GPT-5.3 Codex
| Maker | OpenAI |
|---|---|
| Released | 2026-02-24 |
| Context | 400K |
| Max output | 128K |
| Open weights | Closed |
| Modalities | text, image, pdf → text |
|---|---|
| Input / 1M | $1.75 |
| Output / 1M | $14.00 |
| Cached input / 1M | $0.175 |
| Review call | $0.0797 |
| Reasoning efforts | low, medium, high, xhigh |
|---|---|
| Hosts | OpenAI, OpenRouter |
| Model id | gpt-5.3-codex |
CodePanel's benchmark has not run GPT-5.3 Codex as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
No GPT Codex model is ranked yet. Of OpenAI's ranked models, GPT-6.1 Sol is the closest in list price; it caught 89% [80%–97%] of the known bugs at rank 1 of 17, with a measured review cost of $0.0401. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0797 on GPT-5.3 Codex and $0.0766 on GPT-6.1 Sol, so this model's call is about the same as that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| OpenAI | gpt-5.3-codex | $1.75 | $14.00 |
Source: OpenAI pricing, Oct 16, 2026
| Benchmark | Score | Range | Setting | Source | Date |
|---|---|---|---|---|---|
| Epoch Capabilities Index | 157 ECI | 153 to 161 | – | Epoch AI CC BY 4.0 | Feb 5, 2026 |
Same as on GPT-5.6 Terra.
Updated Oct 23, 2026