← Models

GPT-5-Codex

OpenAI · GPT-5

Earlier GPT-5 Codex release entry kept as a historical baseline in OpenAI's Codex model lineage.

Part of GPT family · Other versions: 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-5.3-Codex , GPT-5.2-Codex , GPT-5.2-Pro , GPT-5.2 , GPT-5 mini , GPT-5 , GPT-5 nano , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , GPT-4o mini , GPT-4o
Type
language
Context
400K tokens
Max Output
128K tokens
Status
legacy
Input
$1.25/1M tok
Output
$10/1M tok
API Access
Yes
License
proprietary
coding agentic software-engineering tool-use code-review refactoring
Released September 2025 · Updated April 18, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on April 18, 2026.

GPT-5-Codex was the initial coding-specialized release in the GPT-5 generation. OpenAI’s current docs still publish it as a live model page with pricing and capability details, but it now matters more as a lineage and compatibility reference than as the clean answer to “what does Codex use today?”

Capabilities

It is designed for multi-file code understanding, patch generation, refactoring, and review-oriented development workflows where reliability matters.

Technical Details

OpenAI’s current model card still lists GPT-5-Codex with a 400K context window, 128K max output, and pricing at 1.25/1.25 / 10 per million input/output tokens. The same card also says the underlying snapshot will be regularly updated. Treat this as a maintained historical API route, not as proof that every current Codex client defaults to this model.

Pricing & Access

Current published API pricing for this older Codex tier remains:

  • Input: $1.25 per 1M tokens
  • Output: $10.00 per 1M tokens

OpenAI’s pricing docs also list a cached input rate of $0.125 per 1M tokens.

Best Use Cases

Treat this entry as a historical baseline for GPT-5 Codex evolution, compatibility checks, and older API integrations that still reference the original GPT-5 Codex route. For new coding-agent builds, use OpenAI Codex as the stable product-level reference and current model pages like GPT-5.2-Codex when you need an explicit API model snapshot.

Comparisons

  • GPT-5.2-Codex (OpenAI): Newer published coding-specialized API snapshot in OpenAI’s current model docs.
  • OpenAI Codex (OpenAI): Stable product-level reference when the exact model varies by surface or configuration.
  • Claude Opus family (Anthropic): Strong alternative for premium coding and review workflows outside the OpenAI stack.