Mercury 2 vs MiniMax M3

API pricing, context window and capabilities for Mercury 2 and MiniMax M3, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

MiniMax M3 wins on coding, on intelligence and on context window.

Price
Tied
Coding
MiniMax M3
Intelligence
MiniMax M3
Context window
MiniMax M3

Key takeaways

who wins on what, from the published numbers

Mercury 2 wins

  • Cheaper output ($0.75 vs $0.96 /1M)

MiniMax M3 wins

  • Cheaper input ($0.25 vs $0.23 /1M)
  • Larger context window (128K vs 1M)
  • Higher max output (50K vs 524K)
  • More serving providers (2 vs 8)
  • Supports vision
  • Has reasoning mode
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
MiniMax M3
1M
More providers
MiniMax M3
8 providers

Pricing & specs

cheapest serving route · per 1M tokens
Mercury 2MiniMax M3
Input $/1M$0.25 $0.23 best
Output $/1M$0.75 best$0.96
Context window128K 1M best
Max output50K 524K best
Serving providers2 8 best
Released2026-02-24 2026-06-01

Benchmarks

Artificial Analysis indices, side by side
Mercury 2MiniMax M3
Intelligence21.9 45.4 best
Coding31.1 58.6 best
GPQA Diamond77% 93% best
Output speed939 t/s best108 t/s
Latency (TTFT)3.44s 1.08s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Mercury 2
via Inception
$2.00
MiniMax M3
via Wandb
$2.11

Capabilities

feature support, side by side
FeatureMercury 2MiniMax M3
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Mercury 2 or MiniMax M3?
MiniMax M3 is cheaper for input ($0.25 vs $0.23 per 1M tokens). Mercury 2 is cheaper for output ($0.75 vs $0.96 per 1M tokens).
What is the context window difference between Mercury 2 and MiniMax M3?
Mercury 2 has a 128K-token context window and MiniMax M3 has 1M tokens, so MiniMax M3 can take a larger prompt.
How do Mercury 2 and MiniMax M3 compare on benchmarks?
On the tracked Artificial Analysis indices, MiniMax M3 leads on coding, and MiniMax M3 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