OpenAI model
o1 API cost calculator
o1 costs $15 per 1M input tokens and $60 per 1M output tokens on the OpenAI API, with a 200K-token context window. A typical request (2K input, 500 output tokens) costs $0.06 — about $1,800/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on o1
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.03 | $25.50 |
| RAG query with context | 4,000 / 500 | $0.09 | $90.00 |
| Document summarization | 20,000 / 1,000 | $0.36 | $360 |
| Agent coding session | 100,000 / 5,000 | $1.80 | $1,800 |
o1 vs other OpenAI models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| o1 | $15 | $60 | 200K |
| GPT-5.6 Luna Pro | $0.20 | $1.20 | 1.1M |
| GPT-5.6 Luna | $0.20 | $1.20 | 1.1M |
| GPT-5.6 Terra Pro | $2 | $12 | 1.1M |
| GPT-5.6 Terra | $2 | $12 | 1.1M |
Frequently asked questions
How much does o1 cost per 1M tokens?
According to current pricing data, o1 costs $15 per 1M input tokens and $60 per 1M output tokens. Processing 1M tokens each way costs $75.00.
What does a typical API request to o1 cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.06. At 1,000 requests per day that is $60.00 daily, or about $1,800 per month.
What is o1's context window?
o1 supports a 200K-token context window (200,000 tokens).
Does o1 support prompt caching?
Yes. Cached input tokens cost $7.50 per 1M — a 50% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to o1?
Ling-2.6-flash from Inclusionai is currently the cheapest comparable option at $0.01 per 1M input tokens versus $15 for o1 — roughly 1500x cheaper on input.
Prices may differ from OpenAI's official pricing page for batch, tiered, or fine-tuned usage. Compare all current prices on the live model pricing dashboard, see o1 vs Ling-2.6-flash pricing, or run o1 head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.