Fireworks
GPT OSS 120B (Fireworks) token cost
Open GPT OSS 120B on Fireworks with cached-input discounts on Standard path.
Published list rates
Input
$0.15
per 1M tokens
Output
$0.6
per 1M tokens
Cached input
$0.015
per 1M tokens
Context window
131,072
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
GPT OSS 120B (Fireworks) at rising volume: prompt-only, reply-only, and a mixed chat (70% in, 30% out).
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000015 | $0.0000006 | $0.000000285 |
| 10 | $0.000002 | $0.000006 | $0.000003 |
| 100 | $0.000015 | $0.00006 | $0.000029 |
| 200 | $0.00003 | $0.00012 | $0.000057 |
| 300 | $0.000045 | $0.00018 | $0.000086 |
| 400 | $0.00006 | $0.00024 | $0.000114 |
| 500 | $0.000075 | $0.0003 | $0.000143 |
| 1,000 | $0.00015 | $0.0006 | $0.000285 |
| 2,000 | $0.0003 | $0.0012 | $0.00057 |
| 5,000 | $0.00075 | $0.003 | $0.001425 |
| 10,000 | $0.0015 | $0.006 | $0.00285 |
| 25,000 | $0.00375 | $0.015 | $0.007125 |
| 50,000 | $0.0075 | $0.03 | $0.01425 |
| 100,000 | $0.015 | $0.06 | $0.0285 |
| 250,000 | $0.0375 | $0.15 | $0.07125 |
| 500,000 | $0.075 | $0.3 | $0.1425 |
| 1,000,000 | $0.15 | $0.6 | $0.285 |
| 5,000,000 | $0.75 | $3.00 | $1.425 |
| 10,000,000 | $1.50 | $6.00 | $2.85 |
| 50,000,000 | $7.50 | $30.00 | $14.25 |
| 100,000,000 | $15.00 | $60.00 | $28.50 |
| 500,000,000 | $75.00 | $300.00 | $142.50 |
| 1,000,000,000 | $150.00 | $600.00 | $285.00 |
| 10,000,000,000 | $1,500.00 | $6,000.00 | $2,850.00 |
| 100,000,000,000 | $15,000.00 | $60,000.00 | $28,500.00 |
Tokens for a fixed budget
How far a fixed spend goes on GPT OSS 120B (Fireworks) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 66,667 | 16,667 | 35,088 |
| $0.1 | 666,667 | 166,667 | 350,877 |
| $0.5 | 3.33M | 833,333 | 1.75M |
| $1.00 | 6.67M | 1.67M | 3.51M |
| $5.00 | 33.3M | 8.33M | 17.5M |
| $10.00 | 66.7M | 16.7M | 35.1M |
| $20.00 | 133.3M | 33.3M | 70.2M |
| $25.00 | 166.7M | 41.7M | 87.7M |
| $30.00 | 200M | 50M | 105.3M |
| $50.00 | 333.3M | 83.3M | 175.4M |
| $100.00 | 666.7M | 166.7M | 350.9M |
| $250.00 | 1.67B | 416.7M | 877.2M |
| $500.00 | 3.33B | 833.3M | 1.75B |
| $1,000.00 | 6.67B | 1.67B | 3.51B |
| $5,000.00 | 33.3B | 8.33B | 17.5B |
| $10,000.00 | 66.7B | 16.7B | 35.1B |
At these rates
- A workload with 70% input and 30% output costs $0.285 per 1 million total tokens and $28.50 per 100 million.
- At the same token count, output costs 4 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 131,072-token context window with input alone would cost about $0.01966, before any output.
- Cached input is $0.015 per million, 90% 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.