← Back to all models

GPT-5.3-Codex

OpenAICodeProprietary

OpenAI's most capable agentic coding model combining frontier coding performance with deep reasoning. Handles long-running tasks involving research, tool use, and complex execution. Can be steered interactively while working.

Abilities

Code GenerationText GenerationReasoningMathVisionFunction CallingStructured OutputLong Context

Use Cases

Coding AssistantResearchEnterpriseAutomation

Available in Tools

Availability

How to Use

Use the OpenAI API with model ID `gpt-5.3-codex`. Also accessible through ChatGPT (Plus, Pro, Enterprise), the open-source Codex CLI, and Codex Cloud for background task execution.

Pros

  • State-of-the-art coding performance — 56.8% on SWE-Bench Pro and 75.1% on Terminal-Bench 2.0
  • 400K token context window — can process entire large codebases in a single session
  • Interactive steering — redirect mid-task without losing context, like working with a colleague
  • 25% faster than predecessor Codex models
  • 90% prompt caching discount significantly reduces repeat-query costs
  • Integrations with GitHub, Slack, Linear, and MCP support

Cons

  • High output token pricing at $14/1M — verbose responses amplify costs
  • Significant latency (~98 seconds time-to-first-token) due to extended thinking
  • Can hallucinate files in large codebases — references components that do not exist
  • No fine-tuning support
  • Not optimized for conversational use — use GPT-5.4 for chat scenarios

What to Use It For

star

Perfect For

Complex multi-file software engineering tasks

Industry-leading SWE-Bench Pro and Terminal-Bench scores for cross-codebase coordination and feature implementation

Long-running agentic coding workflows

Designed for multi-step tasks involving research, tool use, and execution with interactive steering

thumb_up

Good For

Code review and bug fixing

Deep code comprehension with 400K context for analyzing large codebases

Automated testing and migrations

Can plan and execute multi-step coding tasks autonomously in sandboxed environments

warning

Not Recommended

Quick conversational chat

~98 second time-to-first-token makes it unusable for real-time conversation

Try instead: GPT-5.4, GPT-4o

Budget-constrained high-volume tasks

$14/1M output tokens with verbose responses adds up fast

Try instead: GPT-4.1 Mini

block

Do Not Use For

Latency-sensitive real-time applications

Extended thinking phase causes ~98 second time-to-first-token — completely unsuitable

Try instead: GPT-4o, GPT-4.1

Image or audio generation

Code-focused model — no image or audio capabilities

Try instead: GPT-Image-1, OpenAI TTS

Technical Details

Pricing$1.75 / 1M input tokens, $14.00 / 1M output tokens
ParametersUndisclosed
detail.contextWindow400K tokens

Links