Cloudflare
Llama 4 Scout (Workers AI) token cost
Llama 4 Scout 17B on Workers AI for edge-friendly open instruction following.
Published list rates
Input
$0.27
per 1M tokens
Output
$0.85
per 1M tokens
Context window
131,000
tokens
Pricing source: Cloudflare Workers 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
What Llama 4 Scout (Workers AI) costs if you only send tokens, only get a reply, or do both (70% in / 30% out). Rows start small and go up to huge traffic.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000027 | $0.00000085 | $0.000000444 |
| 10 | $0.000003 | $0.000009 | $0.000004 |
| 100 | $0.000027 | $0.000085 | $0.000044 |
| 200 | $0.000054 | $0.00017 | $0.000089 |
| 300 | $0.000081 | $0.000255 | $0.000133 |
| 400 | $0.000108 | $0.00034 | $0.000178 |
| 500 | $0.000135 | $0.000425 | $0.000222 |
| 1,000 | $0.00027 | $0.00085 | $0.000444 |
| 2,000 | $0.00054 | $0.0017 | $0.000888 |
| 5,000 | $0.00135 | $0.00425 | $0.00222 |
| 10,000 | $0.0027 | $0.0085 | $0.00444 |
| 25,000 | $0.00675 | $0.02125 | $0.0111 |
| 50,000 | $0.0135 | $0.0425 | $0.0222 |
| 100,000 | $0.027 | $0.085 | $0.0444 |
| 250,000 | $0.0675 | $0.2125 | $0.111 |
| 500,000 | $0.135 | $0.425 | $0.222 |
| 1,000,000 | $0.27 | $0.85 | $0.444 |
| 5,000,000 | $1.35 | $4.25 | $2.22 |
| 10,000,000 | $2.70 | $8.50 | $4.44 |
| 50,000,000 | $13.50 | $42.50 | $22.20 |
| 100,000,000 | $27.00 | $85.00 | $44.40 |
| 500,000,000 | $135.00 | $425.00 | $222.00 |
| 1,000,000,000 | $270.00 | $850.00 | $444.00 |
| 10,000,000,000 | $2,700.00 | $8,500.00 | $4,440.00 |
| 100,000,000,000 | $27,000.00 | $85,000.00 | $44,400.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many Llama 4 Scout (Workers AI) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 37,037 | 11,765 | 22,523 |
| $0.1 | 370,370 | 117,647 | 225,225 |
| $0.5 | 1.85M | 588,235 | 1.13M |
| $1.00 | 3.7M | 1.18M | 2.25M |
| $5.00 | 18.5M | 5.88M | 11.3M |
| $10.00 | 37M | 11.8M | 22.5M |
| $20.00 | 74.1M | 23.5M | 45M |
| $25.00 | 92.6M | 29.4M | 56.3M |
| $30.00 | 111.1M | 35.3M | 67.6M |
| $50.00 | 185.2M | 58.8M | 112.6M |
| $100.00 | 370.4M | 117.6M | 225.2M |
| $250.00 | 925.9M | 294.1M | 563.1M |
| $500.00 | 1.85B | 588.2M | 1.13B |
| $1,000.00 | 3.7B | 1.18B | 2.25B |
| $5,000.00 | 18.5B | 5.88B | 11.3B |
| $10,000.00 | 37B | 11.8B | 22.5B |
At these rates
- A workload with 70% input and 30% output costs $0.444 per 1 million total tokens and $44.40 per 100 million.
- At the same token count, output costs 3.15 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 131,000-token context window with input alone would cost about $0.03537, 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.