OpenAI
GPT-5.3-Codex
Launched 2026-02-05 · Knowledge up to 2025-08-31 · Listed on OpenRouter 2026-02-24
Prices updated . Benchmarks updated .
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...
You send / 1M
$1.75
tokens in
It replies / 1M
$14.00
tokens out
Context
400K
tokens it can read at once
Typical request
$0.0093
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| SWE-bench VerifiedHigh effort | 74.8% | Independent | 2026-02-25 | Epoch AI |
| Terminal-Benchagent SageAgent | 78.4% | Independent | 2026-02-05 | Terminal-Bench, republished by Epoch AI |
| CritPtExtra high effort | 16.9% | Independent | 2026-02-05 | CritPt, republished by Epoch AI |
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Azure | $1.75 | $14.00 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image, file, pdf
- Writes: text
- Weights: Closed
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 128K tokens
- Repeated text is billed at $0.175 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with GPT-5.3-Codex
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.
