o1 vs o3
Sample workload: short support reply (~512 output tokens). Open the calculator for your own prompt.
| Field | o1 | o3 |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Accuracy | Exact | Exact |
| Input / 1M | $15.00/1M | $2.00/1M |
| Output / 1M | $60.00/1M | $8.00/1M |
| Sample input tokens | 16 | 16 |
| Sample request cost | $0.03096 | $0.004128 |
| Pages | Model page | Model page |
Try your own prompt
Sample costs above use a fixed support-chat prompt. For your text, open the main calculator with either model preselected.
o1 in calculator · o3 in calculator · Count tokens (o1) · Count tokens (o3) · All comparisons
Related tools
LLM cost calculator · Cheapest LLM API · Cache savings · Batch pricing
Related guides
How LLM API pricing works · How prompt cost is calculated · Prompt caching explained · Exact vs Approx
Sources and references
Official documentation used for definitions, counting methods, or rate cards. Always confirm critical budgets on the provider page.