DeepInfra
Llama 3.1 8B Turbo (DeepInfra) token cost
Ultra-cheap Llama 3.1 8B Turbo on DeepInfra for routing, classification, and light agents.
Published list rates
Input
$0.02
per 1M tokens
Output
$0.04
per 1M tokens
Context window
128,000
tokens
Pricing source: DeepInfra 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
Llama 3.1 8B Turbo (DeepInfra) at rising volume: prompt-only, reply-only, and a mixed chat (70% in, 30% out).
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000002 | $0.00000004 | $0.000000026 |
| 10 | $0.0000002 | $0.0000004 | $0.00000026 |
| 100 | $0.000002 | $0.000004 | $0.000003 |
| 200 | $0.000004 | $0.000008 | $0.000005 |
| 300 | $0.000006 | $0.000012 | $0.000008 |
| 400 | $0.000008 | $0.000016 | $0.00001 |
| 500 | $0.00001 | $0.00002 | $0.000013 |
| 1,000 | $0.00002 | $0.00004 | $0.000026 |
| 2,000 | $0.00004 | $0.00008 | $0.000052 |
| 5,000 | $0.0001 | $0.0002 | $0.00013 |
| 10,000 | $0.0002 | $0.0004 | $0.00026 |
| 25,000 | $0.0005 | $0.001 | $0.00065 |
| 50,000 | $0.001 | $0.002 | $0.0013 |
| 100,000 | $0.002 | $0.004 | $0.0026 |
| 250,000 | $0.005 | $0.01 | $0.0065 |
| 500,000 | $0.01 | $0.02 | $0.013 |
| 1,000,000 | $0.02 | $0.04 | $0.026 |
| 5,000,000 | $0.1 | $0.2 | $0.13 |
| 10,000,000 | $0.2 | $0.4 | $0.26 |
| 50,000,000 | $1.00 | $2.00 | $1.30 |
| 100,000,000 | $2.00 | $4.00 | $2.60 |
| 500,000,000 | $10.00 | $20.00 | $13.00 |
| 1,000,000,000 | $20.00 | $40.00 | $26.00 |
| 10,000,000,000 | $200.00 | $400.00 | $260.00 |
| 100,000,000,000 | $2,000.00 | $4,000.00 | $2,600.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many Llama 3.1 8B Turbo (DeepInfra) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 500,000 | 250,000 | 384,615 |
| $0.1 | 5M | 2.5M | 3.85M |
| $0.5 | 25M | 12.5M | 19.2M |
| $1.00 | 50M | 25M | 38.5M |
| $5.00 | 250M | 125M | 192.3M |
| $10.00 | 500M | 250M | 384.6M |
| $20.00 | 1B | 500M | 769.2M |
| $25.00 | 1.25B | 625M | 961.5M |
| $30.00 | 1.5B | 750M | 1.15B |
| $50.00 | 2.5B | 1.25B | 1.92B |
| $100.00 | 5B | 2.5B | 3.85B |
| $250.00 | 12.5B | 6.25B | 9.62B |
| $500.00 | 25B | 12.5B | 19.2B |
| $1,000.00 | 50B | 25B | 38.5B |
| $5,000.00 | 250B | 125B | 192.3B |
| $10,000.00 | 500B | 250B | 384.6B |
At these rates
- A workload with 70% input and 30% output costs $0.026 per 1 million total tokens and $2.60 per 100 million.
- At the same token count, output costs 2 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 $0.00256, 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.