---
id: "openai/o3-pro"
also: ["openai/o3-pro-2025-06-10", "requesty/openai/o3-pro", "vercel/openai/o3-pro"]
card_usd_per_m: "20.0 in, 80.0 out, at openai"
cheapest_list_usd_per_m: "20.0 in, 80.0 out, at openai on openrouter"
cheapest_effective_usd_per_m: "20.0 in, 80.0 out, at openai on openrouter"
context: 200000
max_output: 100000
input: ["text", "file", "image"]
output: ["text"]
released: "2025-06-10"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools"]
endpoints: 4
gateways: "requesty (2), openrouter (1), vercel (1)"
no_training: 4
trains: 0
retains_prompts: 3
---
# OpenAI: o3 Pro

The o3 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.