SambaNova
Llama 3.3 70B (SambaNova) token cost
Llama 3.3 70B Instruct on SambaNova Cloud for high-speed production chat.
Published list rates
Input
$0.6
per 1M tokens
Output
$1.20
per 1M tokens
Context window
128,000
tokens
Pricing source: SambaNova Cloud 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 Llama 3.3 70B (SambaNova) 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 | $0.0000006 | $0.000001 | $0.00000078 |
| 10 | $0.000006 | $0.000012 | $0.000008 |
| 100 | $0.00006 | $0.00012 | $0.000078 |
| 200 | $0.00012 | $0.00024 | $0.000156 |
| 300 | $0.00018 | $0.00036 | $0.000234 |
| 400 | $0.00024 | $0.00048 | $0.000312 |
| 500 | $0.0003 | $0.0006 | $0.00039 |
| 1,000 | $0.0006 | $0.0012 | $0.00078 |
| 2,000 | $0.0012 | $0.0024 | $0.00156 |
| 5,000 | $0.003 | $0.006 | $0.0039 |
| 10,000 | $0.006 | $0.012 | $0.0078 |
| 25,000 | $0.015 | $0.03 | $0.0195 |
| 50,000 | $0.03 | $0.06 | $0.039 |
| 100,000 | $0.06 | $0.12 | $0.078 |
| 250,000 | $0.15 | $0.3 | $0.195 |
| 500,000 | $0.3 | $0.6 | $0.39 |
| 1,000,000 | $0.6 | $1.20 | $0.78 |
| 5,000,000 | $3.00 | $6.00 | $3.90 |
| 10,000,000 | $6.00 | $12.00 | $7.80 |
| 50,000,000 | $30.00 | $60.00 | $39.00 |
| 100,000,000 | $60.00 | $120.00 | $78.00 |
| 500,000,000 | $300.00 | $600.00 | $390.00 |
| 1,000,000,000 | $600.00 | $1,200.00 | $780.00 |
| 10,000,000,000 | $6,000.00 | $12,000.00 | $7,800.00 |
| 100,000,000,000 | $60,000.00 | $120,000.00 | $78,000.00 |
Tokens for a fixed budget
How far a fixed spend goes on Llama 3.3 70B (SambaNova) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 16,667 | 8,333 | 12,821 |
| $0.1 | 166,667 | 83,333 | 128,205 |
| $0.5 | 833,333 | 416,667 | 641,026 |
| $1.00 | 1.67M | 833,333 | 1.28M |
| $5.00 | 8.33M | 4.17M | 6.41M |
| $10.00 | 16.7M | 8.33M | 12.8M |
| $20.00 | 33.3M | 16.7M | 25.6M |
| $25.00 | 41.7M | 20.8M | 32.1M |
| $30.00 | 50M | 25M | 38.5M |
| $50.00 | 83.3M | 41.7M | 64.1M |
| $100.00 | 166.7M | 83.3M | 128.2M |
| $250.00 | 416.7M | 208.3M | 320.5M |
| $500.00 | 833.3M | 416.7M | 641M |
| $1,000.00 | 1.67B | 833.3M | 1.28B |
| $5,000.00 | 8.33B | 4.17B | 6.41B |
| $10,000.00 | 16.7B | 8.33B | 12.8B |
At these rates
- A workload with 70% input and 30% output costs $0.78 per 1 million total tokens and $78.00 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 $0.0768, 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.