---
id: "openai/o4-mini"
also: ["openai/o4-mini-2025-04-16", "requesty/openai/o4-mini", "vercel/openai/o4-mini"]
card_usd_per_m: "1.1 in, 4.4 out, at openai"
cheapest_list_usd_per_m: "1.1 in, 4.4 out, at openai on openrouter"
cheapest_effective_usd_per_m: "0.6952 in, 4.4 out, at openai-responses on requesty"
context: 200000
max_output: 100000
input: ["image", "text", "file"]
output: ["text"]
released: "2025-04-16"
params: ["include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "tool_choice", "tools"]
endpoints: 11
gateways: "requesty (8), vercel (2), openrouter (1)"
no_training: 10
trains: 0
retains_prompts: 3
intelligence: 16.7000
---
# OpenAI: o4 Mini

o4-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.