Price Per TokenPrice Per Token
Minimax
Minimax
vs
Mistral AI
Mistral AI

MiniMax M2.5 vs Mistral Medium 3

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 M2.5 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
  • Higher intelligence benchmark
  • Better at coding

Mistral Medium 3 wins:

  • Faster response time
  • Better at math
  • Supports vision
  • Supports tool calls
Price Advantage
MiniMax M2.5
Benchmark Advantage
MiniMax M2.5
Context Window
MiniMax M2.5
Speed
Mistral Medium 3

Pricing Comparison

Price Comparison

MetricMiniMax M2.5Mistral Medium 3Winner
Input (per 1M tokens)$0.20$0.40 MiniMax M2.5
Output (per 1M tokens)$1.00$2.00 MiniMax M2.5
Using a 3:1 input/output ratio, MiniMax M2.5 is 50% cheaper overall.

MiniMax M2.5 Providers

SiliconFlow $0.20 (Cheapest)
Minimax $0.30
AtlasCloud $0.30
Fireworks $0.30
Novita $0.30

Mistral Medium 3 Providers

Mistral $0.40 (Cheapest)

Benchmark Comparison

7
Benchmarks Compared
3
MiniMax M2.5 Wins
0
Mistral Medium 3 Wins

Benchmark Scores

BenchmarkMiniMax M2.5Mistral Medium 3Winner
Intelligence Index
Overall intelligence score
42.018.7
Coding Index
Code generation & understanding
37.413.6
Math Index
Mathematical reasoning
-30.3-
MMLU Pro
Academic knowledge
-76.0-
GPQA
Graduate-level science
84.857.8
LiveCodeBench
Competitive programming
-40.0-
AIME
Competition math
-44.0-
MiniMax M2.5 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Other models

Context & Performance

Context Window

MiniMax M2.5
196,608
tokens
Max output: 131,072 tokens
Mistral Medium 3
131,072
tokens
MiniMax M2.5 has a 33% larger context window.

Speed Performance

MetricMiniMax M2.5Mistral Medium 3Winner
Tokens/second57.3 tok/s90.5 tok/s
Time to First Token2.30s0.38s
Mistral Medium 3 responds 58% faster on average.

Capabilities

Feature Comparison

FeatureMiniMax M2.5Mistral Medium 3
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyMiniMax M2.5Mistral Medium 3
LicenseProprietaryProprietary
AuthorMinimaxMistral AI
ReleasedFeb 2026May 2025

MiniMax M2.5 Modalities

Input
text
Output
text

Mistral Medium 3 Modalities

Input
textimage
Output
text

Related Comparisons

Compare MiniMax M2.5 with:

Compare Mistral Medium 3 with:

Frequently Asked Questions

MiniMax M2.5 has cheaper input pricing at $0.20/M tokens. MiniMax M2.5 has cheaper output pricing at $1.00/M tokens.
MiniMax M2.5 scores higher on coding benchmarks with a score of 37.4, compared to Mistral Medium 3's score of 13.6.
MiniMax M2.5 has a 196,608 token context window, while Mistral Medium 3 has a 131,072 token context window.
MiniMax M2.5 does not support vision. Mistral Medium 3 supports vision.