Model Details
Where is o1 a perfect fit?
- Complex math, science, and multi-step reasoning tasks.
- High-accuracy code generation, verification, and debugging workflows.
- Research-grade analysis where chain-of-thought style reasoning improves outcomes.
- Situations where correctness matters more than raw speed or cost.
Quick Model Estimate
Your o1 Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
Cost Breakdown
Prices are watched for changes and checked against the provider's own page.
Pricing
Other Models in the o1 Family
FAQs about o1
How much does o1 cost per 1M tokens?
o1 costs between $7.50 and $15.00 per million input tokens, and between $30.00 and $60.00 per million output tokens. The range covers Standard and Batch pricing.
What does a typical workload cost with o1?
1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $30.00 with o1 at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use o1?
o1 is available through OpenAI, from $7.50 per million input tokens.
Is there cheaper o1 pricing than the standard rate?
Yes. Batch pricing for o1 starts at $7.50 per million input tokens against $15.00 on the standard tier, about 50% lower.
What is o1's context window?
o1 has a context window of 200,000 tokens, and returns up to 100,000 tokens in a single response.
Is o1 still available?
o1 is a legacy model and is scheduled for retirement on 23 October 2026. The replacement is GPT-5.6 Sol.