Cerebras
GPT OSS 120B (Cerebras) token cost
GPT OSS 120B on Cerebras wafer-scale inference — compare host rates with Groq, Fireworks, and Together.
Published list rates
Input
$0.35
per 1M tokens
Output
$0.75
per 1M tokens
Context window
131,072
tokens
Pricing source: Cerebras 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
What GPT OSS 120B (Cerebras) 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 | $0.00000035 | $0.00000075 | $0.00000047 |
| 10 | $0.000004 | $0.000008 | $0.000005 |
| 100 | $0.000035 | $0.000075 | $0.000047 |
| 200 | $0.00007 | $0.00015 | $0.000094 |
| 300 | $0.000105 | $0.000225 | $0.000141 |
| 400 | $0.00014 | $0.0003 | $0.000188 |
| 500 | $0.000175 | $0.000375 | $0.000235 |
| 1,000 | $0.00035 | $0.00075 | $0.00047 |
| 2,000 | $0.0007 | $0.0015 | $0.00094 |
| 5,000 | $0.00175 | $0.00375 | $0.00235 |
| 10,000 | $0.0035 | $0.0075 | $0.0047 |
| 25,000 | $0.00875 | $0.01875 | $0.01175 |
| 50,000 | $0.0175 | $0.0375 | $0.0235 |
| 100,000 | $0.035 | $0.075 | $0.047 |
| 250,000 | $0.0875 | $0.1875 | $0.1175 |
| 500,000 | $0.175 | $0.375 | $0.235 |
| 1,000,000 | $0.35 | $0.75 | $0.47 |
| 5,000,000 | $1.75 | $3.75 | $2.35 |
| 10,000,000 | $3.50 | $7.50 | $4.70 |
| 50,000,000 | $17.50 | $37.50 | $23.50 |
| 100,000,000 | $35.00 | $75.00 | $47.00 |
| 500,000,000 | $175.00 | $375.00 | $235.00 |
| 1,000,000,000 | $350.00 | $750.00 | $470.00 |
| 10,000,000,000 | $3,500.00 | $7,500.00 | $4,700.00 |
| 100,000,000,000 | $35,000.00 | $75,000.00 | $47,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many GPT OSS 120B (Cerebras) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 28,571 | 13,333 | 21,277 |
| $0.1 | 285,714 | 133,333 | 212,766 |
| $0.5 | 1.43M | 666,667 | 1.06M |
| $1.00 | 2.86M | 1.33M | 2.13M |
| $5.00 | 14.3M | 6.67M | 10.6M |
| $10.00 | 28.6M | 13.3M | 21.3M |
| $20.00 | 57.1M | 26.7M | 42.6M |
| $25.00 | 71.4M | 33.3M | 53.2M |
| $30.00 | 85.7M | 40M | 63.8M |
| $50.00 | 142.9M | 66.7M | 106.4M |
| $100.00 | 285.7M | 133.3M | 212.8M |
| $250.00 | 714.3M | 333.3M | 531.9M |
| $500.00 | 1.43B | 666.7M | 1.06B |
| $1,000.00 | 2.86B | 1.33B | 2.13B |
| $5,000.00 | 14.3B | 6.67B | 10.6B |
| $10,000.00 | 28.6B | 13.3B | 21.3B |
At these rates
- A workload with 70% input and 30% output costs $0.47 per 1 million total tokens and $47.00 per 100 million.
- At the same token count, output costs 2.14 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 $0.04588, 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.