DeepInfra
DeepSeek V4 Pro (DeepInfra) token cost
DeepSeek V4 Pro hosted on DeepInfra for long-context reasoning with cache-aware rates.
Published list rates
Input
$1.30
per 1M tokens
Output
$2.60
per 1M tokens
Cached input
$0.1
per 1M tokens
Context window
1,024,000
tokens
Pricing source: DeepInfra 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
DeepSeek V4 Pro (DeepInfra) 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 | $0.000001 | $0.000003 | $0.000002 |
| 10 | $0.000013 | $0.000026 | $0.000017 |
| 100 | $0.00013 | $0.00026 | $0.000169 |
| 200 | $0.00026 | $0.00052 | $0.000338 |
| 300 | $0.00039 | $0.00078 | $0.000507 |
| 400 | $0.00052 | $0.00104 | $0.000676 |
| 500 | $0.00065 | $0.0013 | $0.000845 |
| 1,000 | $0.0013 | $0.0026 | $0.00169 |
| 2,000 | $0.0026 | $0.0052 | $0.00338 |
| 5,000 | $0.0065 | $0.013 | $0.00845 |
| 10,000 | $0.013 | $0.026 | $0.0169 |
| 25,000 | $0.0325 | $0.065 | $0.04225 |
| 50,000 | $0.065 | $0.13 | $0.0845 |
| 100,000 | $0.13 | $0.26 | $0.169 |
| 250,000 | $0.325 | $0.65 | $0.4225 |
| 500,000 | $0.65 | $1.30 | $0.845 |
| 1,000,000 | $1.30 | $2.60 | $1.69 |
| 5,000,000 | $6.50 | $13.00 | $8.45 |
| 10,000,000 | $13.00 | $26.00 | $16.90 |
| 50,000,000 | $65.00 | $130.00 | $84.50 |
| 100,000,000 | $130.00 | $260.00 | $169.00 |
| 500,000,000 | $650.00 | $1,300.00 | $845.00 |
| 1,000,000,000 | $1,300.00 | $2,600.00 | $1,690.00 |
| 10,000,000,000 | $13,000.00 | $26,000.00 | $16,900.00 |
| 100,000,000,000 | $130,000.00 | $260,000.00 | $169,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many DeepSeek V4 Pro (DeepInfra) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 7,692 | 3,846 | 5,917 |
| $0.1 | 76,923 | 38,462 | 59,172 |
| $0.5 | 384,615 | 192,308 | 295,858 |
| $1.00 | 769,231 | 384,615 | 591,716 |
| $5.00 | 3.85M | 1.92M | 2.96M |
| $10.00 | 7.69M | 3.85M | 5.92M |
| $20.00 | 15.4M | 7.69M | 11.8M |
| $25.00 | 19.2M | 9.62M | 14.8M |
| $30.00 | 23.1M | 11.5M | 17.8M |
| $50.00 | 38.5M | 19.2M | 29.6M |
| $100.00 | 76.9M | 38.5M | 59.2M |
| $250.00 | 192.3M | 96.2M | 147.9M |
| $500.00 | 384.6M | 192.3M | 295.9M |
| $1,000.00 | 769.2M | 384.6M | 591.7M |
| $5,000.00 | 3.85B | 1.92B | 2.96B |
| $10,000.00 | 7.69B | 3.85B | 5.92B |
At these rates
- A workload with 70% input and 30% output costs $1.69 per 1 million total tokens and $169.00 per 100 million.
- At the same token count, output costs 2 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 1,024,000-token context window with input alone would cost about $1.3312, before any output.
- Cached input is $0.1 per million, 92% below standard input when the workload meets the provider’s cache rules.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.