IBM
Mistral Small 3.1 24B (watsonx.ai) token cost
Mistral Small 3.1 24B on watsonx.ai for low-cost European open routing.
Published list rates
Input
$0.106
per 1M tokens
Output
$0.318
per 1M tokens
Context window
128,000
tokens
Pricing source: IBM watsonx.ai 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
Mistral Small 3.1 24B (watsonx.ai) at rising volume: prompt-only, reply-only, and a mixed chat (70% in, 30% out).
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.000000106 | $0.000000318 | $0.0000001696 |
| 10 | $0.000001 | $0.000003 | $0.000002 |
| 100 | $0.000011 | $0.000032 | $0.000017 |
| 200 | $0.000021 | $0.000064 | $0.000034 |
| 300 | $0.000032 | $0.000095 | $0.000051 |
| 400 | $0.000042 | $0.000127 | $0.000068 |
| 500 | $0.000053 | $0.000159 | $0.000085 |
| 1,000 | $0.000106 | $0.000318 | $0.00017 |
| 2,000 | $0.000212 | $0.000636 | $0.000339 |
| 5,000 | $0.00053 | $0.00159 | $0.000848 |
| 10,000 | $0.00106 | $0.00318 | $0.001696 |
| 25,000 | $0.00265 | $0.00795 | $0.00424 |
| 50,000 | $0.0053 | $0.0159 | $0.00848 |
| 100,000 | $0.0106 | $0.0318 | $0.01696 |
| 250,000 | $0.0265 | $0.0795 | $0.0424 |
| 500,000 | $0.053 | $0.159 | $0.0848 |
| 1,000,000 | $0.106 | $0.318 | $0.1696 |
| 5,000,000 | $0.53 | $1.59 | $0.848 |
| 10,000,000 | $1.06 | $3.18 | $1.696 |
| 50,000,000 | $5.30 | $15.90 | $8.48 |
| 100,000,000 | $10.60 | $31.80 | $16.96 |
| 500,000,000 | $53.00 | $159.00 | $84.80 |
| 1,000,000,000 | $106.00 | $318.00 | $169.60 |
| 10,000,000,000 | $1,060.00 | $3,180.00 | $1,696.00 |
| 100,000,000,000 | $10,600.00 | $31,800.00 | $16,960.00 |
Tokens for a fixed budget
How far a fixed spend goes on Mistral Small 3.1 24B (watsonx.ai) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 94,340 | 31,447 | 58,962 |
| $0.1 | 943,396 | 314,465 | 589,623 |
| $0.5 | 4.72M | 1.57M | 2.95M |
| $1.00 | 9.43M | 3.14M | 5.9M |
| $5.00 | 47.2M | 15.7M | 29.5M |
| $10.00 | 94.3M | 31.4M | 59M |
| $20.00 | 188.7M | 62.9M | 117.9M |
| $25.00 | 235.8M | 78.6M | 147.4M |
| $30.00 | 283M | 94.3M | 176.9M |
| $50.00 | 471.7M | 157.2M | 294.8M |
| $100.00 | 943.4M | 314.5M | 589.6M |
| $250.00 | 2.36B | 786.2M | 1.47B |
| $500.00 | 4.72B | 1.57B | 2.95B |
| $1,000.00 | 9.43B | 3.14B | 5.9B |
| $5,000.00 | 47.2B | 15.7B | 29.5B |
| $10,000.00 | 94.3B | 31.4B | 59B |
At these rates
- A workload with 70% input and 30% output costs $0.1696 per 1 million total tokens and $16.96 per 100 million.
- At the same token count, output costs 3 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 $0.01357, 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.