OpenAI Codex (deprecated)

Name: OpenAI Codex (deprecated)
Author: OpenAI

✓ Verified

Legacy code models retired on March 23, 2023

Updated Dec 7, 2025

Deprecated ModelDeprecated

Last reviewed: Dec 7, 2025Details verified against vendor changelogs and hands-on usage.

Visit Website →

Pricing and features change frequently—confirm on the vendor site.

About

OpenAI Codex was the early natural-language-to-code model family (e.g., code-davinci-002, code-cushman-002). Per OpenAI’s deprecation notice, all Codex models were shut down on March 23, 2023, with GPT-4o and newer GPT models recommended for coding tasks. The Codex API is no longer available.

Key Features

✓Legacy natural-language-to-code models (code-davinci-002, code-cushman-002)
✓API access ended March 23, 2023
✓OpenAI recommends GPT-4o or newer GPT models for code tasks

Use Cases

Technical Details

Languages

AI Models

code-davinci-002 (deprecated)code-cushman-002 (deprecated)

Frequently Asked Questions

What is OpenAI Codex (deprecated)?

How much does OpenAI Codex (deprecated) cost?

OpenAI Codex (deprecated) offers deprecated pricing. Plans include: .

What AI models does OpenAI Codex (deprecated) use?

OpenAI Codex (deprecated) is powered by code-davinci-002 (deprecated), code-cushman-002 (deprecated).

Pricing

Company

Name: OpenAI
Founded: 2015
Location: San Francisco, CA

Links

GitHub →Twitter →

Similar Tools

Compare OpenAI Codex (deprecated) with these alternatives

Compare All

OpenAI API

✓

API access to GPT-5.1, GPT-5, GPT-4o, images, audio, and tools

API/SDK Tool

OpenAI’s API gives developers pay-per-use access to the latest GPT models (GPT-5.1, GPT-5, GPT-4o, GPT-4.1, GPT-4.1 mini/nano, o-series), plus images (GPT-Image-1), speech (gpt-audio, Whisper), embeddings, and moderation. It supports tool calling, structured outputs, Assistants/Responses/Chat Completions, Batch, Realtime, prompt caching, fine-tuning, and file/image/audio endpoints. Pricing is metered per model; for example, GPT-5.1 Standard is $1.25 per 1M input ($0.125 cached) and $10 per 1M output, or $0.625 / $5 via Batch (see pricing page for all models).

Pay-per-use

Key Features:

•Access to GPT-5.1, GPT-5, GPT-4o, GPT-4.1, GPT-4.1 mini/nano, and o-series models
•Text and image inputs with text outputs; audio (TTS/STT) and image generation endpoints
•Tool calling, structured/JSON outputs, and Assistants/Responses/Chat Completions APIs

API

Learn more →

Claude Code

✓

Anthropic’s coding companion for terminal and desktop, powered by Claude Opus 4.5

AI Coding CLI

Claude Code is Anthropic’s terminal-first coding experience available in Claude desktop/web and CLI. It uses Claude Opus 4.5 (and Sonnet 4.5 where applicable) to work across your local repositories with project context via CLAUDE.md, multi-file edits, code search, and permissioned command execution. Included with Claude Pro, Max, Team, and Enterprise plans; API usage is billed separately per model pricing.

Subscription

Key Features:

•Available in Claude desktop/web and CLI
•CLAUDE.md file for project-specific context
•Project-wide code search and multi-file editing

macOSLinuxWindows

Learn more →

DeepSeek Coder

✓

Open-source MoE coding model (V2) with 128K context

Open Source Model

DeepSeek Coder V2 is an open Mixture-of-Experts coding model (16B Lite and 236B) with a 128K context window and support for 338 programming languages. Weights are published on Hugging Face for self-hosting; code is MIT-licensed and the model weights use the DeepSeek Model License. Hosted inference is available through the DeepSeek API using OpenAI-compatible endpoints.

Open Source

Key Features:

•DeepSeek-Coder-V2 Mixture-of-Experts models (236B total / 21B active, plus 16B Lite / 2.4B active)
•128K context window with fill-in-the-middle support
•Supports 338 programming languages

All platforms via API

Learn more →

View detailed comparison