Back to every model

OpenAI

o3 API pricing and specs

OpenAI's o3: price per million tokens, context window, limits and capabilities, re-read from OpenRouter's model feed every 6 hours.

Input

$2

Output

$8

Context

200K

o3 costs $2 per million input tokens and $8 per million output tokens. Cached input is billed at $0.50 per million, 75% less than fresh input.

Specifications

LabOpenAI
Model idopenai/o3
Input price$2 per million tokens
Output price$8 per million tokens
Cached input price$0.50 per million tokens
Context window200,000 tokens (200K)
Maximum output100,000 tokens (100K)
Tool callingyes
Image inputyes
Reasoningyes
First listed16 April 2025

OpenAI's other models

ModelInput / 1MOutput / 1MContextListed
GPT-6.1 Terra$1$51.05M26 October 2026
GPT-6.1 Terra Pro$1$51.05M26 October 2026
GPT-6.1 Sol$2$101.05M29 September 2026
GPT-6.1 Sol Pro$2$101.05M29 September 2026
GPT-6 Luna$0.10$0.501.05M22 September 2026
GPT-6 Luna Pro$0.10$0.501.05M22 September 2026
GPT-6 Sol Pro$2$101.05M22 September 2026
GPT-6 Astra$10$501.05M4 September 2026
GPT-6 Astra Pro$10$501.05M4 September 2026
GPT-5.6 Luna$0.20$1.201.05M9 July 2026
GPT-5.6 Luna Pro$0.20$1.201.05M9 July 2026
GPT-5.6 Sol Pro$4$201.05M9 July 2026

Where these numbers come from

Read from OpenRouter's listing of o3 every 6 hours into the catalog Founden's builders choose their models from. Prices are OpenRouter's listed price per million tokens: for a lab's closed models that is the lab's own list price, and for an open-weight model it is the price of the host OpenRouter routes to by default, which can differ from the lab's own API and from other hosts. US dollars, before batch, volume or regional discounts. Every model.