OpenRouter
DeepSeek V3.2 (OpenRouter) token cost
DeepSeek V3.2 on OpenRouter with competitive open chat rates and cache reads.
Published list rates
Input
$0.269
per 1M tokens
Output
$0.4
per 1M tokens
Cached input
$0.1345
per 1M tokens
Context window
163,840
tokens
Pricing source: OpenRouter model 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 V3.2 (OpenRouter) 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 | $0.000000269 | $0.0000004 | $0.0000003083 |
| 10 | $0.000003 | $0.000004 | $0.000003 |
| 100 | $0.000027 | $0.00004 | $0.000031 |
| 200 | $0.000054 | $0.00008 | $0.000062 |
| 300 | $0.000081 | $0.00012 | $0.000092 |
| 400 | $0.000108 | $0.00016 | $0.000123 |
| 500 | $0.000135 | $0.0002 | $0.000154 |
| 1,000 | $0.000269 | $0.0004 | $0.000308 |
| 2,000 | $0.000538 | $0.0008 | $0.000617 |
| 5,000 | $0.001345 | $0.002 | $0.001542 |
| 10,000 | $0.00269 | $0.004 | $0.003083 |
| 25,000 | $0.006725 | $0.01 | $0.007708 |
| 50,000 | $0.01345 | $0.02 | $0.01542 |
| 100,000 | $0.0269 | $0.04 | $0.03083 |
| 250,000 | $0.06725 | $0.1 | $0.07708 |
| 500,000 | $0.1345 | $0.2 | $0.15415 |
| 1,000,000 | $0.269 | $0.4 | $0.3083 |
| 5,000,000 | $1.345 | $2.00 | $1.5415 |
| 10,000,000 | $2.69 | $4.00 | $3.083 |
| 50,000,000 | $13.45 | $20.00 | $15.415 |
| 100,000,000 | $26.90 | $40.00 | $30.83 |
| 500,000,000 | $134.50 | $200.00 | $154.15 |
| 1,000,000,000 | $269.00 | $400.00 | $308.30 |
| 10,000,000,000 | $2,690.00 | $4,000.00 | $3,083.00 |
| 100,000,000,000 | $26,900.00 | $40,000.00 | $30,830.00 |
Tokens for a fixed budget
How far a fixed spend goes on DeepSeek V3.2 (OpenRouter) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 37,175 | 25,000 | 32,436 |
| $0.1 | 371,747 | 250,000 | 324,359 |
| $0.5 | 1.86M | 1.25M | 1.62M |
| $1.00 | 3.72M | 2.5M | 3.24M |
| $5.00 | 18.6M | 12.5M | 16.2M |
| $10.00 | 37.2M | 25M | 32.4M |
| $20.00 | 74.3M | 50M | 64.9M |
| $25.00 | 92.9M | 62.5M | 81.1M |
| $30.00 | 111.5M | 75M | 97.3M |
| $50.00 | 185.9M | 125M | 162.2M |
| $100.00 | 371.7M | 250M | 324.4M |
| $250.00 | 929.4M | 625M | 810.9M |
| $500.00 | 1.86B | 1.25B | 1.62B |
| $1,000.00 | 3.72B | 2.5B | 3.24B |
| $5,000.00 | 18.6B | 12.5B | 16.2B |
| $10,000.00 | 37.2B | 25B | 32.4B |
At these rates
- A workload with 70% input and 30% output costs $0.3083 per 1 million total tokens and $30.83 per 100 million.
- At the same token count, output costs 1.49 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 163,840-token context window with input alone would cost about $0.04407, before any output.
- Cached input is $0.1345 per million, 50% 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.