Price Per TokenPrice Per Token
Minimax
Minimax
vs
Minimax
Minimax

MiniMax M2.1 vs MiniMax M2.5

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

112 out of our 301 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

MiniMax M2.1 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Better at math
  • Has reasoning mode
  • Supports tool calls

MiniMax M2.5 wins:

  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
Price Advantage
MiniMax M2.1
Benchmark Advantage
MiniMax M2.5
Context Window
MiniMax M2.5
Speed
MiniMax M2.5

Pricing Comparison

Price Comparison

MetricMiniMax M2.1MiniMax M2.5Winner
Input (per 1M tokens)$0.27$0.30 MiniMax M2.1
Output (per 1M tokens)$0.95$1.20 MiniMax M2.1
Cache Read (per 1M)$30000.00$30000.00Tie
Using a 3:1 input/output ratio, MiniMax M2.1 is 16% cheaper overall.

MiniMax M2.1 Providers

Chutes $0.27 (Cheapest)
DeepInfra $0.27 (Cheapest)
AtlasCloud $0.29
SiliconFlow $0.29
Minimax $0.30

MiniMax M2.5 Providers

Minimax $0.30 (Cheapest)
Novita $0.30 (Cheapest)

Benchmark Comparison

6
Benchmarks Compared
0
MiniMax M2.1 Wins
3
MiniMax M2.5 Wins

Benchmark Scores

BenchmarkMiniMax M2.1MiniMax M2.5Winner
Intelligence Index
Overall intelligence score
39.542.0
Coding Index
Code generation & understanding
32.837.4
Math Index
Mathematical reasoning
82.7--
MMLU Pro
Academic knowledge
87.5--
GPQA
Graduate-level science
83.084.8
LiveCodeBench
Competitive programming
81.0--
MiniMax M2.1 shows stronger mathematical reasoning abilities.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
MiniMax M2.1
Other models

Context & Performance

Context Window

MiniMax M2.1
196,608
tokens
MiniMax M2.5
204,800
tokens
Max output: 131,072 tokens
MiniMax M2.5 has a 4% larger context window.

Speed Performance

MetricMiniMax M2.1MiniMax M2.5Winner
Tokens/second57.2 tok/s80.3 tok/s
Time to First Token2.20s1.52s
MiniMax M2.5 responds 40% faster on average.

Capabilities

Feature Comparison

FeatureMiniMax M2.1MiniMax M2.5
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyMiniMax M2.1MiniMax M2.5
LicenseProprietaryProprietary
AuthorMinimaxMinimax
ReleasedDec 2025Feb 2026

MiniMax M2.1 Modalities

Input
text
Output
text

MiniMax M2.5 Modalities

Input
text
Output
text

Related Comparisons

Compare MiniMax M2.1 with:

Compare MiniMax M2.5 with:

Frequently Asked Questions

MiniMax M2.1 has cheaper input pricing at $0.27/M tokens. MiniMax M2.1 has cheaper output pricing at $0.95/M tokens.
MiniMax M2.5 scores higher on coding benchmarks with a score of 37.4, compared to MiniMax M2.1's score of 32.8.
MiniMax M2.1 has a 196,608 token context window, while MiniMax M2.5 has a 204,800 token context window.
MiniMax M2.1 does not support vision. MiniMax M2.5 does not support vision.