---
id: "openai/o1"
also: ["openai/o1-2024-12-17", "requesty/openai/o1", "vercel/openai/o1"]
card_usd_per_m: "15.0 in, 60.0 out, at openai"
cheapest_list_usd_per_m: "15.0 in, 60.0 out, at openai on openrouter"
cheapest_effective_usd_per_m: "10.5977 in, 60.0 out, at openai on vercel"
context: 200000
max_output: 100000
input: ["text", "image", "file"]
output: ["text"]
released: "2024-12-17"
params: ["include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "tool_choice", "tools"]
endpoints: 4
gateways: "vercel (2), openrouter (1), requesty (1)"
no_training: 3
trains: 0
retains_prompts: 2
intelligence: 15.2000
coding: 39.7000
---
# OpenAI: o1

The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user. The o1 reasoning model is designed to solve hard problems across domains. The knowledge cutoff for o1 and o1-mini models is October, 2023.