Price Per TokenPrice Per Token
Minimax
vs
Mistral AI
Mistral AI

MiniMax M2 vs Ministral 3 8B 2512

A detailed comparison of pricing, benchmarks, and capabilities

Sponsor Price Per Token Reach 5000+ developers comparing LLM APIs

125 out of our 298 tracked models have had a price change in January.

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

Key Takeaways

MiniMax M2 wins:

  • Higher intelligence benchmark
  • Better at coding
  • Better at math
  • Has reasoning mode

Ministral 3 8B 2512 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
  • Faster response time
  • Supports vision
Price Advantage
Ministral 3 8B 2512
Benchmark Advantage
MiniMax M2
Context Window
Ministral 3 8B 2512
Speed
Ministral 3 8B 2512

Pricing Comparison

Price Comparison

MetricMiniMax M2Ministral 3 8B 2512Winner
Input (per 1M tokens)$0.20$0.15 Ministral 3 8B 2512
Output (per 1M tokens)$1.00$0.15 Ministral 3 8B 2512
Cache Read (per 1M)$30000.00N/A MiniMax M2
Using a 3:1 input/output ratio, Ministral 3 8B 2512 is 63% cheaper overall.

MiniMax M2 Providers

AtlasCloud $0.20 (Cheapest)
DeepInfra $0.25
Minimax $0.26
Google $0.30
Novita $0.30

Ministral 3 8B 2512 Providers

Mistral $0.15 (Cheapest)

Benchmark Comparison

6
Benchmarks Compared
6
MiniMax M2 Wins
0
Ministral 3 8B 2512 Wins

Benchmark Scores

BenchmarkMiniMax M2Ministral 3 8B 2512Winner
Intelligence Index
Overall intelligence score
36.015.2
Coding Index
Code generation & understanding
29.210.0
Math Index
Mathematical reasoning
78.331.7
MMLU Pro
Academic knowledge
82.064.2
GPQA
Graduate-level science
77.747.1
LiveCodeBench
Competitive programming
82.630.3
MiniMax M2 significantly outperforms in coding benchmarks.

Cost vs Quality

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

Context & Performance

Context Window

MiniMax M2
196,608
tokens
Max output: 65,536 tokens
Ministral 3 8B 2512
262,144
tokens
Ministral 3 8B 2512 has a 25% larger context window.

Speed Performance

MetricMiniMax M2Ministral 3 8B 2512Winner
Tokens/second75.6 tok/s197.4 tok/s
Time to First Token1.31s0.27s
Ministral 3 8B 2512 responds 161% faster on average.

Capabilities

Feature Comparison

FeatureMiniMax M2Ministral 3 8B 2512
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyMiniMax M2Ministral 3 8B 2512
LicenseProprietaryOpen Source
AuthorMinimaxMistral AI
ReleasedOct 2025Dec 2025

MiniMax M2 Modalities

Input
text
Output
text

Ministral 3 8B 2512 Modalities

Input
textimage
Output
text

Related Comparisons

Compare MiniMax M2 with:

Compare Ministral 3 8B 2512 with:

Frequently Asked Questions

Ministral 3 8B 2512 has cheaper input pricing at $0.15/M tokens. Ministral 3 8B 2512 has cheaper output pricing at $0.15/M tokens.
MiniMax M2 scores higher on coding benchmarks with a score of 29.2, compared to Ministral 3 8B 2512's score of 10.0.
MiniMax M2 has a 196,608 token context window, while Ministral 3 8B 2512 has a 262,144 token context window.
MiniMax M2 does not support vision. Ministral 3 8B 2512 supports vision.