Compare models
GPT-5.4
Best intelligence at scale for agentic, coding, and professional workflows
Reasoning
Speed
Input
Output
Reasoning tokens
Pricing
Per 1M tokens
Input
$2.50
Cached Input
$0.25
Output
$15.00
Context
Window
1,050,000
Max Output Tokens
128,000
Knowledge Cutoff
Aug 31, 2025
Endpoints
v1/chat/completions
v1/responses
v1/batch
Supported Features
Streaming
Function calling
Structured outputs
Distillation
Image input
Rate Limits
TPM
Free
-
Tier 1
500,000
Tier 2
1,000,000
Tier 3
2,000,000
Tier 4
4,000,000
Tier 5
40,000,000
GPT-5.4 mini
Our strongest mini model yet for coding, computer use, and subagents
Reasoning
Speed
Input
Output
Reasoning tokens
Pricing
Per 1M tokens
Input
$0.75
Cached Input
$0.08
Output
$4.50
Context
Window
400,000
Max Output Tokens
128,000
Knowledge Cutoff
Aug 31, 2025
Endpoints
v1/chat/completions
v1/responses
v1/batch
Supported Features
Streaming
Function calling
Structured outputs
Distillation
Image input
Rate Limits
TPM
Free
-
Tier 1
500,000
Tier 2
2,000,000
Tier 3
4,000,000
Tier 4
10,000,000
Tier 5
180,000,000