SambaNova
Gemma 4 31B (SambaNova) token cost
Gemma 4 31B on SambaNova for fast open multimodal-class chat at mid-tier rates.
Published list rates
Input
$0.38
per 1M tokens
Output
$1.15
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
Gemma 4 31B (SambaNova) 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 | $0.00000038 | $0.000001 | $0.000000611 |
| 10 | $0.000004 | $0.000012 | $0.000006 |
| 100 | $0.000038 | $0.000115 | $0.000061 |
| 200 | $0.000076 | $0.00023 | $0.000122 |
| 300 | $0.000114 | $0.000345 | $0.000183 |
| 400 | $0.000152 | $0.00046 | $0.000244 |
| 500 | $0.00019 | $0.000575 | $0.000306 |
| 1,000 | $0.00038 | $0.00115 | $0.000611 |
| 2,000 | $0.00076 | $0.0023 | $0.001222 |
| 5,000 | $0.0019 | $0.00575 | $0.003055 |
| 10,000 | $0.0038 | $0.0115 | $0.00611 |
| 25,000 | $0.0095 | $0.02875 | $0.01528 |
| 50,000 | $0.019 | $0.0575 | $0.03055 |
| 100,000 | $0.038 | $0.115 | $0.0611 |
| 250,000 | $0.095 | $0.2875 | $0.15275 |
| 500,000 | $0.19 | $0.575 | $0.3055 |
| 1,000,000 | $0.38 | $1.15 | $0.611 |
| 5,000,000 | $1.90 | $5.75 | $3.055 |
| 10,000,000 | $3.80 | $11.50 | $6.11 |
| 50,000,000 | $19.00 | $57.50 | $30.55 |
| 100,000,000 | $38.00 | $115.00 | $61.10 |
| 500,000,000 | $190.00 | $575.00 | $305.50 |
| 1,000,000,000 | $380.00 | $1,150.00 | $611.00 |
| 10,000,000,000 | $3,800.00 | $11,500.00 | $6,110.00 |
| 100,000,000,000 | $38,000.00 | $115,000.00 | $61,100.00 |
Tokens for a fixed budget
Tokens Gemma 4 31B (SambaNova) 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 | 26,316 | 8,696 | 16,367 |
| $0.1 | 263,158 | 86,957 | 163,666 |
| $0.5 | 1.32M | 434,783 | 818,331 |
| $1.00 | 2.63M | 869,565 | 1.64M |
| $5.00 | 13.2M | 4.35M | 8.18M |
| $10.00 | 26.3M | 8.7M | 16.4M |
| $20.00 | 52.6M | 17.4M | 32.7M |
| $25.00 | 65.8M | 21.7M | 40.9M |
| $30.00 | 78.9M | 26.1M | 49.1M |
| $50.00 | 131.6M | 43.5M | 81.8M |
| $100.00 | 263.2M | 87M | 163.7M |
| $250.00 | 657.9M | 217.4M | 409.2M |
| $500.00 | 1.32B | 434.8M | 818.3M |
| $1,000.00 | 2.63B | 869.6M | 1.64B |
| $5,000.00 | 13.2B | 4.35B | 8.18B |
| $10,000.00 | 26.3B | 8.7B | 16.4B |
At these rates
- A workload with 70% input and 30% output costs $0.611 per 1 million total tokens and $61.10 per 100 million.
- At the same token count, output costs 3.03 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 $0.04864, 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.