OpenAI
GPT-4.1 nano token cost
Cheapest OpenAI model on the price sheet for bulk routing, classification, and extraction.
Published list rates
Input
$0.1
per 1M tokens
Output
$0.4
per 1M tokens
Cached input
$0.01
per 1M tokens
Context window
1,000,000
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-4.1 nano 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 | $0.0000001 | $0.0000004 | $0.00000019 |
| 10 | $0.000001 | $0.000004 | $0.000002 |
| 100 | $0.00001 | $0.00004 | $0.000019 |
| 200 | $0.00002 | $0.00008 | $0.000038 |
| 300 | $0.00003 | $0.00012 | $0.000057 |
| 400 | $0.00004 | $0.00016 | $0.000076 |
| 500 | $0.00005 | $0.0002 | $0.000095 |
| 1,000 | $0.0001 | $0.0004 | $0.00019 |
| 2,000 | $0.0002 | $0.0008 | $0.00038 |
| 5,000 | $0.0005 | $0.002 | $0.00095 |
| 10,000 | $0.001 | $0.004 | $0.0019 |
| 25,000 | $0.0025 | $0.01 | $0.00475 |
| 50,000 | $0.005 | $0.02 | $0.0095 |
| 100,000 | $0.01 | $0.04 | $0.019 |
| 250,000 | $0.025 | $0.1 | $0.0475 |
| 500,000 | $0.05 | $0.2 | $0.095 |
| 1,000,000 | $0.1 | $0.4 | $0.19 |
| 5,000,000 | $0.5 | $2.00 | $0.95 |
| 10,000,000 | $1.00 | $4.00 | $1.90 |
| 50,000,000 | $5.00 | $20.00 | $9.50 |
| 100,000,000 | $10.00 | $40.00 | $19.00 |
| 500,000,000 | $50.00 | $200.00 | $95.00 |
| 1,000,000,000 | $100.00 | $400.00 | $190.00 |
| 10,000,000,000 | $1,000.00 | $4,000.00 | $1,900.00 |
| 100,000,000,000 | $10,000.00 | $40,000.00 | $19,000.00 |
Tokens for a fixed budget
Tokens GPT-4.1 nano 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 | 100,000 | 25,000 | 52,632 |
| $0.1 | 1M | 250,000 | 526,316 |
| $0.5 | 5M | 1.25M | 2.63M |
| $1.00 | 10M | 2.5M | 5.26M |
| $5.00 | 50M | 12.5M | 26.3M |
| $10.00 | 100M | 25M | 52.6M |
| $20.00 | 200M | 50M | 105.3M |
| $25.00 | 250M | 62.5M | 131.6M |
| $30.00 | 300M | 75M | 157.9M |
| $50.00 | 500M | 125M | 263.2M |
| $100.00 | 1B | 250M | 526.3M |
| $250.00 | 2.5B | 625M | 1.32B |
| $500.00 | 5B | 1.25B | 2.63B |
| $1,000.00 | 10B | 2.5B | 5.26B |
| $5,000.00 | 50B | 12.5B | 26.3B |
| $10,000.00 | 100B | 25B | 52.6B |
At these rates
- A workload with 70% input and 30% output costs $0.19 per 1 million total tokens and $19.00 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 1,000,000-token context window with input alone would cost about $0.1, before any output.
- Cached input is $0.01 per million, 90% 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.