GPT 5.3 Codex
GPT 5.3 Codex is the GPT-5.3 generation of OpenAI's coding agent models, advancing autonomous software engineering with GPT-5.3 generation improvements in reasoning and code comprehension.
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-5.3-codex', prompt: 'Why is the sky blue?'})Playground
Try out GPT 5.3 Codex by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by OpenAI
| Model |
|---|
| 1M | 3.2s | 45tps | $5.00/M | $30.00/M | Read: $0.5/M Write: — | $10.00/K + input costs | — |   | 04/24/2026 | ||||
| 400K | 1.5s | 235tps | $0.75/M | $4.50/M | Read:$0.07/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 400K | 0.4s | 19tps | $0.20/M | $1.25/M | Read:$0.02/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 1.1M | 0.9s | 65tps | $2.50/M | $15.00/M | Read: $0.25/M Write: — | $10.00/K + input costs | — | | 03/05/2026 | ||||
| 128K | 0.5s | 108tps | $1.25/M | $10.00/M | Read:$0.13/M Write:— | $10.00/K + input costs | — | | 11/12/2025 | ||||
| 131K | 0.1s | 241tps | $0.35/M | $0.75/M | Read:$0.25/M Write:— | — | — |    +5 | 08/05/2025 |
About GPT 5.3 Codex
GPT 5.3 Codex became available on February 24, 2026 on AI Gateway as OpenAI's GPT-5.3 generation codex model. Two generations of refinement since GPT-5.1 codex translate to measurable gains in code comprehension depth and the ability to reason across files in large repositories.
The GPT-5.3 generation sharpens the codex agent loop (reading context, planning changes, writing code, running tests, and iterating) with better accuracy at each stage. Where earlier generations occasionally missed cross-file dependencies or produced partially correct refactors, GPT 5.3 Codex handles these patterns more consistently.
The context window of 400K tokens gives GPT 5.3 Codex comprehensive codebase understanding, letting it trace call chains, data flows, and type relationships across modules in a single pass.
What To Consider When Choosing a Provider
- Configuration: GPT 5.3 Codex incorporates GPT-5.3 generation advances in reasoning and code comprehension over GPT-5.2 codex.
- Configuration: Each codex generation brings measurable improvements in code quality, reasoning depth, and task completion reliability.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use GPT 5.3 Codex
Best For
- Complex coding automation: Tasks that benefit from GPT-5.3 generation reasoning improvements
- Complex enterprise projects: Large-scale development, migration, and modernization requiring strong model quality
- Advanced agent architectures: AI coding tools that benefit from GPT-5.3 generation improvements
- Performance-critical code: Optimization tasks where stronger reasoning produces meaningfully better results
- Development tools: Products that benefit from GPT-5.3 generation coding capabilities
Consider Alternatives When
- Routine coding tasks: Earlier codex mini models for everyday bug fixes and scaffolding
- Cost optimization: Previous generation codex models at lower price points
- Non-coding tasks: GPT-5.2 or other general-purpose models for reasoning and generation workloads unrelated to code
- Extended reasoning: O3 for pure chain-of-thought reasoning on hard problems
Conclusion
Two codex generations of refinement make GPT 5.3 Codex more reliable at cross-file reasoning and complex refactors than its predecessors. For teams already using the codex agent architecture, it provides a direct upgrade path through AI Gateway.
Frequently Asked Questions
How does GPT 5.3 Codex improve over GPT-5.2 codex?
It incorporates the GPT-5.3 generation's advances in reasoning and code comprehension, producing higher-quality code and more reliable autonomous task completion.
What context window does GPT 5.3 Codex support?
400K tokens, enabling comprehensive codebase analysis in a single pass.
Can GPT 5.3 Codex verify its own output?
Yes. It operates in sandboxed environments where it executes code, runs test suites, and iterates on solutions before returning results.
How does AI Gateway handle authentication for GPT 5.3 Codex?
AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.
Should I upgrade from GPT-5.2 codex?
If your workloads benefit from improved reasoning and code quality, yes. Test with your specific tasks to confirm the improvement justifies any pricing differences.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.