DeepInfra
DeepSeek V4 Flash (DeepInfra) token cost
DeepSeek V4 Flash on DeepInfra with cache discounts — compare against first-party and Fireworks.
Published list rates
Input
$0.09
per 1M tokens
Output
$0.18
per 1M tokens
Cached input
$0.018
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
What DeepSeek V4 Flash (DeepInfra) 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 | $0.00000009 | $0.00000018 | $0.000000117 |
| 10 | $0.0000009 | $0.000002 | $0.000001 |
| 100 | $0.000009 | $0.000018 | $0.000012 |
| 200 | $0.000018 | $0.000036 | $0.000023 |
| 300 | $0.000027 | $0.000054 | $0.000035 |
| 400 | $0.000036 | $0.000072 | $0.000047 |
| 500 | $0.000045 | $0.00009 | $0.000059 |
| 1,000 | $0.00009 | $0.00018 | $0.000117 |
| 2,000 | $0.00018 | $0.00036 | $0.000234 |
| 5,000 | $0.00045 | $0.0009 | $0.000585 |
| 10,000 | $0.0009 | $0.0018 | $0.00117 |
| 25,000 | $0.00225 | $0.0045 | $0.002925 |
| 50,000 | $0.0045 | $0.009 | $0.00585 |
| 100,000 | $0.009 | $0.018 | $0.0117 |
| 250,000 | $0.0225 | $0.045 | $0.02925 |
| 500,000 | $0.045 | $0.09 | $0.0585 |
| 1,000,000 | $0.09 | $0.18 | $0.117 |
| 5,000,000 | $0.45 | $0.9 | $0.585 |
| 10,000,000 | $0.9 | $1.80 | $1.17 |
| 50,000,000 | $4.50 | $9.00 | $5.85 |
| 100,000,000 | $9.00 | $18.00 | $11.70 |
| 500,000,000 | $45.00 | $90.00 | $58.50 |
| 1,000,000,000 | $90.00 | $180.00 | $117.00 |
| 10,000,000,000 | $900.00 | $1,800.00 | $1,170.00 |
| 100,000,000,000 | $9,000.00 | $18,000.00 | $11,700.00 |
Tokens for a fixed budget
Tokens DeepSeek V4 Flash (DeepInfra) can process for a set budget — send-only, reply-only, and a 70/30 mix.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 111,111 | 55,556 | 85,470 |
| $0.1 | 1.11M | 555,556 | 854,701 |
| $0.5 | 5.56M | 2.78M | 4.27M |
| $1.00 | 11.1M | 5.56M | 8.55M |
| $5.00 | 55.6M | 27.8M | 42.7M |
| $10.00 | 111.1M | 55.6M | 85.5M |
| $20.00 | 222.2M | 111.1M | 170.9M |
| $25.00 | 277.8M | 138.9M | 213.7M |
| $30.00 | 333.3M | 166.7M | 256.4M |
| $50.00 | 555.6M | 277.8M | 427.4M |
| $100.00 | 1.11B | 555.6M | 854.7M |
| $250.00 | 2.78B | 1.39B | 2.14B |
| $500.00 | 5.56B | 2.78B | 4.27B |
| $1,000.00 | 11.1B | 5.56B | 8.55B |
| $5,000.00 | 55.6B | 27.8B | 42.7B |
| $10,000.00 | 111.1B | 55.6B | 85.5B |
At these rates
- A workload with 70% input and 30% output costs $0.117 per 1 million total tokens and $11.70 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 $0.09216, before any output.
- Cached input is $0.018 per million, 80% 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.