Baseten
Kimi K2.6 (Baseten) token cost
Kimi K2.6 on Baseten for long-context agent loops with cached input discounts.
Published list rates
Input
$0.95
per 1M tokens
Output
$4.00
per 1M tokens
Cached input
$0.16
per 1M tokens
Context window
256,000
tokens
Pricing source: Baseten Model APIs 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
Kimi K2.6 (Baseten) 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 | $0.00000095 | $0.000004 | $0.000002 |
| 10 | $0.00001 | $0.00004 | $0.000019 |
| 100 | $0.000095 | $0.0004 | $0.000186 |
| 200 | $0.00019 | $0.0008 | $0.000373 |
| 300 | $0.000285 | $0.0012 | $0.00056 |
| 400 | $0.00038 | $0.0016 | $0.000746 |
| 500 | $0.000475 | $0.002 | $0.000933 |
| 1,000 | $0.00095 | $0.004 | $0.001865 |
| 2,000 | $0.0019 | $0.008 | $0.00373 |
| 5,000 | $0.00475 | $0.02 | $0.009325 |
| 10,000 | $0.0095 | $0.04 | $0.01865 |
| 25,000 | $0.02375 | $0.1 | $0.04663 |
| 50,000 | $0.0475 | $0.2 | $0.09325 |
| 100,000 | $0.095 | $0.4 | $0.1865 |
| 250,000 | $0.2375 | $1.00 | $0.46625 |
| 500,000 | $0.475 | $2.00 | $0.9325 |
| 1,000,000 | $0.95 | $4.00 | $1.865 |
| 5,000,000 | $4.75 | $20.00 | $9.325 |
| 10,000,000 | $9.50 | $40.00 | $18.65 |
| 50,000,000 | $47.50 | $200.00 | $93.25 |
| 100,000,000 | $95.00 | $400.00 | $186.50 |
| 500,000,000 | $475.00 | $2,000.00 | $932.50 |
| 1,000,000,000 | $950.00 | $4,000.00 | $1,865.00 |
| 10,000,000,000 | $9,500.00 | $40,000.00 | $18,650.00 |
| 100,000,000,000 | $95,000.00 | $400,000.00 | $186,500.00 |
Tokens for a fixed budget
Tokens Kimi K2.6 (Baseten) 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 | 10,526 | 2,500 | 5,362 |
| $0.1 | 105,263 | 25,000 | 53,619 |
| $0.5 | 526,316 | 125,000 | 268,097 |
| $1.00 | 1.05M | 250,000 | 536,193 |
| $5.00 | 5.26M | 1.25M | 2.68M |
| $10.00 | 10.5M | 2.5M | 5.36M |
| $20.00 | 21.1M | 5M | 10.7M |
| $25.00 | 26.3M | 6.25M | 13.4M |
| $30.00 | 31.6M | 7.5M | 16.1M |
| $50.00 | 52.6M | 12.5M | 26.8M |
| $100.00 | 105.3M | 25M | 53.6M |
| $250.00 | 263.2M | 62.5M | 134M |
| $500.00 | 526.3M | 125M | 268.1M |
| $1,000.00 | 1.05B | 250M | 536.2M |
| $5,000.00 | 5.26B | 1.25B | 2.68B |
| $10,000.00 | 10.5B | 2.5B | 5.36B |
At these rates
- A workload with 70% input and 30% output costs $1.865 per 1 million total tokens and $186.50 per 100 million.
- At the same token count, output costs 4.21 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 256,000-token context window with input alone would cost about $0.2432, before any output.
- Cached input is $0.16 per million, 83% 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.