OpenAI
o4-mini token cost
Budget OpenAI reasoning model for math, coding, and agent loops.
Published list rates
Input
$1.10
per 1M tokens
Output
$4.40
per 1M tokens
Cached input
$0.275
per 1M tokens
Context window
200,000
tokens
Pricing source: OpenAI API pricing
Estimate cost
Estimate from text
Calculate from a token total
Project monthly volume
Daily requests × tokens per request × 30 days.
Estimated cost
- Estimated tokens
- —
- Characters
- —
- Words
- —
- Input tokens
- —
- Output tokens
- —
- Input cost
- —
- Output cost
- —
- Total cost
- —
- Combined price per 1M tokens
- —
- Estimated monthly cost
- —
- Estimated daily cost
- —
Cost as volume grows
What o4-mini costs if you only send tokens, only get a reply, or do both (70% in / 30% out). Rows start small and go up to huge traffic.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.000001 | $0.000004 | $0.000002 |
| 10 | $0.000011 | $0.000044 | $0.000021 |
| 100 | $0.00011 | $0.00044 | $0.000209 |
| 200 | $0.00022 | $0.00088 | $0.000418 |
| 300 | $0.00033 | $0.00132 | $0.000627 |
| 400 | $0.00044 | $0.00176 | $0.000836 |
| 500 | $0.00055 | $0.0022 | $0.001045 |
| 1,000 | $0.0011 | $0.0044 | $0.00209 |
| 2,000 | $0.0022 | $0.0088 | $0.00418 |
| 5,000 | $0.0055 | $0.022 | $0.01045 |
| 10,000 | $0.011 | $0.044 | $0.0209 |
| 25,000 | $0.0275 | $0.11 | $0.05225 |
| 50,000 | $0.055 | $0.22 | $0.1045 |
| 100,000 | $0.11 | $0.44 | $0.209 |
| 250,000 | $0.275 | $1.10 | $0.5225 |
| 500,000 | $0.55 | $2.20 | $1.045 |
| 1,000,000 | $1.10 | $4.40 | $2.09 |
| 5,000,000 | $5.50 | $22.00 | $10.45 |
| 10,000,000 | $11.00 | $44.00 | $20.90 |
| 50,000,000 | $55.00 | $220.00 | $104.50 |
| 100,000,000 | $110.00 | $440.00 | $209.00 |
| 500,000,000 | $550.00 | $2,200.00 | $1,045.00 |
| 1,000,000,000 | $1,100.00 | $4,400.00 | $2,090.00 |
| 10,000,000,000 | $11,000.00 | $44,000.00 | $20,900.00 |
| 100,000,000,000 | $110,000.00 | $440,000.00 | $209,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many o4-mini tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 9,091 | 2,273 | 4,785 |
| $0.1 | 90,909 | 22,727 | 47,847 |
| $0.5 | 454,545 | 113,636 | 239,234 |
| $1.00 | 909,091 | 227,273 | 478,469 |
| $5.00 | 4.55M | 1.14M | 2.39M |
| $10.00 | 9.09M | 2.27M | 4.78M |
| $20.00 | 18.2M | 4.55M | 9.57M |
| $25.00 | 22.7M | 5.68M | 12M |
| $30.00 | 27.3M | 6.82M | 14.4M |
| $50.00 | 45.5M | 11.4M | 23.9M |
| $100.00 | 90.9M | 22.7M | 47.8M |
| $250.00 | 227.3M | 56.8M | 119.6M |
| $500.00 | 454.5M | 113.6M | 239.2M |
| $1,000.00 | 909.1M | 227.3M | 478.5M |
| $5,000.00 | 4.55B | 1.14B | 2.39B |
| $10,000.00 | 9.09B | 2.27B | 4.78B |
At these rates
- A workload with 70% input and 30% output costs $2.09 per 1 million total tokens and $209.00 per 100 million.
- At the same token count, output costs 4 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 200,000-token context window with input alone would cost about $0.22, before any output.
- Cached input is $0.275 per million, 75% below standard input when the workload meets the provider’s cache rules.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.