OpenAI
GPT-4o token cost
Legacy multimodal OpenAI chat model still available on the API price list.
Published list rates
Input
$2.50
per 1M tokens
Output
$10.00
per 1M tokens
Cached input
$1.25
per 1M tokens
Context window
128,000
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
Read down to see GPT-4o get more expensive as tokens grow. The last column is a typical mix: 70% input, 30% output.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.000002 | $0.00001 | $0.000005 |
| 10 | $0.000025 | $0.0001 | $0.000048 |
| 100 | $0.00025 | $0.001 | $0.000475 |
| 200 | $0.0005 | $0.002 | $0.00095 |
| 300 | $0.00075 | $0.003 | $0.001425 |
| 400 | $0.001 | $0.004 | $0.0019 |
| 500 | $0.00125 | $0.005 | $0.002375 |
| 1,000 | $0.0025 | $0.01 | $0.00475 |
| 2,000 | $0.005 | $0.02 | $0.0095 |
| 5,000 | $0.0125 | $0.05 | $0.02375 |
| 10,000 | $0.025 | $0.1 | $0.0475 |
| 25,000 | $0.0625 | $0.25 | $0.11875 |
| 50,000 | $0.125 | $0.5 | $0.2375 |
| 100,000 | $0.25 | $1.00 | $0.475 |
| 250,000 | $0.625 | $2.50 | $1.1875 |
| 500,000 | $1.25 | $5.00 | $2.375 |
| 1,000,000 | $2.50 | $10.00 | $4.75 |
| 5,000,000 | $12.50 | $50.00 | $23.75 |
| 10,000,000 | $25.00 | $100.00 | $47.50 |
| 50,000,000 | $125.00 | $500.00 | $237.50 |
| 100,000,000 | $250.00 | $1,000.00 | $475.00 |
| 500,000,000 | $1,250.00 | $5,000.00 | $2,375.00 |
| 1,000,000,000 | $2,500.00 | $10,000.00 | $4,750.00 |
| 10,000,000,000 | $25,000.00 | $100,000.00 | $47,500.00 |
| 100,000,000,000 | $250,000.00 | $1,000,000.00 | $475,000.00 |
Tokens for a fixed budget
Tokens GPT-4o can process for a set budget — send-only, reply-only, and a 70/30 mix.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 4,000 | 1,000 | 2,105 |
| $0.1 | 40,000 | 10,000 | 21,053 |
| $0.5 | 200,000 | 50,000 | 105,263 |
| $1.00 | 400,000 | 100,000 | 210,526 |
| $5.00 | 2M | 500,000 | 1.05M |
| $10.00 | 4M | 1M | 2.11M |
| $20.00 | 8M | 2M | 4.21M |
| $25.00 | 10M | 2.5M | 5.26M |
| $30.00 | 12M | 3M | 6.32M |
| $50.00 | 20M | 5M | 10.5M |
| $100.00 | 40M | 10M | 21.1M |
| $250.00 | 100M | 25M | 52.6M |
| $500.00 | 200M | 50M | 105.3M |
| $1,000.00 | 400M | 100M | 210.5M |
| $5,000.00 | 2B | 500M | 1.05B |
| $10,000.00 | 4B | 1B | 2.11B |
At these rates
- A workload with 70% input and 30% output costs $4.75 per 1 million total tokens and $475.00 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 128,000-token context window with input alone would cost about $0.32, before any output.
- Cached input is $1.25 per million, 50% 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.