DeepInfra
Llama 4 Scout (DeepInfra) token cost
Meta Llama 4 Scout multimodal tier on DeepInfra for efficient long-context work.
Published list rates
Input
$0.1
per 1M tokens
Output
$0.3
per 1M tokens
Context window
320,000
tokens
Pricing source: DeepInfra 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
Llama 4 Scout (DeepInfra) 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 | $0.0000001 | $0.0000003 | $0.00000016 |
| 10 | $0.000001 | $0.000003 | $0.000002 |
| 100 | $0.00001 | $0.00003 | $0.000016 |
| 200 | $0.00002 | $0.00006 | $0.000032 |
| 300 | $0.00003 | $0.00009 | $0.000048 |
| 400 | $0.00004 | $0.00012 | $0.000064 |
| 500 | $0.00005 | $0.00015 | $0.00008 |
| 1,000 | $0.0001 | $0.0003 | $0.00016 |
| 2,000 | $0.0002 | $0.0006 | $0.00032 |
| 5,000 | $0.0005 | $0.0015 | $0.0008 |
| 10,000 | $0.001 | $0.003 | $0.0016 |
| 25,000 | $0.0025 | $0.0075 | $0.004 |
| 50,000 | $0.005 | $0.015 | $0.008 |
| 100,000 | $0.01 | $0.03 | $0.016 |
| 250,000 | $0.025 | $0.075 | $0.04 |
| 500,000 | $0.05 | $0.15 | $0.08 |
| 1,000,000 | $0.1 | $0.3 | $0.16 |
| 5,000,000 | $0.5 | $1.50 | $0.8 |
| 10,000,000 | $1.00 | $3.00 | $1.60 |
| 50,000,000 | $5.00 | $15.00 | $8.00 |
| 100,000,000 | $10.00 | $30.00 | $16.00 |
| 500,000,000 | $50.00 | $150.00 | $80.00 |
| 1,000,000,000 | $100.00 | $300.00 | $160.00 |
| 10,000,000,000 | $1,000.00 | $3,000.00 | $1,600.00 |
| 100,000,000,000 | $10,000.00 | $30,000.00 | $16,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many Llama 4 Scout (DeepInfra) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 100,000 | 33,333 | 62,500 |
| $0.1 | 1M | 333,333 | 625,000 |
| $0.5 | 5M | 1.67M | 3.13M |
| $1.00 | 10M | 3.33M | 6.25M |
| $5.00 | 50M | 16.7M | 31.3M |
| $10.00 | 100M | 33.3M | 62.5M |
| $20.00 | 200M | 66.7M | 125M |
| $25.00 | 250M | 83.3M | 156.3M |
| $30.00 | 300M | 100M | 187.5M |
| $50.00 | 500M | 166.7M | 312.5M |
| $100.00 | 1B | 333.3M | 625M |
| $250.00 | 2.5B | 833.3M | 1.56B |
| $500.00 | 5B | 1.67B | 3.13B |
| $1,000.00 | 10B | 3.33B | 6.25B |
| $5,000.00 | 50B | 16.7B | 31.3B |
| $10,000.00 | 100B | 33.3B | 62.5B |
At these rates
- A workload with 70% input and 30% output costs $0.16 per 1 million total tokens and $16.00 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 320,000-token context window with input alone would cost about $0.032, 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.