OpenAI · Pricing & cost calculator

o1 pricing

OpenAI's heavy reasoning model. Expensive output tokens — use sparingly.

Input tokens

$0.01500

per 1,000 tokens

Output tokens

$0.06000

per 1,000 tokens

Context window

200,000

tokens max

Prices sourced from OpenAI's public API rate card. Last reviewed April 2026.

Calculate your o1 spend

Drag the sliders. The math runs in your browser.

Per request

$0.052500

at 1,500/500 tokens

Monthly spend

$525

10,000 requests × $0.052500

Could save ~80% with a similar-quality alternative

Switch from o1 to o1-mini and save $420.00/month

Same workload at 1,500/500 tokens × 10,000 req/month: $525 $105. 5× cheaper input, 5× cheaper output.

TrackCost's gateway auto-detects which requests are safe to route to the cheaper model and flags the ones that need o1's full capability. You stay in control — we surface the opportunity.

When should you use o1?

  • Math proofs
  • Complex debugging
  • Research

o1 pricing FAQ

How much does o1 cost per 1,000 tokens?

o1 costs $0.01500 per 1,000 input tokens and $0.06000 per 1,000 output tokens as of the current OpenAI API pricing.

What is a cheaper alternative to o1?

o1-mini is significantly cheaper than o1 (5× cheaper input, 5× cheaper output) and often works fine for tasks that don't need o1's full capability. TrackCost automatically suggests model downgrades where safe.

How can I reduce my o1 API costs?

The three highest-leverage ways: (1) route requests to a cheaper model where possible, (2) cache identical requests so you don't pay twice for the same response, (3) set hard monthly budgets that block requests when exceeded. TrackCost automates all three at the gateway layer.

What's the context window for o1?

o1 supports up to 200,000 tokens of context. For comparison with other models, use the TrackCost savings calculator.

Compare pricing across other models