← All models
O

o1

OpenAI

OpenAI's original frontier reasoning model — deep thinking for the hardest problems

Input price$15.00 / 1M tokens
Output price$60.00 / 1M tokens
Context window200k tokens
Last updated2026-04-22

Quick calculator

tokens
tokens
req/day
Per request
$0.0450
Daily
$450.00
Monthly
$13,500.00
per month · 30-day estimate
Yearly
$164,250.00

Tips to reduce cost

  • Use prompt caching to reuse repeated system prompts
  • Trim whitespace and reduce verbose instructions
  • Use a smaller model for classification or routing tasks
  • Batch async requests to get 50% discount (OpenAI/Anthropic)
  • Cache identical requests at the application layer

Similar models from OpenAI

Compared at your current token settings

About o1

o1 is a premium large language model from openai, priced at $15/1M input tokens and $60/1M output tokens. It is priced above the market average and best suited for hard reasoning problems. The 200k context window handles long documents, extended conversations, and large code files comfortably.

As a reasoning model, o1 generates internal thinking tokens before responding. These are billed at the output token rate and can add 2–8x to effective output cost. For tasks requiring deep reasoning — math, complex coding, multi-step analysis — this overhead is usually justified by fewer errors and retries.

o1 supports prompt caching at $7.5/1M — a 50% discount on repeated input tokens. For applications with a fixed system prompt or repeated document context (RAG, chatbots, agents), enabling caching is the single highest-leverage cost optimization available.

Frequently Asked Questions

How much does o1 cost per 1,000 tokens?
o1 costs $0.0150 per 1,000 input tokens and $0.0600 per 1,000 output tokens.
What is o1's context window?
o1 supports a context window of 200k tokens, which is suitable for long documents and multi-turn conversations.
How does o1 compare to GPT-4o on price?
o1 is priced above the market average on input tokens. At $15/1M input vs $2.50/1M for GPT-4o, the cost difference becomes significant at scale — 10,000 requests/day with 1,000 input tokens each costs $4500/month with o1 vs $750/month with GPT-4o.
Does o1 support prompt caching?
Yes. o1 supports prompt caching at $7.5/1M tokens — a 50% discount on repeated input. This is especially effective for RAG pipelines and chatbots with large system prompts that repeat across requests.

Compare o1 with other models

o1 vs Claude Opus 4.5o1 vs Claude 3 Opuso1 vs Claude Fable 5o1 vs Gemini 3 Ultrao1 vs Claude Opus 4.8o1 vs Claude Opus 4.7