Groq
Llama Prompt Guard 2 22M (Groq) token cost
Tiny Llama Prompt Guard 2 22M on Groq at a flat $0.03/$0.03 for prompt-injection and jailbreak screening.
Published list rates
Input
$0.03
per 1M tokens
Output
$0.03
per 1M tokens
Context window
512
tokens
Pricing source: GroqCloud models
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
- $0.0021
- Output cost
- $0.0009
- Total cost
- $0.003
- Combined price per 1M tokens
- $0.03
- Estimated monthly cost
- $1.80
- Estimated daily cost
- $0.06
Cost as volume grows
Read down to see Llama Prompt Guard 2 22M (Groq) 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 | $0.00000003 | $0.00000003 | $0.00000003 |
| 10 | $0.0000003 | $0.0000003 | $0.0000003 |
| 100 | $0.000003 | $0.000003 | $0.000003 |
| 200 | $0.000006 | $0.000006 | $0.000006 |
| 300 | $0.000009 | $0.000009 | $0.000009 |
| 400 | $0.000012 | $0.000012 | $0.000012 |
| 500 | $0.000015 | $0.000015 | $0.000015 |
| 1,000 | $0.00003 | $0.00003 | $0.00003 |
| 2,000 | $0.00006 | $0.00006 | $0.00006 |
| 5,000 | $0.00015 | $0.00015 | $0.00015 |
| 10,000 | $0.0003 | $0.0003 | $0.0003 |
| 25,000 | $0.00075 | $0.00075 | $0.00075 |
| 50,000 | $0.0015 | $0.0015 | $0.0015 |
| 100,000 | $0.003 | $0.003 | $0.003 |
| 250,000 | $0.0075 | $0.0075 | $0.0075 |
| 500,000 | $0.015 | $0.015 | $0.015 |
| 1,000,000 | $0.03 | $0.03 | $0.03 |
| 5,000,000 | $0.15 | $0.15 | $0.15 |
| 10,000,000 | $0.3 | $0.3 | $0.3 |
| 50,000,000 | $1.50 | $1.50 | $1.50 |
| 100,000,000 | $3.00 | $3.00 | $3.00 |
| 500,000,000 | $15.00 | $15.00 | $15.00 |
| 1,000,000,000 | $30.00 | $30.00 | $30.00 |
| 10,000,000,000 | $300.00 | $300.00 | $300.00 |
| 100,000,000,000 | $3,000.00 | $3,000.00 | $3,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many Llama Prompt Guard 2 22M (Groq) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 333,333 | 333,333 | 333,333 |
| $0.1 | 3.33M | 3.33M | 3.33M |
| $0.5 | 16.7M | 16.7M | 16.7M |
| $1.00 | 33.3M | 33.3M | 33.3M |
| $5.00 | 166.7M | 166.7M | 166.7M |
| $10.00 | 333.3M | 333.3M | 333.3M |
| $20.00 | 666.7M | 666.7M | 666.7M |
| $25.00 | 833.3M | 833.3M | 833.3M |
| $30.00 | 1B | 1B | 1B |
| $50.00 | 1.67B | 1.67B | 1.67B |
| $100.00 | 3.33B | 3.33B | 3.33B |
| $250.00 | 8.33B | 8.33B | 8.33B |
| $500.00 | 16.7B | 16.7B | 16.7B |
| $1,000.00 | 33.3B | 33.3B | 33.3B |
| $5,000.00 | 166.7B | 166.7B | 166.7B |
| $10,000.00 | 333.3B | 333.3B | 333.3B |
At these rates
- A workload with 70% input and 30% output costs $0.03 per 1 million total tokens and $3.00 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 512-token context window with input alone would cost about $0.000015, before any output.
Listed as a preview model on GroqCloud. Context window is 512 tokens.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.