SiliconFlow
DeepSeek V4 Flash (SiliconFlow) token cost
DeepSeek V4 Flash on SiliconFlow for high-volume open chat with long context.
Published list rates
Input
$0.13
per 1M tokens
Output
$0.28
per 1M tokens
Cached input
$0.028
per 1M tokens
Context window
1,049,000
tokens
Pricing source: SiliconFlow 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
Three views of DeepSeek V4 Flash (SiliconFlow): sending only, receiving only, and a 70/30 mix. Same list rates, bigger rows.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000013 | $0.00000028 | $0.000000175 |
| 10 | $0.000001 | $0.000003 | $0.000002 |
| 100 | $0.000013 | $0.000028 | $0.000018 |
| 200 | $0.000026 | $0.000056 | $0.000035 |
| 300 | $0.000039 | $0.000084 | $0.000053 |
| 400 | $0.000052 | $0.000112 | $0.00007 |
| 500 | $0.000065 | $0.00014 | $0.000088 |
| 1,000 | $0.00013 | $0.00028 | $0.000175 |
| 2,000 | $0.00026 | $0.00056 | $0.00035 |
| 5,000 | $0.00065 | $0.0014 | $0.000875 |
| 10,000 | $0.0013 | $0.0028 | $0.00175 |
| 25,000 | $0.00325 | $0.007 | $0.004375 |
| 50,000 | $0.0065 | $0.014 | $0.00875 |
| 100,000 | $0.013 | $0.028 | $0.0175 |
| 250,000 | $0.0325 | $0.07 | $0.04375 |
| 500,000 | $0.065 | $0.14 | $0.0875 |
| 1,000,000 | $0.13 | $0.28 | $0.175 |
| 5,000,000 | $0.65 | $1.40 | $0.875 |
| 10,000,000 | $1.30 | $2.80 | $1.75 |
| 50,000,000 | $6.50 | $14.00 | $8.75 |
| 100,000,000 | $13.00 | $28.00 | $17.50 |
| 500,000,000 | $65.00 | $140.00 | $87.50 |
| 1,000,000,000 | $130.00 | $280.00 | $175.00 |
| 10,000,000,000 | $1,300.00 | $2,800.00 | $1,750.00 |
| 100,000,000,000 | $13,000.00 | $28,000.00 | $17,500.00 |
Tokens for a fixed budget
Tokens DeepSeek V4 Flash (SiliconFlow) 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 | 76,923 | 35,714 | 57,143 |
| $0.1 | 769,231 | 357,143 | 571,429 |
| $0.5 | 3.85M | 1.79M | 2.86M |
| $1.00 | 7.69M | 3.57M | 5.71M |
| $5.00 | 38.5M | 17.9M | 28.6M |
| $10.00 | 76.9M | 35.7M | 57.1M |
| $20.00 | 153.8M | 71.4M | 114.3M |
| $25.00 | 192.3M | 89.3M | 142.9M |
| $30.00 | 230.8M | 107.1M | 171.4M |
| $50.00 | 384.6M | 178.6M | 285.7M |
| $100.00 | 769.2M | 357.1M | 571.4M |
| $250.00 | 1.92B | 892.9M | 1.43B |
| $500.00 | 3.85B | 1.79B | 2.86B |
| $1,000.00 | 7.69B | 3.57B | 5.71B |
| $5,000.00 | 38.5B | 17.9B | 28.6B |
| $10,000.00 | 76.9B | 35.7B | 57.1B |
At these rates
- A workload with 70% input and 30% output costs $0.175 per 1 million total tokens and $17.50 per 100 million.
- At the same token count, output costs 2.15 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 1,049,000-token context window with input alone would cost about $0.13637, before any output.
- Cached input is $0.028 per million, 78% 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.