Baseten
GPT OSS 120B (Baseten) token cost
OpenAI gpt-oss-120b on Baseten Model APIs at low open-weight token rates.
Published list rates
Input
$0.1
per 1M tokens
Output
$0.5
per 1M tokens
Context window
128,000
tokens
Pricing source: Baseten Model APIs 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 (Baseten): 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 | $0.0000001 | $0.0000005 | $0.00000022 |
| 10 | $0.000001 | $0.000005 | $0.000002 |
| 100 | $0.00001 | $0.00005 | $0.000022 |
| 200 | $0.00002 | $0.0001 | $0.000044 |
| 300 | $0.00003 | $0.00015 | $0.000066 |
| 400 | $0.00004 | $0.0002 | $0.000088 |
| 500 | $0.00005 | $0.00025 | $0.00011 |
| 1,000 | $0.0001 | $0.0005 | $0.00022 |
| 2,000 | $0.0002 | $0.001 | $0.00044 |
| 5,000 | $0.0005 | $0.0025 | $0.0011 |
| 10,000 | $0.001 | $0.005 | $0.0022 |
| 25,000 | $0.0025 | $0.0125 | $0.0055 |
| 50,000 | $0.005 | $0.025 | $0.011 |
| 100,000 | $0.01 | $0.05 | $0.022 |
| 250,000 | $0.025 | $0.125 | $0.055 |
| 500,000 | $0.05 | $0.25 | $0.11 |
| 1,000,000 | $0.1 | $0.5 | $0.22 |
| 5,000,000 | $0.5 | $2.50 | $1.10 |
| 10,000,000 | $1.00 | $5.00 | $2.20 |
| 50,000,000 | $5.00 | $25.00 | $11.00 |
| 100,000,000 | $10.00 | $50.00 | $22.00 |
| 500,000,000 | $50.00 | $250.00 | $110.00 |
| 1,000,000,000 | $100.00 | $500.00 | $220.00 |
| 10,000,000,000 | $1,000.00 | $5,000.00 | $2,200.00 |
| 100,000,000,000 | $10,000.00 | $50,000.00 | $22,000.00 |
Tokens for a fixed budget
Tokens GPT OSS 120B (Baseten) 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 | 100,000 | 20,000 | 45,455 |
| $0.1 | 1M | 200,000 | 454,545 |
| $0.5 | 5M | 1M | 2.27M |
| $1.00 | 10M | 2M | 4.55M |
| $5.00 | 50M | 10M | 22.7M |
| $10.00 | 100M | 20M | 45.5M |
| $20.00 | 200M | 40M | 90.9M |
| $25.00 | 250M | 50M | 113.6M |
| $30.00 | 300M | 60M | 136.4M |
| $50.00 | 500M | 100M | 227.3M |
| $100.00 | 1B | 200M | 454.5M |
| $250.00 | 2.5B | 500M | 1.14B |
| $500.00 | 5B | 1B | 2.27B |
| $1,000.00 | 10B | 2B | 4.55B |
| $5,000.00 | 50B | 10B | 22.7B |
| $10,000.00 | 100B | 20B | 45.5B |
At these rates
- A workload with 70% input and 30% output costs $0.22 per 1 million total tokens and $22.00 per 100 million.
- At the same token count, output costs 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.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.