Nebius
Llama 3.1 405B (Nebius) token cost
Meta Llama 3.1 405B on Nebius at competitive frontier open-weight rates.
Published list rates
Input
$1.00
per 1M tokens
Output
$3.00
per 1M tokens
Context window
128,000
tokens
Pricing source: Nebius Token Factory
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
- $0.07
- Output cost
- $0.09
- Total cost
- $0.16
- Combined price per 1M tokens
- $1.60
- Estimated monthly cost
- $96.00
- Estimated daily cost
- $3.20
Cost as volume grows
Read down to see Llama 3.1 405B (Nebius) 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 | $0.000001 | $0.000003 | $0.000002 |
| 10 | $0.00001 | $0.00003 | $0.000016 |
| 100 | $0.0001 | $0.0003 | $0.00016 |
| 200 | $0.0002 | $0.0006 | $0.00032 |
| 300 | $0.0003 | $0.0009 | $0.00048 |
| 400 | $0.0004 | $0.0012 | $0.00064 |
| 500 | $0.0005 | $0.0015 | $0.0008 |
| 1,000 | $0.001 | $0.003 | $0.0016 |
| 2,000 | $0.002 | $0.006 | $0.0032 |
| 5,000 | $0.005 | $0.015 | $0.008 |
| 10,000 | $0.01 | $0.03 | $0.016 |
| 25,000 | $0.025 | $0.075 | $0.04 |
| 50,000 | $0.05 | $0.15 | $0.08 |
| 100,000 | $0.1 | $0.3 | $0.16 |
| 250,000 | $0.25 | $0.75 | $0.4 |
| 500,000 | $0.5 | $1.50 | $0.8 |
| 1,000,000 | $1.00 | $3.00 | $1.60 |
| 5,000,000 | $5.00 | $15.00 | $8.00 |
| 10,000,000 | $10.00 | $30.00 | $16.00 |
| 50,000,000 | $50.00 | $150.00 | $80.00 |
| 100,000,000 | $100.00 | $300.00 | $160.00 |
| 500,000,000 | $500.00 | $1,500.00 | $800.00 |
| 1,000,000,000 | $1,000.00 | $3,000.00 | $1,600.00 |
| 10,000,000,000 | $10,000.00 | $30,000.00 | $16,000.00 |
| 100,000,000,000 | $100,000.00 | $300,000.00 | $160,000.00 |
Tokens for a fixed budget
Tokens Llama 3.1 405B (Nebius) can process for a set budget — send-only, reply-only, and a 70/30 mix.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 10,000 | 3,333 | 6,250 |
| $0.1 | 100,000 | 33,333 | 62,500 |
| $0.5 | 500,000 | 166,667 | 312,500 |
| $1.00 | 1M | 333,333 | 625,000 |
| $5.00 | 5M | 1.67M | 3.13M |
| $10.00 | 10M | 3.33M | 6.25M |
| $20.00 | 20M | 6.67M | 12.5M |
| $25.00 | 25M | 8.33M | 15.6M |
| $30.00 | 30M | 10M | 18.8M |
| $50.00 | 50M | 16.7M | 31.3M |
| $100.00 | 100M | 33.3M | 62.5M |
| $250.00 | 250M | 83.3M | 156.3M |
| $500.00 | 500M | 166.7M | 312.5M |
| $1,000.00 | 1B | 333.3M | 625M |
| $5,000.00 | 5B | 1.67B | 3.13B |
| $10,000.00 | 10B | 3.33B | 6.25B |
At these rates
- A workload with 70% input and 30% output costs $1.60 per 1 million total tokens and $160.00 per 100 million.
- At the same token count, output costs 3 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 $0.128, 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.