Mistral
Ministral 14B token cost
Largest Ministral 3 edge model at $0.20/$0.20 when you want more headroom without jumping to Small 4.
Published list rates
Input
$0.2
per 1M tokens
Output
$0.2
per 1M tokens
Context window
128,000
tokens
Pricing source: Mistral 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
- 100,000
- Characters
- 400,000
- Words
- 75,000
- Input tokens
- 70,000
- Output tokens
- 30,000
- Input cost
- $0.014
- Output cost
- $0.006
- Total cost
- $0.02
- Combined price per 1M tokens
- $0.2
- Estimated monthly cost
- $12.00
- Estimated daily cost
- $0.4
Cost as volume grows
Three views of Ministral 14B: 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 | $0.0000002 | $0.0000002 | $0.0000002 |
| 10 | $0.000002 | $0.000002 | $0.000002 |
| 100 | $0.00002 | $0.00002 | $0.00002 |
| 200 | $0.00004 | $0.00004 | $0.00004 |
| 300 | $0.00006 | $0.00006 | $0.00006 |
| 400 | $0.00008 | $0.00008 | $0.00008 |
| 500 | $0.0001 | $0.0001 | $0.0001 |
| 1,000 | $0.0002 | $0.0002 | $0.0002 |
| 2,000 | $0.0004 | $0.0004 | $0.0004 |
| 5,000 | $0.001 | $0.001 | $0.001 |
| 10,000 | $0.002 | $0.002 | $0.002 |
| 25,000 | $0.005 | $0.005 | $0.005 |
| 50,000 | $0.01 | $0.01 | $0.01 |
| 100,000 | $0.02 | $0.02 | $0.02 |
| 250,000 | $0.05 | $0.05 | $0.05 |
| 500,000 | $0.1 | $0.1 | $0.1 |
| 1,000,000 | $0.2 | $0.2 | $0.2 |
| 5,000,000 | $1.00 | $1.00 | $1.00 |
| 10,000,000 | $2.00 | $2.00 | $2.00 |
| 50,000,000 | $10.00 | $10.00 | $10.00 |
| 100,000,000 | $20.00 | $20.00 | $20.00 |
| 500,000,000 | $100.00 | $100.00 | $100.00 |
| 1,000,000,000 | $200.00 | $200.00 | $200.00 |
| 10,000,000,000 | $2,000.00 | $2,000.00 | $2,000.00 |
| 100,000,000,000 | $20,000.00 | $20,000.00 | $20,000.00 |
Tokens for a fixed budget
How far a fixed spend goes on Ministral 14B at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 50,000 | 50,000 | 50,000 |
| $0.1 | 500,000 | 500,000 | 500,000 |
| $0.5 | 2.5M | 2.5M | 2.5M |
| $1.00 | 5M | 5M | 5M |
| $5.00 | 25M | 25M | 25M |
| $10.00 | 50M | 50M | 50M |
| $20.00 | 100M | 100M | 100M |
| $25.00 | 125M | 125M | 125M |
| $30.00 | 150M | 150M | 150M |
| $50.00 | 250M | 250M | 250M |
| $100.00 | 500M | 500M | 500M |
| $250.00 | 1.25B | 1.25B | 1.25B |
| $500.00 | 2.5B | 2.5B | 2.5B |
| $1,000.00 | 5B | 5B | 5B |
| $5,000.00 | 25B | 25B | 25B |
| $10,000.00 | 50B | 50B | 50B |
At these rates
- A workload with 70% input and 30% output costs $0.2 per 1 million total tokens and $20.00 per 100 million.
- At the same token count, output costs 1 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 $0.0256, before any output.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.