Parasail
gpt-oss-120b (Parasail) token cost
OpenAI gpt-oss-120b on Parasail with cache reads for multi-host open compare.
Published list rates
Input
$0.1
per 1M tokens
Output
$0.75
per 1M tokens
Cached input
$0.055
per 1M tokens
Context window
128,000
tokens
Pricing source: Parasail 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
- 100,000
- Characters
- 400,000
- Words
- 75,000
- Input tokens
- 70,000
- Output tokens
- 30,000
- Input cost
- $0.007
- Output cost
- $0.0225
- Total cost
- $0.0295
- Combined price per 1M tokens
- $0.295
- Estimated monthly cost
- $17.70
- Estimated daily cost
- $0.59
Cost as volume grows
Read down to see gpt-oss-120b (Parasail) 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 | $0.0000001 | $0.00000075 | $0.000000295 |
| 10 | $0.000001 | $0.000008 | $0.000003 |
| 100 | $0.00001 | $0.000075 | $0.00003 |
| 200 | $0.00002 | $0.00015 | $0.000059 |
| 300 | $0.00003 | $0.000225 | $0.000089 |
| 400 | $0.00004 | $0.0003 | $0.000118 |
| 500 | $0.00005 | $0.000375 | $0.000148 |
| 1,000 | $0.0001 | $0.00075 | $0.000295 |
| 2,000 | $0.0002 | $0.0015 | $0.00059 |
| 5,000 | $0.0005 | $0.00375 | $0.001475 |
| 10,000 | $0.001 | $0.0075 | $0.00295 |
| 25,000 | $0.0025 | $0.01875 | $0.007375 |
| 50,000 | $0.005 | $0.0375 | $0.01475 |
| 100,000 | $0.01 | $0.075 | $0.0295 |
| 250,000 | $0.025 | $0.1875 | $0.07375 |
| 500,000 | $0.05 | $0.375 | $0.1475 |
| 1,000,000 | $0.1 | $0.75 | $0.295 |
| 5,000,000 | $0.5 | $3.75 | $1.475 |
| 10,000,000 | $1.00 | $7.50 | $2.95 |
| 50,000,000 | $5.00 | $37.50 | $14.75 |
| 100,000,000 | $10.00 | $75.00 | $29.50 |
| 500,000,000 | $50.00 | $375.00 | $147.50 |
| 1,000,000,000 | $100.00 | $750.00 | $295.00 |
| 10,000,000,000 | $1,000.00 | $7,500.00 | $2,950.00 |
| 100,000,000,000 | $10,000.00 | $75,000.00 | $29,500.00 |
Tokens for a fixed budget
How far a fixed spend goes on gpt-oss-120b (Parasail) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 100,000 | 13,333 | 33,898 |
| $0.1 | 1M | 133,333 | 338,983 |
| $0.5 | 5M | 666,667 | 1.69M |
| $1.00 | 10M | 1.33M | 3.39M |
| $5.00 | 50M | 6.67M | 16.9M |
| $10.00 | 100M | 13.3M | 33.9M |
| $20.00 | 200M | 26.7M | 67.8M |
| $25.00 | 250M | 33.3M | 84.7M |
| $30.00 | 300M | 40M | 101.7M |
| $50.00 | 500M | 66.7M | 169.5M |
| $100.00 | 1B | 133.3M | 339M |
| $250.00 | 2.5B | 333.3M | 847.5M |
| $500.00 | 5B | 666.7M | 1.69B |
| $1,000.00 | 10B | 1.33B | 3.39B |
| $5,000.00 | 50B | 6.67B | 16.9B |
| $10,000.00 | 100B | 13.3B | 33.9B |
At these rates
- A workload with 70% input and 30% output costs $0.295 per 1 million total tokens and $29.50 per 100 million.
- At the same token count, output costs 7.5 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 $0.0128, before any output.
- Cached input is $0.055 per million, 45% 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.