Cloudflare
GPT OSS 20B (Workers AI) token cost
OpenAI GPT OSS 20B on Cloudflare Workers AI at $0.20 / $0.30 per 1M tokens for edge-hosted open weights.
Published list rates
Input
$0.2
per 1M tokens
Output
$0.3
per 1M tokens
Context window
128,000
tokens
Pricing source: Cloudflare Workers 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 20B (Workers 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 | $0.0000002 | $0.0000003 | $0.00000023 |
| 10 | $0.000002 | $0.000003 | $0.000002 |
| 100 | $0.00002 | $0.00003 | $0.000023 |
| 200 | $0.00004 | $0.00006 | $0.000046 |
| 300 | $0.00006 | $0.00009 | $0.000069 |
| 400 | $0.00008 | $0.00012 | $0.000092 |
| 500 | $0.0001 | $0.00015 | $0.000115 |
| 1,000 | $0.0002 | $0.0003 | $0.00023 |
| 2,000 | $0.0004 | $0.0006 | $0.00046 |
| 5,000 | $0.001 | $0.0015 | $0.00115 |
| 10,000 | $0.002 | $0.003 | $0.0023 |
| 25,000 | $0.005 | $0.0075 | $0.00575 |
| 50,000 | $0.01 | $0.015 | $0.0115 |
| 100,000 | $0.02 | $0.03 | $0.023 |
| 250,000 | $0.05 | $0.075 | $0.0575 |
| 500,000 | $0.1 | $0.15 | $0.115 |
| 1,000,000 | $0.2 | $0.3 | $0.23 |
| 5,000,000 | $1.00 | $1.50 | $1.15 |
| 10,000,000 | $2.00 | $3.00 | $2.30 |
| 50,000,000 | $10.00 | $15.00 | $11.50 |
| 100,000,000 | $20.00 | $30.00 | $23.00 |
| 500,000,000 | $100.00 | $150.00 | $115.00 |
| 1,000,000,000 | $200.00 | $300.00 | $230.00 |
| 10,000,000,000 | $2,000.00 | $3,000.00 | $2,300.00 |
| 100,000,000,000 | $20,000.00 | $30,000.00 | $23,000.00 |
Tokens for a fixed budget
How far a fixed spend goes on GPT OSS 20B (Workers AI) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 50,000 | 33,333 | 43,478 |
| $0.1 | 500,000 | 333,333 | 434,783 |
| $0.5 | 2.5M | 1.67M | 2.17M |
| $1.00 | 5M | 3.33M | 4.35M |
| $5.00 | 25M | 16.7M | 21.7M |
| $10.00 | 50M | 33.3M | 43.5M |
| $20.00 | 100M | 66.7M | 87M |
| $25.00 | 125M | 83.3M | 108.7M |
| $30.00 | 150M | 100M | 130.4M |
| $50.00 | 250M | 166.7M | 217.4M |
| $100.00 | 500M | 333.3M | 434.8M |
| $250.00 | 1.25B | 833.3M | 1.09B |
| $500.00 | 2.5B | 1.67B | 2.17B |
| $1,000.00 | 5B | 3.33B | 4.35B |
| $5,000.00 | 25B | 16.7B | 21.7B |
| $10,000.00 | 50B | 33.3B | 43.5B |
At these rates
- A workload with 70% input and 30% output costs $0.23 per 1 million total tokens and $23.00 per 100 million.
- At the same token count, output costs 1.5 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 $0.0256, 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.