Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
OpenAI
OpenAI

Claude 3.5 Sonnet vs GPT-5.3 Codex

A detailed comparison of pricing, benchmarks, and capabilities

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

OpenClaw

Deploy OpenClaw in Under 1 Minute We handle hosting, scaling, and maintenance

Key Takeaways

Claude 3.5 Sonnet wins:

  • No clear advantages in compared metrics

GPT-5.3 Codex wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Has reasoning mode
Price Advantage
GPT-5.3 Codex
Benchmark Advantage
GPT-5.3 Codex
Context Window
GPT-5.3 Codex
Speed
GPT-5.3 Codex

Pricing Comparison

Benchmark Comparison

Context & Performance

Capabilities

Feature Comparison

FeatureClaude 3.5 SonnetGPT-5.3 Codex
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude 3.5 SonnetGPT-5.3 Codex
LicenseProprietaryProprietary
AuthorAnthropicOpenAI
ReleasedOct 2024Feb 2026

Claude 3.5 Sonnet Modalities

Input
textimagefile
Output
text

GPT-5.3 Codex Modalities

Input
textimage
Output
text

Related Comparisons

Compare Claude 3.5 Sonnet with:

Compare GPT-5.3 Codex with:

Frequently Asked Questions

GPT-5.3 Codex has cheaper input pricing at $1.75/M tokens. GPT-5.3 Codex has cheaper output pricing at $14.00/M tokens.
GPT-5.3 Codex scores higher on coding benchmarks with a score of 53.1, compared to Claude 3.5 Sonnet's score of 30.2.
Claude 3.5 Sonnet has a 200,000 token context window, while GPT-5.3 Codex has a 400,000 token context window.
Claude 3.5 Sonnet supports vision. GPT-5.3 Codex supports vision.