AI21
Jamba Mini token cost
Jamba Mini at $0.20/$0.40 for high-volume long-context classification and light generation.
Published list rates
Input
$0.2
per 1M tokens
Output
$0.4
per 1M tokens
Context window
256,000
tokens
Pricing source: AI21 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
- $0.012
- Total cost
- $0.026
- Combined price per 1M tokens
- $0.26
- Estimated monthly cost
- $15.60
- Estimated daily cost
- $0.52
Cost as volume grows
Three views of Jamba 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 | $0.0000002 | $0.0000004 | $0.00000026 |
| 10 | $0.000002 | $0.000004 | $0.000003 |
| 100 | $0.00002 | $0.00004 | $0.000026 |
| 200 | $0.00004 | $0.00008 | $0.000052 |
| 300 | $0.00006 | $0.00012 | $0.000078 |
| 400 | $0.00008 | $0.00016 | $0.000104 |
| 500 | $0.0001 | $0.0002 | $0.00013 |
| 1,000 | $0.0002 | $0.0004 | $0.00026 |
| 2,000 | $0.0004 | $0.0008 | $0.00052 |
| 5,000 | $0.001 | $0.002 | $0.0013 |
| 10,000 | $0.002 | $0.004 | $0.0026 |
| 25,000 | $0.005 | $0.01 | $0.0065 |
| 50,000 | $0.01 | $0.02 | $0.013 |
| 100,000 | $0.02 | $0.04 | $0.026 |
| 250,000 | $0.05 | $0.1 | $0.065 |
| 500,000 | $0.1 | $0.2 | $0.13 |
| 1,000,000 | $0.2 | $0.4 | $0.26 |
| 5,000,000 | $1.00 | $2.00 | $1.30 |
| 10,000,000 | $2.00 | $4.00 | $2.60 |
| 50,000,000 | $10.00 | $20.00 | $13.00 |
| 100,000,000 | $20.00 | $40.00 | $26.00 |
| 500,000,000 | $100.00 | $200.00 | $130.00 |
| 1,000,000,000 | $200.00 | $400.00 | $260.00 |
| 10,000,000,000 | $2,000.00 | $4,000.00 | $2,600.00 |
| 100,000,000,000 | $20,000.00 | $40,000.00 | $26,000.00 |
Tokens for a fixed budget
How far a fixed spend goes on Jamba Mini at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 50,000 | 25,000 | 38,462 |
| $0.1 | 500,000 | 250,000 | 384,615 |
| $0.5 | 2.5M | 1.25M | 1.92M |
| $1.00 | 5M | 2.5M | 3.85M |
| $5.00 | 25M | 12.5M | 19.2M |
| $10.00 | 50M | 25M | 38.5M |
| $20.00 | 100M | 50M | 76.9M |
| $25.00 | 125M | 62.5M | 96.2M |
| $30.00 | 150M | 75M | 115.4M |
| $50.00 | 250M | 125M | 192.3M |
| $100.00 | 500M | 250M | 384.6M |
| $250.00 | 1.25B | 625M | 961.5M |
| $500.00 | 2.5B | 1.25B | 1.92B |
| $1,000.00 | 5B | 2.5B | 3.85B |
| $5,000.00 | 25B | 12.5B | 19.2B |
| $10,000.00 | 50B | 25B | 38.5B |
At these rates
- A workload with 70% input and 30% output costs $0.26 per 1 million total tokens and $26.00 per 100 million.
- At the same token count, output costs 2 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 256,000-token context window with input alone would cost about $0.0512, 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.