Openai

gpt-5.3-codex

Auto-router

openai/gpt-5.3-codex

ChatVisionToolsSystem promptReasoning

Context

400K

Max output

128K

Input / 1M

$1.75

Output / 1M

$14.00

Cached / 1M

$0.175

Cutoff

Aug 2025

About this model

GPT-5.3-Codex is OpenAI's most capable agentic coding model to date, optimized for agentic coding tasks in Codex and similar environments. Supports low/medium/high/xhigh reasoning effort.

Best suited for

Agentic coding and software engineering
Codex CLI/IDE/cloud workflows
Tool calling and structured outputs
Computer-use / agentic tool workflows

Capabilities

Vision

Accepts images alongside text in the same message.

Tools

Native function calling, so agents can invoke your endpoints.

System prompt

Honours a dedicated system role, separate from the user turn.

Reasoning

Emits a separate thinking pass before the answer.

Supported parameters

max_tokensMax Tokens Limit

Specifies the maximum number of text units (tokens) allowed in a response, limiting its length.

tools

Lists tool definitions or capabilities available to the model.

tool_choice

Decides whether to use tools or just the model for generating responses.

response_type

Defines the format or type of the generated response.

parallel_tool_calls

Enables parallel execution of tools, allowing multiple tools to run simultaneously.

reasoning

Controls the level of reasoning effort used by the model (low, medium, high, xhigh).

stream

Sends the response in real-time as it's being generated.