Hyperbolic
Llama 3.3 70B (Hyperbolic) token cost
Llama 3.3 70B on Hyperbolic among the cheapest 70B serverless hosts.
Published list rates
Input
$0.12
per 1M tokens
Output
$0.3
per 1M tokens
Context window
131,072
tokens
Pricing source: Hyperbolic 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 (Hyperbolic) 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 | $0.00000012 | $0.0000003 | $0.000000174 |
| 10 | $0.000001 | $0.000003 | $0.000002 |
| 100 | $0.000012 | $0.00003 | $0.000017 |
| 200 | $0.000024 | $0.00006 | $0.000035 |
| 300 | $0.000036 | $0.00009 | $0.000052 |
| 400 | $0.000048 | $0.00012 | $0.00007 |
| 500 | $0.00006 | $0.00015 | $0.000087 |
| 1,000 | $0.00012 | $0.0003 | $0.000174 |
| 2,000 | $0.00024 | $0.0006 | $0.000348 |
| 5,000 | $0.0006 | $0.0015 | $0.00087 |
| 10,000 | $0.0012 | $0.003 | $0.00174 |
| 25,000 | $0.003 | $0.0075 | $0.00435 |
| 50,000 | $0.006 | $0.015 | $0.0087 |
| 100,000 | $0.012 | $0.03 | $0.0174 |
| 250,000 | $0.03 | $0.075 | $0.0435 |
| 500,000 | $0.06 | $0.15 | $0.087 |
| 1,000,000 | $0.12 | $0.3 | $0.174 |
| 5,000,000 | $0.6 | $1.50 | $0.87 |
| 10,000,000 | $1.20 | $3.00 | $1.74 |
| 50,000,000 | $6.00 | $15.00 | $8.70 |
| 100,000,000 | $12.00 | $30.00 | $17.40 |
| 500,000,000 | $60.00 | $150.00 | $87.00 |
| 1,000,000,000 | $120.00 | $300.00 | $174.00 |
| 10,000,000,000 | $1,200.00 | $3,000.00 | $1,740.00 |
| 100,000,000,000 | $12,000.00 | $30,000.00 | $17,400.00 |
Tokens for a fixed budget
How far a fixed spend goes on Llama 3.3 70B (Hyperbolic) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 83,333 | 33,333 | 57,471 |
| $0.1 | 833,333 | 333,333 | 574,713 |
| $0.5 | 4.17M | 1.67M | 2.87M |
| $1.00 | 8.33M | 3.33M | 5.75M |
| $5.00 | 41.7M | 16.7M | 28.7M |
| $10.00 | 83.3M | 33.3M | 57.5M |
| $20.00 | 166.7M | 66.7M | 114.9M |
| $25.00 | 208.3M | 83.3M | 143.7M |
| $30.00 | 250M | 100M | 172.4M |
| $50.00 | 416.7M | 166.7M | 287.4M |
| $100.00 | 833.3M | 333.3M | 574.7M |
| $250.00 | 2.08B | 833.3M | 1.44B |
| $500.00 | 4.17B | 1.67B | 2.87B |
| $1,000.00 | 8.33B | 3.33B | 5.75B |
| $5,000.00 | 41.7B | 16.7B | 28.7B |
| $10,000.00 | 83.3B | 33.3B | 57.5B |
At these rates
- A workload with 70% input and 30% output costs $0.174 per 1 million total tokens and $17.40 per 100 million.
- At the same token count, output costs 2.5 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 $0.01573, 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.