Mercury 2 vs MiniMax M2.7

API pricing, context window and capabilities for Mercury 2 and MiniMax M2.7, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

MiniMax M2.7 wins on intelligence and on context window. Benchmark data is unavailable for one or both models.

Price
Tied
Coding
Not called
Intelligence
MiniMax M2.7
Context window
MiniMax M2.7

Key takeaways

who wins on what, from the published numbers

Mercury 2 wins

  • Cheaper input ($0.25 vs $0.26 /1M)
  • Supports prompt caching
  • Supports structured output

MiniMax M2.7 wins

  • Cheaper output ($0.75 vs $0.55 /1M)
  • Larger context window (128K vs 1M)
  • Higher max output (50K vs 1M)
  • More serving providers (1 vs 2)
  • Has reasoning mode
Cheaper overall
MiniMax M2.7
$0.26 + $0.55 /1M
Larger context
MiniMax M2.7
1M
More providers
MiniMax M2.7
2 providers

Pricing & specs

cheapest serving route · per 1M tokens
Mercury 2MiniMax M2.7
Input $/1M$0.25 best$0.26
Output $/1M$0.75 $0.55 best
Context window128K 1M best
Max output50K 1M best
Serving providers1 2 best
Released2026-02-24 2026-03-18

Benchmarks

Artificial Analysis indices, side by side
Mercury 2MiniMax M2.7
Intelligence25.3 38.1 best
CodingNot available 52.6
GPQA Diamond77% 87% best
Output speed602 t/s best59 t/s
Latency (TTFT)2.73s best5.53s

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Mercury 2
via Inception
$2.00
MiniMax M2.7
via Pinstripes
$1.82

Capabilities

feature support, side by side
FeatureMercury 2MiniMax M2.7
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Mercury 2 or MiniMax M2.7?
Mercury 2 is cheaper for input ($0.25 vs $0.26 per 1M tokens). MiniMax M2.7 is cheaper for output ($0.75 vs $0.55 per 1M tokens).
What is the context window difference between Mercury 2 and MiniMax M2.7?
Mercury 2 has a 128K-token context window and MiniMax M2.7 has 1M tokens, so MiniMax M2.7 can take a larger prompt.
How do Mercury 2 and MiniMax M2.7 compare on benchmarks?
On the tracked Artificial Analysis indices, MiniMax M2.7 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