Mistral
Ministral 8B token cost
Ministral 8B edge tier at a flat $0.15 per 1M input and output for compact production text.
Published list rates
Input
$0.15
per 1M tokens
Output
$0.15
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
- —
- 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 Ministral 8B 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 | $0.00000015 | $0.00000015 | $0.00000015 |
| 10 | $0.000002 | $0.000002 | $0.000001 |
| 100 | $0.000015 | $0.000015 | $0.000015 |
| 200 | $0.00003 | $0.00003 | $0.00003 |
| 300 | $0.000045 | $0.000045 | $0.000045 |
| 400 | $0.00006 | $0.00006 | $0.00006 |
| 500 | $0.000075 | $0.000075 | $0.000075 |
| 1,000 | $0.00015 | $0.00015 | $0.00015 |
| 2,000 | $0.0003 | $0.0003 | $0.0003 |
| 5,000 | $0.00075 | $0.00075 | $0.00075 |
| 10,000 | $0.0015 | $0.0015 | $0.0015 |
| 25,000 | $0.00375 | $0.00375 | $0.00375 |
| 50,000 | $0.0075 | $0.0075 | $0.0075 |
| 100,000 | $0.015 | $0.015 | $0.015 |
| 250,000 | $0.0375 | $0.0375 | $0.0375 |
| 500,000 | $0.075 | $0.075 | $0.075 |
| 1,000,000 | $0.15 | $0.15 | $0.15 |
| 5,000,000 | $0.75 | $0.75 | $0.75 |
| 10,000,000 | $1.50 | $1.50 | $1.50 |
| 50,000,000 | $7.50 | $7.50 | $7.50 |
| 100,000,000 | $15.00 | $15.00 | $15.00 |
| 500,000,000 | $75.00 | $75.00 | $75.00 |
| 1,000,000,000 | $150.00 | $150.00 | $150.00 |
| 10,000,000,000 | $1,500.00 | $1,500.00 | $1,500.00 |
| 100,000,000,000 | $15,000.00 | $15,000.00 | $15,000.00 |
Tokens for a fixed budget
How far a fixed spend goes on Ministral 8B at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 66,667 | 66,667 | 66,667 |
| $0.1 | 666,667 | 666,667 | 666,667 |
| $0.5 | 3.33M | 3.33M | 3.33M |
| $1.00 | 6.67M | 6.67M | 6.67M |
| $5.00 | 33.3M | 33.3M | 33.3M |
| $10.00 | 66.7M | 66.7M | 66.7M |
| $20.00 | 133.3M | 133.3M | 133.3M |
| $25.00 | 166.7M | 166.7M | 166.7M |
| $30.00 | 200M | 200M | 200M |
| $50.00 | 333.3M | 333.3M | 333.3M |
| $100.00 | 666.7M | 666.7M | 666.7M |
| $250.00 | 1.67B | 1.67B | 1.67B |
| $500.00 | 3.33B | 3.33B | 3.33B |
| $1,000.00 | 6.67B | 6.67B | 6.67B |
| $5,000.00 | 33.3B | 33.3B | 33.3B |
| $10,000.00 | 66.7B | 66.7B | 66.7B |
At these rates
- A workload with 70% input and 30% output costs $0.15 per 1 million total tokens and $15.00 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 $0.0192, 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.