Novita AI
Llama 4 Scout (Novita) token cost
Llama 4 Scout on Novita for efficient multimodal and long-context workloads.
Published list rates
Input
$0.18
per 1M tokens
Output
$0.59
per 1M tokens
Context window
131,072
tokens
Pricing source: Novita 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
Read down to see Llama 4 Scout (Novita) get more expensive as tokens grow. The last column is a typical mix: 70% input, 30% output.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000018 | $0.00000059 | $0.000000303 |
| 10 | $0.000002 | $0.000006 | $0.000003 |
| 100 | $0.000018 | $0.000059 | $0.00003 |
| 200 | $0.000036 | $0.000118 | $0.000061 |
| 300 | $0.000054 | $0.000177 | $0.000091 |
| 400 | $0.000072 | $0.000236 | $0.000121 |
| 500 | $0.00009 | $0.000295 | $0.000152 |
| 1,000 | $0.00018 | $0.00059 | $0.000303 |
| 2,000 | $0.00036 | $0.00118 | $0.000606 |
| 5,000 | $0.0009 | $0.00295 | $0.001515 |
| 10,000 | $0.0018 | $0.0059 | $0.00303 |
| 25,000 | $0.0045 | $0.01475 | $0.007575 |
| 50,000 | $0.009 | $0.0295 | $0.01515 |
| 100,000 | $0.018 | $0.059 | $0.0303 |
| 250,000 | $0.045 | $0.1475 | $0.07575 |
| 500,000 | $0.09 | $0.295 | $0.1515 |
| 1,000,000 | $0.18 | $0.59 | $0.303 |
| 5,000,000 | $0.9 | $2.95 | $1.515 |
| 10,000,000 | $1.80 | $5.90 | $3.03 |
| 50,000,000 | $9.00 | $29.50 | $15.15 |
| 100,000,000 | $18.00 | $59.00 | $30.30 |
| 500,000,000 | $90.00 | $295.00 | $151.50 |
| 1,000,000,000 | $180.00 | $590.00 | $303.00 |
| 10,000,000,000 | $1,800.00 | $5,900.00 | $3,030.00 |
| 100,000,000,000 | $18,000.00 | $59,000.00 | $30,300.00 |
Tokens for a fixed budget
How far a fixed spend goes on Llama 4 Scout (Novita) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 55,556 | 16,949 | 33,003 |
| $0.1 | 555,556 | 169,492 | 330,033 |
| $0.5 | 2.78M | 847,458 | 1.65M |
| $1.00 | 5.56M | 1.69M | 3.3M |
| $5.00 | 27.8M | 8.47M | 16.5M |
| $10.00 | 55.6M | 16.9M | 33M |
| $20.00 | 111.1M | 33.9M | 66M |
| $25.00 | 138.9M | 42.4M | 82.5M |
| $30.00 | 166.7M | 50.8M | 99M |
| $50.00 | 277.8M | 84.7M | 165M |
| $100.00 | 555.6M | 169.5M | 330M |
| $250.00 | 1.39B | 423.7M | 825.1M |
| $500.00 | 2.78B | 847.5M | 1.65B |
| $1,000.00 | 5.56B | 1.69B | 3.3B |
| $5,000.00 | 27.8B | 8.47B | 16.5B |
| $10,000.00 | 55.6B | 16.9B | 33B |
At these rates
- A workload with 70% input and 30% output costs $0.303 per 1 million total tokens and $30.30 per 100 million.
- At the same token count, output costs 3.28 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 131,072-token context window with input alone would cost about $0.02359, 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.