OpenAI Inc.
o4-mini-deep-research
Optimized for fast reasoning and minimal latency, O4 Mini Deep Research supports caching and high-speed inference. Ideal for lightweight agent use.
👁Vision🧠Reasoning🔧Tool calling⚡Caching
Pricing per 1M tokens
Input
$2.00
Output
$8.00
Cache write
$2.00
Cache read
$0.50
Specifications
Context window100K tokens
Max output200K tokens
API typechat
AddedJul 17, 2025
Model IDopenai/o4-mini-deep-research
Privacy & data
Data retentionYes (30 days)
Used for trainingNo
Provider location🇺🇸 US
Privacy policyOpenAI Privacy Policy →