IBM
GPT OSS 120B (watsonx.ai) token cost
OpenAI gpt-oss-120b on watsonx.ai with transparent multi-host compare rates.
Published list rates
Input
$0.159
per 1M tokens
Output
$0.636
per 1M tokens
Context window
128,000
tokens
Pricing source: IBM watsonx.ai 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
Three views of GPT OSS 120B (watsonx.ai): 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 | $0.000000159 | $0.000000636 | $0.0000003021 |
| 10 | $0.000002 | $0.000006 | $0.000003 |
| 100 | $0.000016 | $0.000064 | $0.00003 |
| 200 | $0.000032 | $0.000127 | $0.00006 |
| 300 | $0.000048 | $0.000191 | $0.000091 |
| 400 | $0.000064 | $0.000254 | $0.000121 |
| 500 | $0.00008 | $0.000318 | $0.000151 |
| 1,000 | $0.000159 | $0.000636 | $0.000302 |
| 2,000 | $0.000318 | $0.001272 | $0.000604 |
| 5,000 | $0.000795 | $0.00318 | $0.001511 |
| 10,000 | $0.00159 | $0.00636 | $0.003021 |
| 25,000 | $0.003975 | $0.0159 | $0.007553 |
| 50,000 | $0.00795 | $0.0318 | $0.01511 |
| 100,000 | $0.0159 | $0.0636 | $0.03021 |
| 250,000 | $0.03975 | $0.159 | $0.07553 |
| 500,000 | $0.0795 | $0.318 | $0.15105 |
| 1,000,000 | $0.159 | $0.636 | $0.3021 |
| 5,000,000 | $0.795 | $3.18 | $1.5105 |
| 10,000,000 | $1.59 | $6.36 | $3.021 |
| 50,000,000 | $7.95 | $31.80 | $15.105 |
| 100,000,000 | $15.90 | $63.60 | $30.21 |
| 500,000,000 | $79.50 | $318.00 | $151.05 |
| 1,000,000,000 | $159.00 | $636.00 | $302.10 |
| 10,000,000,000 | $1,590.00 | $6,360.00 | $3,021.00 |
| 100,000,000,000 | $15,900.00 | $63,600.00 | $30,210.00 |
Tokens for a fixed budget
Tokens GPT OSS 120B (watsonx.ai) can process for a set budget — send-only, reply-only, and a 70/30 mix.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 62,893 | 15,723 | 33,102 |
| $0.1 | 628,931 | 157,233 | 331,016 |
| $0.5 | 3.14M | 786,164 | 1.66M |
| $1.00 | 6.29M | 1.57M | 3.31M |
| $5.00 | 31.4M | 7.86M | 16.6M |
| $10.00 | 62.9M | 15.7M | 33.1M |
| $20.00 | 125.8M | 31.4M | 66.2M |
| $25.00 | 157.2M | 39.3M | 82.8M |
| $30.00 | 188.7M | 47.2M | 99.3M |
| $50.00 | 314.5M | 78.6M | 165.5M |
| $100.00 | 628.9M | 157.2M | 331M |
| $250.00 | 1.57B | 393.1M | 827.5M |
| $500.00 | 3.14B | 786.2M | 1.66B |
| $1,000.00 | 6.29B | 1.57B | 3.31B |
| $5,000.00 | 31.4B | 7.86B | 16.6B |
| $10,000.00 | 62.9B | 15.7B | 33.1B |
At these rates
- A workload with 70% input and 30% output costs $0.3021 per 1 million total tokens and $30.21 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 128,000-token context window with input alone would cost about $0.02035, 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.