SambaNova
MiniMax M2.7 (SambaNova) token cost
MiniMax M2.7 on SambaNova with cached-input discounts for long coding sessions.
Published list rates
Input
$0.6
per 1M tokens
Output
$2.40
per 1M tokens
Cached input
$0.06
per 1M tokens
Context window
200,000
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
MiniMax M2.7 (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 | $0.0000006 | $0.000002 | $0.000001 |
| 10 | $0.000006 | $0.000024 | $0.000011 |
| 100 | $0.00006 | $0.00024 | $0.000114 |
| 200 | $0.00012 | $0.00048 | $0.000228 |
| 300 | $0.00018 | $0.00072 | $0.000342 |
| 400 | $0.00024 | $0.00096 | $0.000456 |
| 500 | $0.0003 | $0.0012 | $0.00057 |
| 1,000 | $0.0006 | $0.0024 | $0.00114 |
| 2,000 | $0.0012 | $0.0048 | $0.00228 |
| 5,000 | $0.003 | $0.012 | $0.0057 |
| 10,000 | $0.006 | $0.024 | $0.0114 |
| 25,000 | $0.015 | $0.06 | $0.0285 |
| 50,000 | $0.03 | $0.12 | $0.057 |
| 100,000 | $0.06 | $0.24 | $0.114 |
| 250,000 | $0.15 | $0.6 | $0.285 |
| 500,000 | $0.3 | $1.20 | $0.57 |
| 1,000,000 | $0.6 | $2.40 | $1.14 |
| 5,000,000 | $3.00 | $12.00 | $5.70 |
| 10,000,000 | $6.00 | $24.00 | $11.40 |
| 50,000,000 | $30.00 | $120.00 | $57.00 |
| 100,000,000 | $60.00 | $240.00 | $114.00 |
| 500,000,000 | $300.00 | $1,200.00 | $570.00 |
| 1,000,000,000 | $600.00 | $2,400.00 | $1,140.00 |
| 10,000,000,000 | $6,000.00 | $24,000.00 | $11,400.00 |
| 100,000,000,000 | $60,000.00 | $240,000.00 | $114,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many MiniMax M2.7 (SambaNova) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 16,667 | 4,167 | 8,772 |
| $0.1 | 166,667 | 41,667 | 87,719 |
| $0.5 | 833,333 | 208,333 | 438,596 |
| $1.00 | 1.67M | 416,667 | 877,193 |
| $5.00 | 8.33M | 2.08M | 4.39M |
| $10.00 | 16.7M | 4.17M | 8.77M |
| $20.00 | 33.3M | 8.33M | 17.5M |
| $25.00 | 41.7M | 10.4M | 21.9M |
| $30.00 | 50M | 12.5M | 26.3M |
| $50.00 | 83.3M | 20.8M | 43.9M |
| $100.00 | 166.7M | 41.7M | 87.7M |
| $250.00 | 416.7M | 104.2M | 219.3M |
| $500.00 | 833.3M | 208.3M | 438.6M |
| $1,000.00 | 1.67B | 416.7M | 877.2M |
| $5,000.00 | 8.33B | 2.08B | 4.39B |
| $10,000.00 | 16.7B | 4.17B | 8.77B |
At these rates
- A workload with 70% input and 30% output costs $1.14 per 1 million total tokens and $114.00 per 100 million.
- At the same token count, output costs 4 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 200,000-token context window with input alone would cost about $0.12, before any output.
- Cached input is $0.06 per million, 90% below standard input when the workload meets the provider’s cache rules.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.