Models

GPT-5.3 Codex (xhigh)

OpenAIOpenAIUnited States

A high-performance code generation model from OpenAI's GPT-5 series, specifically optimized for coding tasks with fast response times and strong reasoning capabilities.

CodingReasoningFastLong context
Input / 1M tokens
$1.75
Output / 1M tokens
$14.00
Output tokens/s
77.07
First-token seconds
84.45s
Supported plans
23

Benchmark history

Evaluations

8

TAU2

Measured Jul 10, 2026Source

Score

0.86

Terminalbench Hard

Measured Jul 10, 2026Source

Score

0.53

Lcr

Measured Jul 10, 2026Source

Score

0.74

Ifbench

Measured Jul 10, 2026Source

Score

0.75

Scicode

Measured Jul 10, 2026Source

Score

0.53

Hle

Measured Jul 10, 2026Source

Score

0.4

Gpqa

Measured Jul 10, 2026Source

Score

0.92

Artificial Analysis Intelligence Index

Measured Jul 10, 2026Source

Score

44.3

Plan availability

Products and plans that support this model

4
Apertis Coding Plan

Apertis Coding Plan

Apertis Coding Plan is a subscription-based AI coding service providing unified access to 30+ AI models (GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro, and more) through a single API key. Designed for developers using coding agents like Claude Code, Cursor, Cline, and OpenCode, it offers predictable monthly pricing, free prompt caching, auto-failover, and quota-based billing across OpenAI, Anthropic, Google, and other providers.

User ratings

Loading ratings...

Discussion

Thinking... Make sure you are connected to GitHub server