OpenAI: GPT-5.3-Codex
GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...
Everything else
| Max output | 128K |
|---|---|
| Input / 1M | $1.75 |
| Output / 1M | $14 |
| Cache read / 1M | $0.175 |
| Cache write / 1M | — |
| 1M in + 1M out | $15.75 |
| Takes | text, image, file |
| Returns | text |
| Tools | yes |
| Reasoning | optional · xhigh, high, medium, low, none |
| Open weights | no |
| Released | 2026-02-24 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | openai/gpt-5.3-codex |
Benchmarks
| source | epoch |
|---|---|
| eci | 155.59 |
| confidence | Likely |
| accessibility | API access |
| sweBenchVerified | 0.748 |
| sweBenchVerifiedStderr | 0.0198 |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.