Skip to content
GPT-5 Codex logo

GPT-5 Codex

Verified

OpenAI's multimodal model for large-scale text and image tasks.

OpenAIMultimodalClosed
Vision
Model page
Updated 2026-06-14

About GPT-5 Codex

GPT-5 Codex was developed by OpenAI as a proprietary multimodal system. It processes combined text and image data across an extensive 400,000-token context. Access is limited to API usage since the weights are not released.

The architecture supports sustained coherence over very long multimodal sequences. This enables detailed analysis of documents paired with visual references. Typical applications include research workflows and content generation that require both visual and textual context.

Capabilities

Long-context reasoning
Code generation
Vision understanding
Multimodal text-image analysis
Complex document processing
Integrated coding and visual tasks

How GPT-5 Codex compares

GPT-5 Codex (striped bar) vs other multimodal on intelligence, speed and price.

Price

USD per 1M output tokens · Lower is better · GPT-5 Codex ranks #65 of 100

$7.5
Mistral Medium 3.5
$8.0
o4 Mini Deep Research
$9.0
Gemini 3.5 Flash
$9.0
Google Gemini Flash Latest
$10.0
GPT-5.1
$10.0
GPT-5
$10.0
GPT-5 Codex
$10.0
GPT-5.1-Codex
$10.0
GPT-5.1-Codex-Max
$10.0
GPT-5 Chat
$10.0
GPT-5.1 Chat
$12.0
Gemini 3.1 Pro Preview Custom Tools
$12.0
Gemini 3.1 Pro Preview

Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).

Best for

Long-Context Codebase Analysis

The model excels at reviewing and refactoring repositories spanning hundreds of thousands of tokens while incorporating visual diagrams or UI screenshots for context.

Multimodal Document Workflows

It processes complex documents that combine text, tables, and images, enabling extraction of insights and generation of updated code or reports in a single pass.

Vision-Integrated Development Tasks

Developers can pair code generation requests with screenshots or design mocks to receive both implementation code and visual verification suggestions.

Strengths & limitations

Strengths

  • +Handles extremely large inputs effectively
  • +Strong coding specialization
  • +Unified text and image reasoning

Limitations

  • High resource demands with maximum context
  • Limited to text and static images
  • Potential coherence loss in very long outputs

Cost calculator

Estimate what GPT-5 Codex would cost for your usage.

$0.00625
per request
$62.5
estimated / month

Based on GPT-5 Codex's $1.25/1M input · $10.00/1M output. Estimate only — actual cost varies by provider and caching.

Quick start

OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.

JavaScript · openai
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "openai/gpt-5-codex",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

Model slug: openai/gpt-5-codex

Editor's verdict

Our take on GPT-5 Codex

GPT-5 Codex is OpenAI's proprietary multimodal with a 400K-token context window.

At $10.00 per 1M output tokens, it is premium-priced for its class.

It is available through OpenAI's API and aggregators like OpenRouter.

Best suited to handles extremely large inputs effectively and strong coding specialization.

Did you find this helpful?

Frequently asked questions

The model supports a context length of 400000 tokens.

User reviews

Real, verified reviews from the community shape this model's rating.

Loading reviews…

Sign in to review

Other GPT models

Sibling versions in the GPT family from OpenAI.

Promote GPT-5 Codex

Add this badge to your website, or share the tool.

DFeatured on DhanasviGPT-5 Codex 2