Mistral AI
Mistral AI
vs
OpenAI
OpenAI

Mistral Small 24B Instruct 2501 vs GPT-5.3 Codex

A detailed comparison of pricing, benchmarks, and capabilities

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

Key Takeaways

Mistral Small 24B Instruct 2501 wins:

  • Cheaper input tokens
  • Cheaper output tokens

GPT-5.3 Codex wins:

  • Larger context window
  • Supports vision
  • Has reasoning mode
Price Advantage
Mistral Small 24B Instruct 2501
Benchmark Advantage
Mistral Small 24B Instruct 2501
Context Window
GPT-5.3 Codex
Speed
N/A

Pricing Comparison

Context & Performance

Capabilities

Feature Comparison

FeatureMistral Small 24B Instruct 2501GPT-5.3 Codex
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyMistral Small 24B Instruct 2501GPT-5.3 Codex
LicenseOpen SourceProprietary
AuthorMistral AIOpenAI
ReleasedJan 2025Feb 2026

Mistral Small 24B Instruct 2501 Modalities

Input
text
Output
text

GPT-5.3 Codex Modalities

Input
textimage
Output
text

Frequently Asked Questions

Mistral Small 24B Instruct 2501 has cheaper input pricing at $0.04/M tokens. Mistral Small 24B Instruct 2501 has cheaper output pricing at $0.06/M tokens.
Mistral Small 24B Instruct 2501 has a 32,768 token context window, while GPT-5.3 Codex has a 400,000 token context window.
Mistral Small 24B Instruct 2501 does not support vision. GPT-5.3 Codex supports vision.