SiliconFlow
gpt-oss-120b (SiliconFlow) token cost
OpenAI gpt-oss-120b on SiliconFlow at competitive open-weight serverless rates.
Published list rates
Input
$0.05
per 1M tokens
Output
$0.45
per 1M tokens
Context window
131,000
tokens
Pricing source: SiliconFlow 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
- $0.0035
- Output cost
- $0.0135
- Total cost
- $0.017
- Combined price per 1M tokens
- $0.17
- Estimated monthly cost
- $10.20
- Estimated daily cost
- $0.34
Cost as volume grows
What gpt-oss-120b (SiliconFlow) costs if you only send tokens, only get a reply, or do both (70% in / 30% out). Rows start small and go up to huge traffic.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000005 | $0.00000045 | $0.00000017 |
| 10 | $0.0000005 | $0.000005 | $0.000002 |
| 100 | $0.000005 | $0.000045 | $0.000017 |
| 200 | $0.00001 | $0.00009 | $0.000034 |
| 300 | $0.000015 | $0.000135 | $0.000051 |
| 400 | $0.00002 | $0.00018 | $0.000068 |
| 500 | $0.000025 | $0.000225 | $0.000085 |
| 1,000 | $0.00005 | $0.00045 | $0.00017 |
| 2,000 | $0.0001 | $0.0009 | $0.00034 |
| 5,000 | $0.00025 | $0.00225 | $0.00085 |
| 10,000 | $0.0005 | $0.0045 | $0.0017 |
| 25,000 | $0.00125 | $0.01125 | $0.00425 |
| 50,000 | $0.0025 | $0.0225 | $0.0085 |
| 100,000 | $0.005 | $0.045 | $0.017 |
| 250,000 | $0.0125 | $0.1125 | $0.0425 |
| 500,000 | $0.025 | $0.225 | $0.085 |
| 1,000,000 | $0.05 | $0.45 | $0.17 |
| 5,000,000 | $0.25 | $2.25 | $0.85 |
| 10,000,000 | $0.5 | $4.50 | $1.70 |
| 50,000,000 | $2.50 | $22.50 | $8.50 |
| 100,000,000 | $5.00 | $45.00 | $17.00 |
| 500,000,000 | $25.00 | $225.00 | $85.00 |
| 1,000,000,000 | $50.00 | $450.00 | $170.00 |
| 10,000,000,000 | $500.00 | $4,500.00 | $1,700.00 |
| 100,000,000,000 | $5,000.00 | $45,000.00 | $17,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many gpt-oss-120b (SiliconFlow) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 200,000 | 22,222 | 58,824 |
| $0.1 | 2M | 222,222 | 588,235 |
| $0.5 | 10M | 1.11M | 2.94M |
| $1.00 | 20M | 2.22M | 5.88M |
| $5.00 | 100M | 11.1M | 29.4M |
| $10.00 | 200M | 22.2M | 58.8M |
| $20.00 | 400M | 44.4M | 117.6M |
| $25.00 | 500M | 55.6M | 147.1M |
| $30.00 | 600M | 66.7M | 176.5M |
| $50.00 | 1B | 111.1M | 294.1M |
| $100.00 | 2B | 222.2M | 588.2M |
| $250.00 | 5B | 555.6M | 1.47B |
| $500.00 | 10B | 1.11B | 2.94B |
| $1,000.00 | 20B | 2.22B | 5.88B |
| $5,000.00 | 100B | 11.1B | 29.4B |
| $10,000.00 | 200B | 22.2B | 58.8B |
At these rates
- A workload with 70% input and 30% output costs $0.17 per 1 million total tokens and $17.00 per 100 million.
- At the same token count, output costs 9 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 131,000-token context window with input alone would cost about $0.00655, 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.