OpenAI
GPT-4.1 mini token cost
Long-context GPT-4.1 mini still listed for high-volume light workloads.
Published list rates
Input
$0.4
per 1M tokens
Output
$1.60
per 1M tokens
Cached input
$0.04
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
Three views of GPT-4.1 mini: sending only, receiving only, and a 70/30 mix. Same list rates, bigger rows.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.0000004 | $0.000002 | $0.00000076 |
| 10 | $0.000004 | $0.000016 | $0.000008 |
| 100 | $0.00004 | $0.00016 | $0.000076 |
| 200 | $0.00008 | $0.00032 | $0.000152 |
| 300 | $0.00012 | $0.00048 | $0.000228 |
| 400 | $0.00016 | $0.00064 | $0.000304 |
| 500 | $0.0002 | $0.0008 | $0.00038 |
| 1,000 | $0.0004 | $0.0016 | $0.00076 |
| 2,000 | $0.0008 | $0.0032 | $0.00152 |
| 5,000 | $0.002 | $0.008 | $0.0038 |
| 10,000 | $0.004 | $0.016 | $0.0076 |
| 25,000 | $0.01 | $0.04 | $0.019 |
| 50,000 | $0.02 | $0.08 | $0.038 |
| 100,000 | $0.04 | $0.16 | $0.076 |
| 250,000 | $0.1 | $0.4 | $0.19 |
| 500,000 | $0.2 | $0.8 | $0.38 |
| 1,000,000 | $0.4 | $1.60 | $0.76 |
| 5,000,000 | $2.00 | $8.00 | $3.80 |
| 10,000,000 | $4.00 | $16.00 | $7.60 |
| 50,000,000 | $20.00 | $80.00 | $38.00 |
| 100,000,000 | $40.00 | $160.00 | $76.00 |
| 500,000,000 | $200.00 | $800.00 | $380.00 |
| 1,000,000,000 | $400.00 | $1,600.00 | $760.00 |
| 10,000,000,000 | $4,000.00 | $16,000.00 | $7,600.00 |
| 100,000,000,000 | $40,000.00 | $160,000.00 | $76,000.00 |
Tokens for a fixed budget
Tokens GPT-4.1 mini 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 | 25,000 | 6,250 | 13,158 |
| $0.1 | 250,000 | 62,500 | 131,579 |
| $0.5 | 1.25M | 312,500 | 657,895 |
| $1.00 | 2.5M | 625,000 | 1.32M |
| $5.00 | 12.5M | 3.13M | 6.58M |
| $10.00 | 25M | 6.25M | 13.2M |
| $20.00 | 50M | 12.5M | 26.3M |
| $25.00 | 62.5M | 15.6M | 32.9M |
| $30.00 | 75M | 18.8M | 39.5M |
| $50.00 | 125M | 31.3M | 65.8M |
| $100.00 | 250M | 62.5M | 131.6M |
| $250.00 | 625M | 156.3M | 328.9M |
| $500.00 | 1.25B | 312.5M | 657.9M |
| $1,000.00 | 2.5B | 625M | 1.32B |
| $5,000.00 | 12.5B | 3.13B | 6.58B |
| $10,000.00 | 25B | 6.25B | 13.2B |
At these rates
- A workload with 70% input and 30% output costs $0.76 per 1 million total tokens and $76.00 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 $0.4, before any output.
- Cached input is $0.04 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.