($2.50 vs $0.75 /1M)
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
Grok 4.3
1M
More providers
Grok 4.3
3 providers

Pricing & specs

cheapest serving route · per 1M tokens
Grok 4.3Mercury 2
Input $/1M$1.25 $0.25 best
Output $/1M$2.50 $0.75 best
Context window1M best128K
Max output1M best50K
Serving providers3 best2
Released2026-04-18 2026-02-24

Benchmarks

Artificial Analysis indices, side by side
Grok 4.3Mercury 2
Intelligence38.0 best21.9
Coding42.3 best31.1
GPQA Diamond90% best77%
Output speed123 t/s 939 t/s best
Latency (TTFT)21.45s 3.44s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Grok 4.3
via Azure
$8.75
Mercury 2
via Inception
$2.00

Capabilities

feature support, side by side
FeatureGrok 4.3Mercury 2
Vision✓—
Tool use✓✓
Reasoning✓—
Audio——
Prompt caching✓✓
Structured output✓✓
Web search✓—

Related comparisons

Frequently asked questions

Which is cheaper, Grok 4.3 or Mercury 2?
Mercury 2 is cheaper for input ($1.25 vs $0.25 per 1M tokens). Mercury 2 is cheaper for output ($2.50 vs $0.75 per 1M tokens).
What is the context window difference between Grok 4.3 and Mercury 2?
Grok 4.3 has a 1M-token context window and Mercury 2 has 128K tokens, so Grok 4.3 can take a larger prompt.
How do Grok 4.3 and Mercury 2 compare on benchmarks?
On the tracked Artificial Analysis indices, Grok 4.3 leads on coding, and 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