GPT 5.3 Codex

Release Date: Feb 24, 2026     Creator: OpenAI

OpenAI's model optimized for coding tasks

Model Specifications
Knowledge Cutoff
Aug 31, 2025
Context (VividLLM)
128,000 Tokens
With a context window of 128,000 tokens, this model can 'remember' and analyze up to 192 pages of data at once. This makes it a top choice for debugging entire codebases and summarizing full-length books.
Context (Native)
400,000 Tokens
Input ModalitiesTextImagePDF
Output TypeText
Max Output8192
Input Weight
1.33 x (Pro)
Output Weight
1.49 x (Pro)
Industry Benchmarks
Intelligence Index (Artificial Analysis) N/A
Coding Index (Artificial Analysis)N/A
Math Index (Artificial Analysis)N/A
Response Speed
Output Tokens per second N/A
Median Time to First Token SecondsN/A
Launch VividLLM Now => :

Benchmarks accessed via : Artificial Analysis

Disclaimer: We are providing Image Upload options to only limit models as of now, so some models which have image upload options might now have that feature on our site.