GPT-5.5

reasoningproprietary

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
Snapshotsgpt-5.5-2026-04-23

Capabilities

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

Details

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

Tools

Function Callingfunction_calling
Call external functions and APIs
Web Searchweb_search
Search the web for information
File Searchfile_search
Search across uploaded files
Tool Searchtool_search
Discover and use tools
Image Generationimage_generation
Generate images inline
Code Interpretercode_interpreter
Execute code in a sandbox
Hosted Shellhosted_shell
Run shell commands in a container
Apply Patchapply_patch
Apply code patches to files
Skillsskills
Use built-in skill modules
Computer Usecomputer_use
Control a virtual desktop
MCPmcp
Connect to Model Context Protocol servers

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.openai.com/v1/chat/completions
ResponsesPOST
Stateful multi-turn conversationshttps://api.openai.com/v1/responses
BatchPOST
Async batch processing at lower costhttps://api.openai.com/v1/batches

Pricing

Text tokensPer 1M tokens
InputOutputCached input30m write12h write
Standard$5$30$0.5——
Batch$2.5$15$0.25——
Fast$12.5$75$1.25——

For GPT-5.5, prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.

Regional processing (data residency) endpoints are charged a 10% uplift for GPT-5.5.

Family Comparison: gpt-5.5

ModelContextMax outPricing
GPT-5.51.1M128K$5$30
GPT-5.5 Pro1.1M128K$30$180

API

GET/v1/models/openai/gpt-5.5

GPT-5.5

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.

gpt-5.5-2026-04-23
Changes · 5 entries
gpt-5.5updateca7a400Nov 2, 2026, 03:02 AM
descriptionGPT-5.5 is our newest frontier model for the most complex...→GPT-5.5 is a flagship model for the most complex professi...
model_typechat→reasoning
page_urlhttps://developers.openai.com/api/docs/models/gpt-5.5?sna...→https://developers.openai.com/api/docs/models/gpt-5.5
pricingtiers[{"label":"Text tokens","unit":"Per 1M tokens","columns":...→[{"label":"Text tokens","unit":"Per 1M tokens","columns":...
tools["function_calling"]→["function_calling","web_search","file_search","tool_sear...
endpoints["responses","chat_completions","batch"]→["chat_completions","responses","batch"]
gpt-5.5update4e8b6afOct 21, 2026, 06:35 AM
pricingtiers[{"label":"Text tokens","unit":"Per 1M tokens","columns":...→[{"label":"Text tokens","unit":"Per 1M tokens","columns":...
gpt-5.5update118451aSep 24, 2026, 07:08 AM
descriptionGPT-5.5 is a flagship model for the most complex professi...→GPT-5.5 is a flagship model for the most complex professi...
pricingtiers[{"label":"Text tokens","unit":"Per 1M tokens","columns":...→[{"label":"Text tokens","unit":"Per 1M tokens","columns":...
endpoints["responses","chat_completions","batch"]→["chat_completions","responses","batch"]
gpt-5.5updatee3d7dedAug 31, 2026, 04:13 AM
descriptionGPT-5.5 is our newest frontier model for the most complex...→GPT-5.5 is a flagship model for the most complex professi...
model_typechat→reasoning
page_urlhttps://developers.openai.com/api/docs/models/gpt-5.5?sna...→https://developers.openai.com/api/docs/models/gpt-5.5
tools["function_calling"]→["function_calling","web_search","file_search","tool_sear...
gpt-5.5createc8065d6Apr 25, 2026, 10:39 AM