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 on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills. The model is optimized for long-running, tool-using workflows and supports interactive steering during execution, making it suitable for complex development tasks, debugging, deployment, and iterative product work.
Beyond coding, GPT-5.3-Codex performs strongly on structured knowledge-work benchmarks such as GDPval, supporting tasks like document drafting, spreadsheet analysis, slide creation, and operational research across domains. It is trained with enhanced cybersecurity awareness, including vulnerability identification capabilities, and deployed with additional safeguards for high-risk use cases. Compared to prior Codex models, it is more token-efficient and approximately 25% faster, targeting professional end-to-end workflows that span reasoning, execution, and computer interaction.
- Organization
- OpenAI
- Family
- gpt-codex
- Providers
- 29
- Context
- 400,000
- Output limit
- 128,000
- Knowledge
- 2025-08-31
- Release
- 2026-02-05
- Updated
- —
- Weights
- Closed
- Input
- text, image/jpeg, image/png, image/gif, image/webp, application/pdf
- Output
- text
- Capabilities
- —
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| Abacus | gpt-5.3-codex-xhigh | 400,000 | 128,000 | — / — | — | — | — | View |
| Abacus | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| AIHubMix | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| AI/ML API | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| CommandCode | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| DevPass (LLM Gateway) | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| DigitalOcean | openai-gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Eden AI | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| FastRouter | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| FreeModel | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| FrogBot | gpt-5-3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| GitHub Copilot | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| GitLab Duo | duo-chat-gpt-5-3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Impossibl | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Kilo Gateway | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| LLM Gateway | azure/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| LLM Gateway | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| NanoGPT | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Neon | gpt-5-3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Ofox | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| OpenCode | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Azurevia OpenRouter | openai/gpt-5.3-codex unknown | 400,000 | 128,000 | $1.75 / $14.00 | Yes | Yes | Yes | View |
| OpenAIvia OpenRouter | openai/gpt-5.3-codex unknown | 400,000 | 128,000 | $1.75 / $14.00 | Yes | Yes | Yes | View |
| OpenAIvia OpenRouter | openai/gpt-5.3-codex unknown | 400,000 | 128,000 | $3.50 / $28.00 | Yes | Yes | Yes | View |
| Opper | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| OrcaRouter | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Poe | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Prime Inference | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Requesty | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Venice AI | openai-gpt-53-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Vercel AI Gateway | openai/gpt-5.3-codex-fast | 400,000 | 128,000 | — / — | — | — | — | View |
| Vercel AI Gateway | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| Vivgrid | gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
| ZenMux | openai/gpt-5.3-codex | 400,000 | 128,000 | — / — | — | — | — | View |
Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.
Pricing
Compare token rates and cache charges across available routes and hosting configurations.
Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.
openai/gpt-5.3-codexObserved - Input
- $1.75
- Output
- $14.00
- Cache read
- $0.175
Additional fees and pricing conditions
- web search
- $0.01 / search
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| Azureazure | $1.75 | $14.00 | $0.175 | — |
| OpenAIopenai | $1.75 | $14.00 | $0.175 | — |
| OpenAIopenai/fast | $3.50 | $28.00 | $0.35 | — |
Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.
Performance
Review reported latency and output-throughput percentiles from the latest observed rolling window.
Time to first token · milliseconds
All latency percentiles 2 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Azureazure | 4,420 ms | 6,918.25 ms | 9,881.6 ms | 15,122.6 ms |
| OpenAIopenai | 1,944 ms | 3,421 ms | 7,336.7 ms | 22,153.95 ms |
Output throughput · tokens per second
All throughput percentiles 2 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Azureazure | 119 t/s | 138 t/s | 149 t/s | 161.42 t/s |
| OpenAIopenai | 87.5 t/s | 108 t/s | 134 t/s | 160.44 t/s |
Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.
Uptime
Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.
Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.
Benchmarks
Review attributed evaluation results on each source's original scale.
openai/gpt-5.3-codexObserved | Design Arena | Category | Elo | Win rate | Rank |
|---|---|---|---|---|
| agents | androidnative | 1,084 | 35.2% | 30 |
| agents | fullstack | 983 | 36.5% | 42 |
| agents | godotgamedev | 1,124 | 45.1% | 27 |
| agents | mobileapps | 1,051 | 41.4% | 44 |
| agents | webapps | 1,025 | 36.9% | 40 |
| models | 3d | 1,013 | 35.3% | 103 |
| models | asciiart | 1,158 | 51.2% | 37 |
| models | codecategories | 1,149 | 47.2% | 78 |
| models | dataviz | 1,167 | 50.6% | 69 |
| models | gamedev | 1,169 | 51.3% | 65 |
| models | svg | 1,128 | 54% | 53 |
| models | uicomponent | 1,141 | 47.3% | 77 |
| models | website | 1,167 | 48.6% | 77 |
Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| Composite indices | GPT-5.3 Codex (Xhigh)openai/gpt-5.3-codex-20260224 | Artificial Analysis | Intelligence 32.5 · Coding — · Agentic — | Details |
| models · dataviz | GPT-5.3 Codexopenai/gpt-5.3-codex-20260224 | Design Arena | 1,164 Elo | Details |
| models · 3d | GPT-5.3 Codexopenai/gpt-5.3-codex-20260224 | Design Arena | 1,008 Elo | Details |
| models · uicomponent | GPT-5.3 Codexopenai/gpt-5.3-codex-20260224 | Design Arena | 1,135 Elo | Details |
| models · gamedev | GPT-5.3 Codexopenai/gpt-5.3-codex-20260224 | Design Arena | 1,161 Elo | Details |
| models · website | GPT-5.3 Codexopenai/gpt-5.3-codex-20260224 | Design Arena | 1,163 Elo | Details |
| models · asciiart | GPT-5.3 Codexopenai/gpt-5.3-codex-20260224 | Design Arena | 1,152 Elo | Details |
| models · codecategories | GPT-5.3 Codexopenai/gpt-5.3-codex-20260224 | Design Arena | 1,145 Elo | Details |
| models · svg | GPT-5.3 Codexopenai/gpt-5.3-codex-20260224 | Design Arena | 1,129 Elo | Details |
| tau bench verified airline | OpenAI: GPT-5.3-Codexopenai/gpt-5.3-codex-20260224 | OpenRouter | 75.333% | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.
Apps & session costs
Compare observed median session costs for applications using this model, grouped by conversation length.
| Application | Model route | Turns | Median cost / session | Details |
|---|---|---|---|---|
| Codex | openai/gpt-5.3-codex-20260224 | 2–9 turns | $0.062356 | Details |
| Codex | openai/gpt-5.3-codex-20260224 | 10–49 turns | $0.386076 | Details |
| Codex | openai/gpt-5.3-codex-20260224 | 1 turn | $0.016171 | Details |
Source: OpenRouter, as of Oct 20, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.
Technical details & API
Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.
openai/gpt-5.3-codexObserved - Context
- 400,000
- Maximum output
- 128,000
- Tokenizer
- GPT
- Input
- text, image, file
- Output
- text
- Moderation
- Yes
- Added to OpenRouter
- 2026-02-24
https://openrouter.ai/api/v1openai/gpt-5.3-codexopenai/gpt-5.3-codex-20260224Reasoning
- Required
- No
- Enabled by default
- Not reported
- Default effort
- medium
- Supported efforts
- xhigh, high, medium, low, none
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosity
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does GPT-5.3 Codex cost?
Listed rates start at $1.75 per million input tokens and $14.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer GPT-5.3 Codex?
There are 34 cataloged offers across 29 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 400,000 tokens. Each serving endpoint may apply a different limit.
Does it support tools and structured output?
Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.
Catalog history · 3 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
abc182f3c7d9 - ·
001f606f89a7 - ·
d52954087d81