GPT-5.3-Codex
GPT-5.3-Codex is a large language model made by OpenAI, added to the catalog on 24 Feb 2026. It has a context window of 400,000 tokens and costs $1.75 per 1M input tokens and $14.00 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: streamline complex software development tasks, draft documents and analyze spreadsheets and identify vulnerabilities in code.
Price checked · source: OpenRouter
What GPT-5.3-Codex is
OpenAI's GPT-5.3-Codex, released on February 24, 2026, is a cutting-edge coding model designed for complex software engineering tasks. With a context length of 400,000 tokens, it supports both text and image inputs, generating text outputs. This model excels in multi-language coding, debugging, and deployment, while also performing well in structured knowledge tasks like document drafting and spreadsheet analysis. Enhanced with cybersecurity awareness, it identifies vulnerabilities and is optimized for efficient workflows, making it a valuable tool for professionals in various domains.
Key features
- Supports text and image inputs
- Optimized for long-running workflows
- Enhanced cybersecurity awareness
- Fast and token-efficient performance
- Strong multi-language coding capabilities
Typical uses
- Streamline complex software development tasks
- Draft documents and analyze spreadsheets
- Identify vulnerabilities in code
- Create presentations and conduct research
GPT-5.3-Codex pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $1.75 |
| Output, per 1M tokens | $14.00 |
| Cached input read, per 1M tokens | $0.175 |
| Web search, per search | $0.01 |
No price change since it was added on 24 Feb 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0051 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.055 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.081 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.284 |
GPT-5.3-Codex specifications
| Model id | openai/gpt-5.3-codex |
|---|---|
| Version | gpt-5.3-codex-20260224 |
| Context window | 400,000 tokensAbout 300,000 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 24 Feb 2026 |
| Input types | text, image, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
AI could positively upend work, leisure, and creativity by shifting people from routine effort to higher-value expression. At work, AI can automate repetitive tasks—scheduling, reporting, data cleanup—so people spend more time on strategy, relationships, and problem-solving. It can also act as a “co-pilot,” helping workers learn faster, draft ideas, and make better decisions, which may widen access to skilled jobs. In leisure, AI can remove friction from daily life: smarter assistants can handle planning, translation, and personalized recommendations for travel, books, and learning. That saved time can become true free time—more rest, family connection, and exploration. For creativity, AI lowers technical barriers. Someone with a story idea can generate visuals, music, or prototypes without years of specialized training. Rather than replacing imagination, AI can amplify it—offering prompts, variations, and instant feedback that spark original work. Used thoughtfully, AI could make life not just more efficient, but more human.