GPT-5-Codex
GPT-5-Codex is a GPT-5 family model specialized for autonomous software engineering, designed to operate as a coding agent that reads repositories, writes code, executes tests, and iterates on solutions in sandboxed environments.
View API reference- Input and output price
- Input $1.25, Output $10, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-5-codex', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out GPT-5-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.
GPT-5-Codex
Copy link to headingProviders
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.
| Provider |
|---|
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call GPT-5-Codex through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-5-codex', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same GPT-5-Codex request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-5-codex', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. openai/gpt-5-codex. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. GPT-5-Codex supports up to 128,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 400K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK openai provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-5-codex', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['azure'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-5-codex', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-5-codex', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-5-codex', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'openai/gpt-5-codex', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingAbout GPT-5-Codex
GPT-5-Codex launched on September 15, 2025 as the GPT-5-class entry in OpenAI's Codex product line, designed specifically for autonomous software engineering. The model combines GPT-5's advanced reasoning capabilities with specialized training for the coding agent workflow: reading repository context, planning changes, writing code, executing tests in sandboxed environments, and iterating until tasks are verified complete.
Unlike general-purpose models that also happen to be good at code, GPT-5-Codex is architecturally optimized for the agentic coding loop. It understands repository structures, respects existing coding conventions, and produces changes that integrate cleanly with the surrounding codebase. The sandboxed execution environment means it can validate its own work by running tests before returning results.
The model supports a context window of 400K tokens, enabling it to read substantial portions of a codebase in a single pass. This broad context awareness is critical for refactoring tasks and architectural changes that span multiple files and modules.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: GPT-5-Codex is built for the full coding agent loop rather than one-shot code generation. It reads repository context, plans changes, writes code, runs tests, and iterates until the task is complete.
- Configuration: It brings GPT-5-level reasoning to coding tasks, making it capable of handling complex refactors, architectural decisions, and multi-file changes that require understanding the broader codebase.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use GPT-5-Codex
Best for
- Autonomous code generation: Writing features from specifications with test verification
- Complex refactoring: Multi-file changes that require understanding architectural patterns
- Bug diagnosis and repair: Tracing issues through codebases and producing verified fixes
- Code review automation: Deep analysis of pull requests with actionable suggestions
- Test generation: Creating comprehensive test suites that cover edge cases
Consider alternatives when
- Simpler coding tasks: Codex mini handles routine bug fixes and feature scaffolding at lower cost
- General-purpose work: Base GPT-5 is better when coding is only part of a broader workflow
- Non-coding reasoning: The o-series reasoning models for pure mathematical or scientific reasoning
- Chat-based code help: GPT-5 chat for conversational coding assistance rather than autonomous execution
Copy link to headingConclusion
GPT-5-Codex combines GPT-5-level reasoning with purpose-built autonomous coding capabilities. For teams building AI-powered development tools on AI Gateway within the GPT-5 generation, it is the coding-specialized option.
Copy link to headingFrequently Asked Questions
How does GPT-5-Codex differ from codex-mini?
GPT-5-Codex brings GPT-5-class reasoning to coding tasks, making it better at complex refactors, architectural decisions, and multi-file changes. Codex-mini is optimized for speed and cost on simpler tasks.
Can GPT-5-Codex execute and test its own code?
Yes. It operates in sandboxed environments where it can run code, execute test suites, and iterate on solutions before returning verified results.
What context window does GPT-5-Codex support?
400K tokens, enabling it to read large portions of a codebase in a single pass for comprehensive understanding.
How does AI Gateway handle authentication for GPT-5-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.
Is GPT-5-Codex suitable for production CI pipelines?
Yes, though its higher cost means it's best reserved for complex tasks. Use codex-mini for routine per-PR checks and GPT-5-Codex for deeper architectural reviews.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.