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

MiniMax M2.5 vs Codestral 2508

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:

  • Faster response time
  • Higher intelligence benchmark
  • Better at coding

Codestral 2508 wins:

  • Cheaper output tokens
  • Larger context window
  • Supports tool calls
Price Advantage
Codestral 2508
Benchmark Advantage
MiniMax M2.5
Context Window
Codestral 2508
Speed
MiniMax M2.5

Pricing Comparison

Price Comparison

MetricMiniMax M2.5Codestral 2508Winner
Input (per 1M tokens)$0.30$0.30Tie
Output (per 1M tokens)$1.20$0.90 Codestral 2508
Cache Read (per 1M)$30000.00N/A MiniMax M2.5
Using a 3:1 input/output ratio, Codestral 2508 is 14% cheaper overall.

MiniMax M2.5 Providers

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

Codestral 2508 Providers

Mistral $0.30 (Cheapest)

Benchmark Comparison

4
Benchmarks Compared
0
MiniMax M2.5 Wins
0
Codestral 2508 Wins

Benchmark Scores

BenchmarkMiniMax M2.5Codestral 2508Winner
Intelligence Index
Overall intelligence score
42.0--
Coding Index
Code generation & understanding
37.4--
GPQA
Graduate-level science
84.8--
Aider
Real-world code editing
-11.1-
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
204,800
tokens
Max output: 131,072 tokens
Codestral 2508
256,000
tokens
Codestral 2508 has a 20% larger context window.

Speed Performance

MetricMiniMax M2.5Codestral 2508Winner
Tokens/second71.0 tok/sN/A
Time to First Token1.67sN/A

Capabilities

Feature Comparison

FeatureMiniMax M2.5Codestral 2508
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyMiniMax M2.5Codestral 2508
LicenseProprietaryOpen Source
AuthorMinimaxMistral AI
ReleasedFeb 2026Aug 2025

MiniMax M2.5 Modalities

Input
text
Output
text

Codestral 2508 Modalities

Input
text
Output
text

Related Comparisons

Compare MiniMax M2.5 with:

Compare Codestral 2508 with:

Frequently Asked Questions

MiniMax M2.5 has cheaper input pricing at $0.30/M tokens. Codestral 2508 has cheaper output pricing at $0.90/M tokens.
MiniMax M2.5 scores higher on coding benchmarks with a score of 37.4, compared to Codestral 2508's score of N/A.
MiniMax M2.5 has a 204,800 token context window, while Codestral 2508 has a 256,000 token context window.
MiniMax M2.5 does not support vision. Codestral 2508 does not support vision.