SambaNova
GPT OSS 120B (SambaNova) token cost
GPT OSS 120B on SambaNova Cloud — compare throughput hosts like Groq and Fireworks.
Published list rates
Input
$0.22
per 1M tokens
Output
$0.59
per 1M tokens
Context window
131,072
tokens
Pricing source: SambaNova Cloud 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
- $0.0154
- Output cost
- $0.0177
- Total cost
- $0.0331
- Combined price per 1M tokens
- $0.331
- Estimated monthly cost
- $19.86
- Estimated daily cost
- $0.662
Cost as volume grows
Three views of GPT OSS 120B (SambaNova): sending only, receiving only, and a 70/30 mix. Same list rates, bigger rows.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000022 | $0.00000059 | $0.000000331 |
| 10 | $0.000002 | $0.000006 | $0.000003 |
| 100 | $0.000022 | $0.000059 | $0.000033 |
| 200 | $0.000044 | $0.000118 | $0.000066 |
| 300 | $0.000066 | $0.000177 | $0.000099 |
| 400 | $0.000088 | $0.000236 | $0.000132 |
| 500 | $0.00011 | $0.000295 | $0.000165 |
| 1,000 | $0.00022 | $0.00059 | $0.000331 |
| 2,000 | $0.00044 | $0.00118 | $0.000662 |
| 5,000 | $0.0011 | $0.00295 | $0.001655 |
| 10,000 | $0.0022 | $0.0059 | $0.00331 |
| 25,000 | $0.0055 | $0.01475 | $0.008275 |
| 50,000 | $0.011 | $0.0295 | $0.01655 |
| 100,000 | $0.022 | $0.059 | $0.0331 |
| 250,000 | $0.055 | $0.1475 | $0.08275 |
| 500,000 | $0.11 | $0.295 | $0.1655 |
| 1,000,000 | $0.22 | $0.59 | $0.331 |
| 5,000,000 | $1.10 | $2.95 | $1.655 |
| 10,000,000 | $2.20 | $5.90 | $3.31 |
| 50,000,000 | $11.00 | $29.50 | $16.55 |
| 100,000,000 | $22.00 | $59.00 | $33.10 |
| 500,000,000 | $110.00 | $295.00 | $165.50 |
| 1,000,000,000 | $220.00 | $590.00 | $331.00 |
| 10,000,000,000 | $2,200.00 | $5,900.00 | $3,310.00 |
| 100,000,000,000 | $22,000.00 | $59,000.00 | $33,100.00 |
Tokens for a fixed budget
How far a fixed spend goes on GPT OSS 120B (SambaNova) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 45,455 | 16,949 | 30,211 |
| $0.1 | 454,545 | 169,492 | 302,115 |
| $0.5 | 2.27M | 847,458 | 1.51M |
| $1.00 | 4.55M | 1.69M | 3.02M |
| $5.00 | 22.7M | 8.47M | 15.1M |
| $10.00 | 45.5M | 16.9M | 30.2M |
| $20.00 | 90.9M | 33.9M | 60.4M |
| $25.00 | 113.6M | 42.4M | 75.5M |
| $30.00 | 136.4M | 50.8M | 90.6M |
| $50.00 | 227.3M | 84.7M | 151.1M |
| $100.00 | 454.5M | 169.5M | 302.1M |
| $250.00 | 1.14B | 423.7M | 755.3M |
| $500.00 | 2.27B | 847.5M | 1.51B |
| $1,000.00 | 4.55B | 1.69B | 3.02B |
| $5,000.00 | 22.7B | 8.47B | 15.1B |
| $10,000.00 | 45.5B | 16.9B | 30.2B |
At these rates
- A workload with 70% input and 30% output costs $0.331 per 1 million total tokens and $33.10 per 100 million.
- At the same token count, output costs 2.68 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 $0.02884, before any output.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.