← Models

GPT-5.3-Codex

OpenAI · GPT-5

API-published GPT-5.3 Codex route for pinned integrations, deprecated in Codex when using ChatGPT sign-in.

Part of GPT family · Other versions: GPT-5.6 Luna , GPT-5.6 Terra , GPT-5.6 Sol , GPT-5.5 Pro , GPT-5.5 , GPT-Rosalind , GPT-5.4 mini , GPT-5.4 nano , GPT-5.4 Pro , GPT-5.4 , GPT-5.3 , GPT-5.2-Codex , GPT-5.2 Pro , GPT-5.2 , GPT-5-Codex , GPT-5 mini , GPT-5 nano , GPT-5 , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , Computer Use Preview , GPT-4o mini , GPT-4o
Type
language
Context
400K tokens
Max Output
128K tokens
Status
current
Input
$1.75/1M tok
Output
$14/1M tok
API Access
Yes
License
proprietary
coding agentic software-engineering tool-use code-review refactoring
Released February 2026 · Updated July 10, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on July 10, 2026.

GPT-5.3-Codex remains an API-published specialized coding model for pinned integrations. OpenAI now lists it as deprecated in Codex when users authenticate with ChatGPT, while noting that some models with that product-level status may remain available through API-key authentication. It should not be described as the current default behind Codex clients; OpenAI Codex and GPT-5.6 are the current starting points for fresh work.

Capabilities

The model is built for multi-file edits, code review, test-aware implementation loops, and longer agent workflows where reliable tool use matters. OpenAI’s launch materials also position it as stronger on computer-style professional work beyond pure coding, including spreadsheets, decks, docs, and longer-running execution.

Technical Details

OpenAI’s API docs keep GPT-5.3-Codex in the published model picture with 400K context, 128K max output, image input support, and coding-specialized positioning. Treat those as API-route details for pinned integrations, while current Codex product guidance recommends GPT-5.6 models.

Pricing & Access

Current published standard API pricing (per 1M tokens):

  • Input: $1.75
  • Cached input: $0.175
  • Output: $14.00

OpenAI’s API model docs still publish GPT-5.3-Codex, but the Codex model guide marks it deprecated for ChatGPT sign-in. API-key users should confirm current access before relying on the route.

Best Use Cases

Use GPT-5.3-Codex for pinned API integrations, regression comparisons, or migrations that still depend on its behavior. Start new Codex evaluations with the currently recommended GPT-5.6 family.

Comparisons

  • GPT-5.5 (OpenAI): Better frontier general model when coding is one part of a broader professional workflow.
  • GPT-5.2-Codex (OpenAI): Older Codex-specialized route retained for compatibility and regression comparisons.
  • Claude Code + Claude Opus family (Anthropic): Strong alternative coding stack when Anthropic-native tooling is preferred.