Skip to main content
AI Choice EngineAI Choice Engine

OpenAI

GPT-5.3-Codex

GPT-5.3-Codex is a OpenAI model with 400K context, $1.75 in / $14 out per million tokens, last verified September 3, 2026. Open weights: no. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.

GPT-5.3-Codex is OpenAI's coding-specialised model powering the Codex agent at $1.75/$14.

Catalog record checked September 3, 2026Individual provider fields may change

AI model specification details
SpecificationGPT-5.3-Codex
ProviderOpenAI
TierFrontier
Context window400K
Max output128K
Input / 1M tokens$1.75
Output / 1M tokens$14
WeightsClosed
ParametersNot disclosed
Reasoning levelsnone, low, medium, high, xhigh, max
Modalitiestext, image
API model idgpt-5.3-codex
ReleasedFebruary 5, 2026

Pricing tiers: Standard $1.75/$14 per MTok; cached input $0.175/MTok; Fast mode $3.50/$28. Purpose-built for the Codex agent.

Verified evidence

Published benchmark results

Each result keeps its source and measurement date visible. A missing benchmark is not treated as a zero.

Published benchmark results for GPT-5.3-Codex
BenchmarkScoreMeasuredSource
Artificial Analysis Intelligence Index [high]522026-08-14Artificial Analysis · View source

Best for

  • Autonomous coding
  • Repo-scale refactors
  • Test generation

Watch out

Tuned for coding, not general chat; use GPT-5.6 for broad reasoning.

Source receipts

Catalog figures for this model were checked against the following sources.

Common questions

GPT-5.3-Codex

Answered from the verified figures on this page rather than general guidance.

How much does GPT-5.3-Codex cost per million tokens?

GPT-5.3-Codex is listed at $1.75 per million input tokens and $14 per million output tokens at standard rates. Output tokens usually dominate real bills, so weigh the output rate more heavily than the input rate. Standard $1.75/$14 per MTok; cached input $0.175/MTok; Fast mode $3.50/$28. Purpose-built for the Codex agent.

What is GPT-5.3-Codex's context window?

GPT-5.3-Codex accepts about 400K tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.

What is GPT-5.3-Codex best for?

GPT-5.3-Codex is a frontier tier from OpenAI. It suits autonomous coding, repo-scale refactors, test generation. Tuned for coding, not general chat; use GPT-5.6 for broad reasoning.