CtrlAltDebrief

Claude Opus 4.8 vs Mercury 2

API pricing, context window and capabilities for Claude Opus 4.8 and Mercury 2, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.

Verdict

computed from the published numbers

Claude Opus 4.8 wins on Terminal-Bench, on intelligence and on context window. Mercury 2 wins on price.

Price
Mercury 2
Terminal-Bench
Claude Opus 4.8
Intelligence
Claude Opus 4.8
Context window
Claude Opus 4.8

Key takeaways

who wins on what, from the published numbers

Claude Opus 4.8 wins

  • Larger context window (1M vs 128K)
  • Higher max output (128K vs 50K)
  • More serving providers (8 vs 3)
  • Supports vision
  • Has reasoning mode
  • Has web search

Mercury 2 wins

  • Cheaper input ($5.00 vs $0.25 /1M)
  • Cheaper output ($25.00 vs $0.75 /1M)
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
Claude Opus 4.8
1M
More providers
Claude Opus 4.8
8 providers

Pricing & specs

cheapest listed route · per 1M tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower.
Claude Opus 4.8Mercury 2
Input $/1M$5.00via Anthropic $0.25via Inception best
Output $/1M$25.00via Anthropic $0.75via Inception best
Context window1M best128K
Max output128K best50K
Serving providers8 best3
DateReleased May 28, 2026 Released Feb 24, 2026

Benchmarks

Benchmark scores, side by side
Claude Opus 4.8Mercury 2
Intelligence41.8 best13.8
Terminal-Bench85% best27%
GPQA Diamond92% best77%
Output speed62 t/s 554 t/s best
Latency (TTFT)56.16s 6.83s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Claude Opus 4.8
via Azure
$50
Mercury 2
via Inception
$2.00

Capabilities

feature support, side by side
FeatureClaude Opus 4.8Mercury 2
Vision✓—
Tool use✓✓
Reasoning✓—
Audio——
Prompt caching✓✓
Structured output✓✓
Web search✓—

Related comparisons

Frequently asked questions

Which is cheaper, Claude Opus 4.8 or Mercury 2?
Mercury 2 is cheaper for input ($5.00 vs $0.25 per 1M tokens) from Inception. Mercury 2 is cheaper for output ($25.00 vs $0.75 per 1M tokens) from Inception.
What is the context window difference between Claude Opus 4.8 and Mercury 2?
Claude Opus 4.8 has a 1M-token context window and Mercury 2 has 128K tokens, so Claude Opus 4.8 can take a larger prompt.
How do Claude Opus 4.8 and Mercury 2 compare on benchmarks?
On the tracked benchmarks, Claude Opus 4.8 leads on Terminal-Bench, and Claude Opus 4.8 leads on intelligence.
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI