Together AI
Kimi K2.6 (Together) token cost
Kimi K2.6 on Together serverless for long-context coding and document agents.
Published list rates
Input
$1.20
per 1M tokens
Output
$4.50
per 1M tokens
Cached input
$0.2
per 1M tokens
Context window
256,000
tokens
Pricing source: Together AI 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
- 100,000
- Characters
- 400,000
- Words
- 75,000
- Input tokens
- 70,000
- Output tokens
- 30,000
- Input cost
- $0.084
- Output cost
- $0.135
- Total cost
- $0.219
- Combined price per 1M tokens
- $2.19
- Estimated monthly cost
- $131.40
- Estimated daily cost
- $4.38
Cost as volume grows
Three views of Kimi K2.6 (Together): sending only, receiving only, and a 70/30 mix. Same list rates, bigger rows.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.000001 | $0.000005 | $0.000002 |
| 10 | $0.000012 | $0.000045 | $0.000022 |
| 100 | $0.00012 | $0.00045 | $0.000219 |
| 200 | $0.00024 | $0.0009 | $0.000438 |
| 300 | $0.00036 | $0.00135 | $0.000657 |
| 400 | $0.00048 | $0.0018 | $0.000876 |
| 500 | $0.0006 | $0.00225 | $0.001095 |
| 1,000 | $0.0012 | $0.0045 | $0.00219 |
| 2,000 | $0.0024 | $0.009 | $0.00438 |
| 5,000 | $0.006 | $0.0225 | $0.01095 |
| 10,000 | $0.012 | $0.045 | $0.0219 |
| 25,000 | $0.03 | $0.1125 | $0.05475 |
| 50,000 | $0.06 | $0.225 | $0.1095 |
| 100,000 | $0.12 | $0.45 | $0.219 |
| 250,000 | $0.3 | $1.125 | $0.5475 |
| 500,000 | $0.6 | $2.25 | $1.095 |
| 1,000,000 | $1.20 | $4.50 | $2.19 |
| 5,000,000 | $6.00 | $22.50 | $10.95 |
| 10,000,000 | $12.00 | $45.00 | $21.90 |
| 50,000,000 | $60.00 | $225.00 | $109.50 |
| 100,000,000 | $120.00 | $450.00 | $219.00 |
| 500,000,000 | $600.00 | $2,250.00 | $1,095.00 |
| 1,000,000,000 | $1,200.00 | $4,500.00 | $2,190.00 |
| 10,000,000,000 | $12,000.00 | $45,000.00 | $21,900.00 |
| 100,000,000,000 | $120,000.00 | $450,000.00 | $219,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many Kimi K2.6 (Together) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 8,333 | 2,222 | 4,566 |
| $0.1 | 83,333 | 22,222 | 45,662 |
| $0.5 | 416,667 | 111,111 | 228,311 |
| $1.00 | 833,333 | 222,222 | 456,621 |
| $5.00 | 4.17M | 1.11M | 2.28M |
| $10.00 | 8.33M | 2.22M | 4.57M |
| $20.00 | 16.7M | 4.44M | 9.13M |
| $25.00 | 20.8M | 5.56M | 11.4M |
| $30.00 | 25M | 6.67M | 13.7M |
| $50.00 | 41.7M | 11.1M | 22.8M |
| $100.00 | 83.3M | 22.2M | 45.7M |
| $250.00 | 208.3M | 55.6M | 114.2M |
| $500.00 | 416.7M | 111.1M | 228.3M |
| $1,000.00 | 833.3M | 222.2M | 456.6M |
| $5,000.00 | 4.17B | 1.11B | 2.28B |
| $10,000.00 | 8.33B | 2.22B | 4.57B |
At these rates
- A workload with 70% input and 30% output costs $2.19 per 1 million total tokens and $219.00 per 100 million.
- At the same token count, output costs 3.75 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 $0.3072, before any output.
- Cached input is $0.2 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.