Hyperbolic
DeepSeek V3 (Hyperbolic) token cost
DeepSeek V3 on Hyperbolic with flat input/output list rates for open reasoning chat.
Published list rates
Input
$0.25
per 1M tokens
Output
$0.25
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
- 100,000
- Characters
- 400,000
- Words
- 75,000
- Input tokens
- 70,000
- Output tokens
- 30,000
- Input cost
- $0.0175
- Output cost
- $0.0075
- Total cost
- $0.025
- Combined price per 1M tokens
- $0.25
- Estimated monthly cost
- $15.00
- Estimated daily cost
- $0.5
Cost as volume grows
Read down to see DeepSeek V3 (Hyperbolic) 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 | $0.00000025 | $0.00000025 | $0.00000025 |
| 10 | $0.000003 | $0.000003 | $0.000002 |
| 100 | $0.000025 | $0.000025 | $0.000025 |
| 200 | $0.00005 | $0.00005 | $0.00005 |
| 300 | $0.000075 | $0.000075 | $0.000075 |
| 400 | $0.0001 | $0.0001 | $0.0001 |
| 500 | $0.000125 | $0.000125 | $0.000125 |
| 1,000 | $0.00025 | $0.00025 | $0.00025 |
| 2,000 | $0.0005 | $0.0005 | $0.0005 |
| 5,000 | $0.00125 | $0.00125 | $0.00125 |
| 10,000 | $0.0025 | $0.0025 | $0.0025 |
| 25,000 | $0.00625 | $0.00625 | $0.00625 |
| 50,000 | $0.0125 | $0.0125 | $0.0125 |
| 100,000 | $0.025 | $0.025 | $0.025 |
| 250,000 | $0.0625 | $0.0625 | $0.0625 |
| 500,000 | $0.125 | $0.125 | $0.125 |
| 1,000,000 | $0.25 | $0.25 | $0.25 |
| 5,000,000 | $1.25 | $1.25 | $1.25 |
| 10,000,000 | $2.50 | $2.50 | $2.50 |
| 50,000,000 | $12.50 | $12.50 | $12.50 |
| 100,000,000 | $25.00 | $25.00 | $25.00 |
| 500,000,000 | $125.00 | $125.00 | $125.00 |
| 1,000,000,000 | $250.00 | $250.00 | $250.00 |
| 10,000,000,000 | $2,500.00 | $2,500.00 | $2,500.00 |
| 100,000,000,000 | $25,000.00 | $25,000.00 | $25,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many DeepSeek V3 (Hyperbolic) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 40,000 | 40,000 | 40,000 |
| $0.1 | 400,000 | 400,000 | 400,000 |
| $0.5 | 2M | 2M | 2M |
| $1.00 | 4M | 4M | 4M |
| $5.00 | 20M | 20M | 20M |
| $10.00 | 40M | 40M | 40M |
| $20.00 | 80M | 80M | 80M |
| $25.00 | 100M | 100M | 100M |
| $30.00 | 120M | 120M | 120M |
| $50.00 | 200M | 200M | 200M |
| $100.00 | 400M | 400M | 400M |
| $250.00 | 1B | 1B | 1B |
| $500.00 | 2B | 2B | 2B |
| $1,000.00 | 4B | 4B | 4B |
| $5,000.00 | 20B | 20B | 20B |
| $10,000.00 | 40B | 40B | 40B |
At these rates
- A workload with 70% input and 30% output costs $0.25 per 1 million total tokens and $25.00 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 131,072-token context window with input alone would cost about $0.03277, 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.