Primary navigation

Legacy APIs

Models

Choosing a model

If you're not sure where to start, use gpt-5.4, our flagship model for complex reasoning and coding. If you're optimizing for latency and cost, choose a smaller variant like gpt-5.4-mini or gpt-5.4-nano.

All latest OpenAI models support text and image input, text output, multilingual capabilities, and vision. Models are available via the Responses API and our Client SDKs.

Frontier models

Start with gpt-5.4 for complex reasoning and coding, or choose gpt-5.4-mini and gpt-5.4-nano for lower-latency, lower-cost workloads.
GPT-5.4
New
Best intelligence at scale for agentic, coding, and professional workflows
Model ID
gpt-5.4
nonelowmediumhighxhigh
Input price
$2.50 / Input MTok
Output price
$15 / Output MTok
Latency
Fast
Max output
128K tokens
Context window
1M
Functions, Web search, File search, Computer use
Knowledge cutoff
Aug 31, 2025
GPT-5.4 mini
New
Our strongest mini model yet for coding, computer use, and subagents
Model ID
gpt-5.4-mini
nonelowmediumhighxhigh
Input price
$0.75 / Input MTok
Output price
$4.50 / Output MTok
Latency
Faster
Max output
128K tokens
Context window
400K
Functions, Web search, File search, Computer use
Knowledge cutoff
Aug 31, 2025
GPT-5.4 nano
New
Our cheapest GPT-5.4-class model for simple high-volume tasks
Model ID
gpt-5.4-nano
nonelowmediumhighxhigh
Input price
$0.20 / Input MTok
Output price
$1.25 / Output MTok
Latency
Faster
Max output
128K tokens
Context window
400K
Functions, Web search, File search, MCP
Knowledge cutoff
Aug 31, 2025

Browse our full catalog of models

Diverse models for a variety of tasks