Cloudflare
Llama 3.3 70B (Workers AI) token cost
Llama 3.3 70B on Cloudflare Workers AI with public per-million token rates (neuron-backed).
Published list rates
Input
$0.293
per 1M tokens
Output
$2.253
per 1M tokens
Context window
128,000
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
Llama 3.3 70B (Workers AI) 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 | $0.000000293 | $0.000002 | $0.000000881 |
| 10 | $0.000003 | $0.000023 | $0.000009 |
| 100 | $0.000029 | $0.000225 | $0.000088 |
| 200 | $0.000059 | $0.000451 | $0.000176 |
| 300 | $0.000088 | $0.000676 | $0.000264 |
| 400 | $0.000117 | $0.000901 | $0.000352 |
| 500 | $0.000146 | $0.001127 | $0.000441 |
| 1,000 | $0.000293 | $0.002253 | $0.000881 |
| 2,000 | $0.000586 | $0.004506 | $0.001762 |
| 5,000 | $0.001465 | $0.01127 | $0.004405 |
| 10,000 | $0.00293 | $0.02253 | $0.00881 |
| 25,000 | $0.007325 | $0.05633 | $0.02203 |
| 50,000 | $0.01465 | $0.11265 | $0.04405 |
| 100,000 | $0.0293 | $0.2253 | $0.0881 |
| 250,000 | $0.07325 | $0.56325 | $0.22025 |
| 500,000 | $0.1465 | $1.1265 | $0.4405 |
| 1,000,000 | $0.293 | $2.253 | $0.881 |
| 5,000,000 | $1.465 | $11.265 | $4.405 |
| 10,000,000 | $2.93 | $22.53 | $8.81 |
| 50,000,000 | $14.65 | $112.65 | $44.05 |
| 100,000,000 | $29.30 | $225.30 | $88.10 |
| 500,000,000 | $146.50 | $1,126.50 | $440.50 |
| 1,000,000,000 | $293.00 | $2,253.00 | $881.00 |
| 10,000,000,000 | $2,930.00 | $22,530.00 | $8,810.00 |
| 100,000,000,000 | $29,300.00 | $225,300.00 | $88,100.00 |
Tokens for a fixed budget
How far a fixed spend goes on Llama 3.3 70B (Workers AI) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 34,130 | 4,439 | 11,351 |
| $0.1 | 341,297 | 44,385 | 113,507 |
| $0.5 | 1.71M | 221,926 | 567,537 |
| $1.00 | 3.41M | 443,853 | 1.14M |
| $5.00 | 17.1M | 2.22M | 5.68M |
| $10.00 | 34.1M | 4.44M | 11.4M |
| $20.00 | 68.3M | 8.88M | 22.7M |
| $25.00 | 85.3M | 11.1M | 28.4M |
| $30.00 | 102.4M | 13.3M | 34.1M |
| $50.00 | 170.6M | 22.2M | 56.8M |
| $100.00 | 341.3M | 44.4M | 113.5M |
| $250.00 | 853.2M | 111M | 283.8M |
| $500.00 | 1.71B | 221.9M | 567.5M |
| $1,000.00 | 3.41B | 443.9M | 1.14B |
| $5,000.00 | 17.1B | 2.22B | 5.68B |
| $10,000.00 | 34.1B | 4.44B | 11.4B |
At these rates
- A workload with 70% input and 30% output costs $0.881 per 1 million total tokens and $88.10 per 100 million.
- At the same token count, output costs 7.69 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 128,000-token context window with input alone would cost about $0.0375, before any output.
Workers AI also bills neurons ($0.011 per 1,000 Neurons after free daily allocation). Token rates above are the published token equivalents.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.