Models

GPT-5.5 (xhigh)

OpenAIOpenAIUnited States

GPT-5.5 (xhigh) is a high-performance variant of OpenAI's GPT-5 series, optimized for superior reasoning, complex code generation, and advanced multimodal tasks. It represents a flagship model designed for demanding applications requiring top-tier intelligence and capability.

CodingReasoningMultimodal
Input / 1M tokens
$5.00
Output / 1M tokens
$30.00
Output tokens/s
68.25
First-token seconds
46.82s
Supported plans
25

Benchmark history

Evaluations

9

TAU2

Measured May 14, 2026Source

Score

0.94

Terminalbench Hard

Measured May 14, 2026Source

Score

0.61

Lcr

Measured May 14, 2026Source

Score

0.74

Ifbench

Measured May 14, 2026Source

Score

0.76

Scicode

Measured May 14, 2026Source

Score

0.56

Hle

Measured May 14, 2026Source

Score

0.44

Gpqa

Measured May 14, 2026Source

Score

0.94

Artificial Analysis Coding Index

Measured May 14, 2026Source

Score

59.1

Artificial Analysis Intelligence Index

Measured May 14, 2026Source

Score

60.2

Plan availability

Products and plans that support this model

6
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.

Discussion

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