Inception
Mercury 2 token cost
Inception Mercury 2 diffusion LLM for high-throughput chat with cached input discounts.
Published list rates
Input
$0.25
per 1M tokens
Output
$0.75
per 1M tokens
Cached input
$0.025
per 1M tokens
Context window
128,000
tokens
Pricing source: Inception models & 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 Mercury 2 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 | $0.00000025 | $0.00000075 | $0.0000004 |
| 10 | $0.000003 | $0.000008 | $0.000004 |
| 100 | $0.000025 | $0.000075 | $0.00004 |
| 200 | $0.00005 | $0.00015 | $0.00008 |
| 300 | $0.000075 | $0.000225 | $0.00012 |
| 400 | $0.0001 | $0.0003 | $0.00016 |
| 500 | $0.000125 | $0.000375 | $0.0002 |
| 1,000 | $0.00025 | $0.00075 | $0.0004 |
| 2,000 | $0.0005 | $0.0015 | $0.0008 |
| 5,000 | $0.00125 | $0.00375 | $0.002 |
| 10,000 | $0.0025 | $0.0075 | $0.004 |
| 25,000 | $0.00625 | $0.01875 | $0.01 |
| 50,000 | $0.0125 | $0.0375 | $0.02 |
| 100,000 | $0.025 | $0.075 | $0.04 |
| 250,000 | $0.0625 | $0.1875 | $0.1 |
| 500,000 | $0.125 | $0.375 | $0.2 |
| 1,000,000 | $0.25 | $0.75 | $0.4 |
| 5,000,000 | $1.25 | $3.75 | $2.00 |
| 10,000,000 | $2.50 | $7.50 | $4.00 |
| 50,000,000 | $12.50 | $37.50 | $20.00 |
| 100,000,000 | $25.00 | $75.00 | $40.00 |
| 500,000,000 | $125.00 | $375.00 | $200.00 |
| 1,000,000,000 | $250.00 | $750.00 | $400.00 |
| 10,000,000,000 | $2,500.00 | $7,500.00 | $4,000.00 |
| 100,000,000,000 | $25,000.00 | $75,000.00 | $40,000.00 |
Tokens for a fixed budget
How far a fixed spend goes on Mercury 2 at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 40,000 | 13,333 | 25,000 |
| $0.1 | 400,000 | 133,333 | 250,000 |
| $0.5 | 2M | 666,667 | 1.25M |
| $1.00 | 4M | 1.33M | 2.5M |
| $5.00 | 20M | 6.67M | 12.5M |
| $10.00 | 40M | 13.3M | 25M |
| $20.00 | 80M | 26.7M | 50M |
| $25.00 | 100M | 33.3M | 62.5M |
| $30.00 | 120M | 40M | 75M |
| $50.00 | 200M | 66.7M | 125M |
| $100.00 | 400M | 133.3M | 250M |
| $250.00 | 1B | 333.3M | 625M |
| $500.00 | 2B | 666.7M | 1.25B |
| $1,000.00 | 4B | 1.33B | 2.5B |
| $5,000.00 | 20B | 6.67B | 12.5B |
| $10,000.00 | 40B | 13.3B | 25B |
At these rates
- A workload with 70% input and 30% output costs $0.4 per 1 million total tokens and $40.00 per 100 million.
- At the same token count, output costs 3 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 128,000-token context window with input alone would cost about $0.032, before any output.
- Cached input is $0.025 per million, 90% below standard input when the workload meets the provider’s cache rules.
New accounts include free trial tokens. Confirm live Inception docs before production budgets.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.