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

Codestral 2508 vs Devstral 2 2512

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

Codestral 2508 wins:

  • No clear advantages in compared metrics

Devstral 2 2512 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
Price Advantage
Devstral 2 2512
Benchmark Advantage
Devstral 2 2512
Context Window
Devstral 2 2512
Speed
Devstral 2 2512

Pricing Comparison

Price Comparison

MetricCodestral 2508Devstral 2 2512Winner
Input (per 1M tokens)$0.30$0.05 Devstral 2 2512
Output (per 1M tokens)$0.90$0.22 Devstral 2 2512
Cache Read (per 1M)N/A$25000.00 Devstral 2 2512
Using a 3:1 input/output ratio, Devstral 2 2512 is 79% cheaper overall.

Codestral 2508 Providers

Mistral $0.30 (Cheapest)

Devstral 2 2512 Providers

Chutes $0.05 (Cheapest)
Mistral $0.40

Benchmark Comparison

7
Benchmarks Compared
0
Codestral 2508 Wins
0
Devstral 2 2512 Wins

Benchmark Scores

BenchmarkCodestral 2508Devstral 2 2512Winner
Intelligence Index
Overall intelligence score
-22.0-
Coding Index
Code generation & understanding
-23.7-
Math Index
Mathematical reasoning
-36.7-
MMLU Pro
Academic knowledge
-76.2-
GPQA
Graduate-level science
-59.4-
LiveCodeBench
Competitive programming
-44.8-
Aider
Real-world code editing
11.1--
Devstral 2 2512 significantly outperforms in coding benchmarks.

Cost vs Quality

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

Context & Performance

Context Window

Codestral 2508
256,000
tokens
Devstral 2 2512
262,144
tokens
Max output: 65,536 tokens
Devstral 2 2512 has a 2% larger context window.

Speed Performance

MetricCodestral 2508Devstral 2 2512Winner
Tokens/secondN/A73.8 tok/s
Time to First TokenN/A0.40s

Capabilities

Feature Comparison

FeatureCodestral 2508Devstral 2 2512
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyCodestral 2508Devstral 2 2512
LicenseOpen SourceOpen Source
AuthorMistral AIMistral AI
ReleasedAug 2025Dec 2025

Codestral 2508 Modalities

Input
text
Output
text

Devstral 2 2512 Modalities

Input
text
Output
text

Related Comparisons

Compare Codestral 2508 with:

Compare Devstral 2 2512 with:

Frequently Asked Questions

Devstral 2 2512 has cheaper input pricing at $0.05/M tokens. Devstral 2 2512 has cheaper output pricing at $0.22/M tokens.
Devstral 2 2512 scores higher on coding benchmarks with a score of 23.7, compared to Codestral 2508's score of N/A.
Codestral 2508 has a 256,000 token context window, while Devstral 2 2512 has a 262,144 token context window.
Codestral 2508 does not support vision. Devstral 2 2512 does not support vision.