Fireworks
GPT OSS 20B (Fireworks) token cost
Smaller GPT OSS 20B on Fireworks for ultra-cheap, fast tool-calling loops.
Published list rates
Input
$0.07
per 1M tokens
Output
$0.3
per 1M tokens
Cached input
$0.035
per 1M tokens
Context window
131,072
tokens
Pricing source: Fireworks serverless 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
Read down to see GPT OSS 20B (Fireworks) get more expensive as tokens grow. The last column is a typical mix: 70% input, 30% output.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000007 | $0.0000003 | $0.000000139 |
| 10 | $0.0000007 | $0.000003 | $0.000001 |
| 100 | $0.000007 | $0.00003 | $0.000014 |
| 200 | $0.000014 | $0.00006 | $0.000028 |
| 300 | $0.000021 | $0.00009 | $0.000042 |
| 400 | $0.000028 | $0.00012 | $0.000056 |
| 500 | $0.000035 | $0.00015 | $0.00007 |
| 1,000 | $0.00007 | $0.0003 | $0.000139 |
| 2,000 | $0.00014 | $0.0006 | $0.000278 |
| 5,000 | $0.00035 | $0.0015 | $0.000695 |
| 10,000 | $0.0007 | $0.003 | $0.00139 |
| 25,000 | $0.00175 | $0.0075 | $0.003475 |
| 50,000 | $0.0035 | $0.015 | $0.00695 |
| 100,000 | $0.007 | $0.03 | $0.0139 |
| 250,000 | $0.0175 | $0.075 | $0.03475 |
| 500,000 | $0.035 | $0.15 | $0.0695 |
| 1,000,000 | $0.07 | $0.3 | $0.139 |
| 5,000,000 | $0.35 | $1.50 | $0.695 |
| 10,000,000 | $0.7 | $3.00 | $1.39 |
| 50,000,000 | $3.50 | $15.00 | $6.95 |
| 100,000,000 | $7.00 | $30.00 | $13.90 |
| 500,000,000 | $35.00 | $150.00 | $69.50 |
| 1,000,000,000 | $70.00 | $300.00 | $139.00 |
| 10,000,000,000 | $700.00 | $3,000.00 | $1,390.00 |
| 100,000,000,000 | $7,000.00 | $30,000.00 | $13,900.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many GPT OSS 20B (Fireworks) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 142,857 | 33,333 | 71,942 |
| $0.1 | 1.43M | 333,333 | 719,424 |
| $0.5 | 7.14M | 1.67M | 3.6M |
| $1.00 | 14.3M | 3.33M | 7.19M |
| $5.00 | 71.4M | 16.7M | 36M |
| $10.00 | 142.9M | 33.3M | 71.9M |
| $20.00 | 285.7M | 66.7M | 143.9M |
| $25.00 | 357.1M | 83.3M | 179.9M |
| $30.00 | 428.6M | 100M | 215.8M |
| $50.00 | 714.3M | 166.7M | 359.7M |
| $100.00 | 1.43B | 333.3M | 719.4M |
| $250.00 | 3.57B | 833.3M | 1.8B |
| $500.00 | 7.14B | 1.67B | 3.6B |
| $1,000.00 | 14.3B | 3.33B | 7.19B |
| $5,000.00 | 71.4B | 16.7B | 36B |
| $10,000.00 | 142.9B | 33.3B | 71.9B |
At these rates
- A workload with 70% input and 30% output costs $0.139 per 1 million total tokens and $13.90 per 100 million.
- At the same token count, output costs 4.29 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 $0.009175, before any output.
- Cached input is $0.035 per million, 50% below standard input when the workload meets the provider’s cache rules.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.