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

Codestral 2508 vs Kimi K2 Thinking

A detailed comparison of pricing, benchmarks, and capabilities

Track Your LLM Costs Across Every Provider Broken down by user, feature, and endpoint

107 out of our 483 tracked models have had a price change in March.

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

Key Takeaways

Codestral 2508 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window

Kimi K2 Thinking wins:

  • Has reasoning mode
Price Advantage
Codestral 2508
Benchmark Advantage
Codestral 2508
Context Window
Codestral 2508
Speed
N/A

Pricing Comparison

Price Comparison

MetricCodestral 2508Kimi K2 ThinkingWinner
Input (per 1M tokens)$0.30$0.47 Codestral 2508
Output (per 1M tokens)$0.90$2.00 Codestral 2508
Cache Read (per 1M)N/A$0.14 Kimi K2 Thinking
Using a 3:1 input/output ratio, Codestral 2508 is 47% cheaper overall.

Codestral 2508 Providers

No provider data available

Kimi K2 Thinking Providers

No provider data available

Benchmark Comparison

1
Benchmarks Compared
0
Codestral 2508 Wins
0
Kimi K2 Thinking Wins

Benchmark Scores

BenchmarkCodestral 2508Kimi K2 ThinkingWinner
Aider
Real-world code editing
11.1--
Both models show comparable benchmark performance.

Cost vs Quality

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

Context & Performance

Context Window

Codestral 2508
256,000
tokens
Kimi K2 Thinking
131,072
tokens
Codestral 2508 has a 49% larger context window.

Speed Performance

Speed benchmarks not available for these models

Capabilities

Feature Comparison

FeatureCodestral 2508Kimi K2 Thinking
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyCodestral 2508Kimi K2 Thinking
LicenseOpen SourceOpen Source
AuthorMistral AIMoonshotai
ReleasedAug 2025Nov 2025

Codestral 2508 Modalities

Input
text
Output
text

Kimi K2 Thinking Modalities

Input
text
Output
text

Related Comparisons

Compare Codestral 2508 with:

Compare Kimi K2 Thinking with:

Frequently Asked Questions

Codestral 2508 has cheaper input pricing at $0.30/M tokens. Codestral 2508 has cheaper output pricing at $0.90/M tokens.
Codestral 2508 scores higher on coding benchmarks with a score of N/A, compared to Kimi K2 Thinking's score of N/A.
Codestral 2508 has a 256,000 token context window, while Kimi K2 Thinking has a 131,072 token context window.
Codestral 2508 does not support vision. Kimi K2 Thinking does not support vision.