OpenAI Codex Models by OpenAI
OpenAIProprietary
2 models2025Up to 200K ctx
About
OpenAI's Codex family of models optimized for software engineering tasks. Built on o3 architecture, trained via reinforcement learning. Powers the OpenAI Codex cloud coding agent with sandboxed execution, GitHub integration, and multi-file reasoning.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
1 in view1 retired
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Codex Mini Latest | Use when the workload needs code and 200K context. | 2025-05 | code200K context | Current |
Release Timeline
1 release group2025-05
1 current · 1 retired
Codex 1
Archivedcode192K contextreasoning
Codex Mini Latest
Currentcode200K context
Specifications(2 models)
| Model | Released | Context | Reasoning | Code Exec |
|---|---|---|---|---|
| Codex Mini Latest | 2025-05 | 200K | No | No |
Frequently Asked Questions
- What is OpenAI Codex used for?
- OpenAI Codex is used for code, reasoning, and code execution. The family description and listed model capabilities point to those workloads as the best fit.
- How does OpenAI Codex compare to GPT Realtime 2?
- OpenAI Codex by OpenAI is strongest where you need code, while GPT Realtime 2 by OpenAI is the closest related family to check for translation. OpenAI Codex has 2 listed variants and reaches up to 200K context, while GPT Realtime 2 reaches up to 131K context, so compare the specs and pricing tables before choosing a production model.
- Which OpenAI Codex model should I use?
- If price is the main constraint, use the pricing table first because OpenAI Codex does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Codex Mini Latest with 200K context.
