Claude 4.5 Sonnet (thinking) vs GPT-5 Codex
Detailed comparison of capabilities, features, and performance.
Feature
Claude 4.5 Sonnet (thinking)
GPT-5 Codex
Model Image
AI Lab
Anthropic
OpenAI
Context Size
1,000,000 tokens
400,000 tokens
Max Output Size
64,000 tokens
128,000 tokens
Frontier Model
Yes
Yes
Vision Support
Yes
Yes
Description
The latest Claude 4.5 Sonnet model from Anthropic with maximum reasoning enabled, 200k reasoning tokens in 1M context.
OpenAI's specialist coding model.
Learn more about Claude 4.5 Sonnet (thinking)
View detailed specifications and capabilities
View model details →Learn more about GPT-5 Codex
View detailed specifications and capabilities
View model details →More model comparisons
Try both models in your workspace
Access both Claude 4.5 Sonnet (thinking) and GPT-5 Codex in a single workspace without managing multiple API keys.
Create your workspace