Fireworks
DeepSeek V4 Flash (Fireworks) token cost
Cheap DeepSeek V4 Flash path on Fireworks for high-volume classification and chat.
Published list rates
Input
$0.14
per 1M tokens
Output
$0.28
per 1M tokens
Cached input
$0.028
per 1M tokens
Context window
256,000
tokens
Pricing source: Fireworks serverless 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
Read down to see DeepSeek V4 Flash (Fireworks) 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 | $0.00000014 | $0.00000028 | $0.000000182 |
| 10 | $0.000001 | $0.000003 | $0.000002 |
| 100 | $0.000014 | $0.000028 | $0.000018 |
| 200 | $0.000028 | $0.000056 | $0.000036 |
| 300 | $0.000042 | $0.000084 | $0.000055 |
| 400 | $0.000056 | $0.000112 | $0.000073 |
| 500 | $0.00007 | $0.00014 | $0.000091 |
| 1,000 | $0.00014 | $0.00028 | $0.000182 |
| 2,000 | $0.00028 | $0.00056 | $0.000364 |
| 5,000 | $0.0007 | $0.0014 | $0.00091 |
| 10,000 | $0.0014 | $0.0028 | $0.00182 |
| 25,000 | $0.0035 | $0.007 | $0.00455 |
| 50,000 | $0.007 | $0.014 | $0.0091 |
| 100,000 | $0.014 | $0.028 | $0.0182 |
| 250,000 | $0.035 | $0.07 | $0.0455 |
| 500,000 | $0.07 | $0.14 | $0.091 |
| 1,000,000 | $0.14 | $0.28 | $0.182 |
| 5,000,000 | $0.7 | $1.40 | $0.91 |
| 10,000,000 | $1.40 | $2.80 | $1.82 |
| 50,000,000 | $7.00 | $14.00 | $9.10 |
| 100,000,000 | $14.00 | $28.00 | $18.20 |
| 500,000,000 | $70.00 | $140.00 | $91.00 |
| 1,000,000,000 | $140.00 | $280.00 | $182.00 |
| 10,000,000,000 | $1,400.00 | $2,800.00 | $1,820.00 |
| 100,000,000,000 | $14,000.00 | $28,000.00 | $18,200.00 |
Tokens for a fixed budget
Tokens DeepSeek V4 Flash (Fireworks) 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 | 71,429 | 35,714 | 54,945 |
| $0.1 | 714,286 | 357,143 | 549,451 |
| $0.5 | 3.57M | 1.79M | 2.75M |
| $1.00 | 7.14M | 3.57M | 5.49M |
| $5.00 | 35.7M | 17.9M | 27.5M |
| $10.00 | 71.4M | 35.7M | 54.9M |
| $20.00 | 142.9M | 71.4M | 109.9M |
| $25.00 | 178.6M | 89.3M | 137.4M |
| $30.00 | 214.3M | 107.1M | 164.8M |
| $50.00 | 357.1M | 178.6M | 274.7M |
| $100.00 | 714.3M | 357.1M | 549.5M |
| $250.00 | 1.79B | 892.9M | 1.37B |
| $500.00 | 3.57B | 1.79B | 2.75B |
| $1,000.00 | 7.14B | 3.57B | 5.49B |
| $5,000.00 | 35.7B | 17.9B | 27.5B |
| $10,000.00 | 71.4B | 35.7B | 54.9B |
At these rates
- A workload with 70% input and 30% output costs $0.182 per 1 million total tokens and $18.20 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 256,000-token context window with input alone would cost about $0.03584, before any output.
- Cached input is $0.028 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.