CtrlAltDebrief

GPT-5.5 vs Mercury 2

API pricing, context window and capabilities for GPT-5.5 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

GPT-5.5 wins on intelligence and on context window. Mercury 2 wins on price. Benchmark data is unavailable for one or both models.

Price
Mercury 2
Coding
Not called
Intelligence
GPT-5.5
Context window
GPT-5.5

Key takeaways

who wins on what, from the published numbers

GPT-5.5 wins

  • Larger context window (1.1M vs 128K)
  • Higher max output (128K vs 50K)
  • More serving providers (2 vs 1)
  • Supports vision
  • Has reasoning mode
  • Has web search

Mercury 2 wins

  • Cheaper input ($5.00 vs $0.25 /1M)
  • Cheaper output ($30.00 vs $0.75 /1M)
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
GPT-5.5
1.1M
More providers
GPT-5.5
2 providers

Pricing & specs

cheapest serving route · per 1M tokens
GPT-5.5Mercury 2
Input $/1M$5.00 $0.25 best
Output $/1M$30.00 $0.75 best
Context window1.1M best128K
Max output128K best50K
Serving providers2 best1
Released2026-04-23 2026-02-24

Benchmarks

Artificial Analysis indices, side by side
GPT-5.5Mercury 2
Intelligence54.8 best25.3
Coding74.9 Not available
GPQA Diamond94% best77%
Output speed87 t/s 602 t/s best
Latency (TTFT)23.21s 2.73s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
GPT-5.5
via Azure
$55
Mercury 2
via Inception
$2.00

Capabilities

feature support, side by side
FeatureGPT-5.5Mercury 2
Vision✓—
Tool use✓✓
Reasoning✓—
Audio——
Prompt caching✓✓
Structured output✓✓
Web search✓—

Related comparisons

Frequently asked questions

Which is cheaper, GPT-5.5 or Mercury 2?
Mercury 2 is cheaper for input ($5.00 vs $0.25 per 1M tokens). Mercury 2 is cheaper for output ($30.00 vs $0.75 per 1M tokens).
What is the context window difference between GPT-5.5 and Mercury 2?
GPT-5.5 has a 1.1M-token context window and Mercury 2 has 128K tokens, so GPT-5.5 can take a larger prompt.
How do GPT-5.5 and Mercury 2 compare on benchmarks?
On the tracked Artificial Analysis indices, GPT-5.5 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