---
id: "openai/o3"
also: ["openai/o3-2025-04-16", "requesty/openai/o3", "vercel/openai/o3"]
card_usd_per_m: "2.0 in, 8.0 out, at openai"
cheapest_list_usd_per_m: "2.0 in, 8.0 out, at openai on openrouter"
cheapest_effective_usd_per_m: "1.4542 in, 8.0 out, at openai on requesty"
context: 200000
max_output: 100000
input: ["image", "text", "file"]
output: ["text"]
released: "2025-04-16"
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", "tool_choice", "tools"]
endpoints: 3
gateways: "openrouter (1), requesty (1), vercel (1)"
no_training: 3
trains: 0
retains_prompts: 2
---
# OpenAI: o3

OpenAI's o3 is their most powerful reasoning model, setting new state-of-the-art benchmarks in coding, math, science, and visual perception. It excels at complex queries requiring multi-faceted analysis, with particular strength in analyzing images, charts, and graphics.