o1 pricing
The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1). This page tracks 5 listings in total. Highlighted lows are $15.00 per million input and $60.00 per million output (see table for which seller matches each).
Pricing across providers
Use this table to read o1 list prices. We show 5 sources right now. Lowest input in the grid: Openrouter. The chart below the table helps when output prices are much higher than input prices.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $15.00 | $60.00 | $7.50 | — |
A Azure | $15.00 | $60.00 | $7.50 | — |
VA Vercel Ai Gateway | $15.00 | $60.00 | $7.50 | — |
R Replicate | $15.00 | $60.00 | — | — |
O OpenAInative | $15.00 | $60.00 | $7.50 | — |
Input vs output · per provider
Cost calculator
Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for o1.
Provider
1.500000¢ / req
3.000000¢ / req
Model specifications
Context length, caps, and capability flags for o1. Family: o1. Values follow the main provider (OpenAI) record in our index.
- Context window
- 200,000 tokens
- Max output
- 100,000 tokens
- Vision (images)
- Yes
- Tool / function calling
- Yes
- Streaming
- No
- Released
- Dec 2024
- Primary provider
- OpenAI
- Model family
- o1
Compare o1
These links open full side by side pages for o1. We picked pairs that people often shop together. 6 ready to open.
Frequently asked questions
Quick frequently asked items for o1 pricing and limits. The short model note from our index: The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. ...
Also from OpenAI
Other models by OpenAI with live pricing in our catalog.