GPT-5.5

proprietary

GPT-5.5 is a flagship model for the most complex professional work. Learn more in our GPT-5.5 model guidance. Reasoning.effort supports: none, low, medium (default), high and xhigh.

Intelligence
Reasoning
Speed
Context
1.1M
Max output
128K
Input price
$5/1M tokens
Output price
$30/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Provider Perplexity
Creator OpenAI
Familygpt-5.5
Licenseproprietary
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window1.1M tokens
Max input—
Max output128K tokens
Reasoning tokensYes
Knowledge cutoff
Release date
Sourceofficial

Pricing

Input
$5
Output
$30
Cache write
—
Cache read
$0.5
Batch in
—
Batch out
—

Input: 5.00 (≤272k) 10.00 (>272k); Output: 30.00 (≤272k) 45.00 (>272k) per 1M tokens.

API

GET/v1/models/perplexity/openai/gpt-5.5