Kimi API pricing, October 2026: every Moonshot AI model per million tokens
Input, cached and output prices for every Kimi model, Moonshot AI's list price next to ours, and what a chat turn and a long-document request cost on Kimi K3, K2.7 Code and K2.5.
How the Kimi API is priced
Moonshot AI bills Kimi API calls per token, at three rates per million tokens: input, cached input and output. Kimi output costs four to five times input, so on a 2,000-token prompt with a 500-token answer, the answer costs more than the prompt. A request costs its tokens times the rates of the model it named; there is no seat or plan price.
Every Kimi model
4 Kimi models. Each row shows our price and Moonshot AI's list price.
| Model | Input | Cached | Output | List input | List cached | List output |
|---|---|---|---|---|---|---|
| Kimi K3 | $0.90 | $0.09 | $4.50 | $3.00 | $0.30 | $15.00 |
| Kimi K2.7 Code | $0.426 | $0.09 | $2.10 | $0.71 | $0.15 | $3.50 |
| Kimi K2.6 | $0.57 | $0.096 | $2.40 | $0.95 | $0.16 | $4.00 |
| Kimi K2.5 | $0.27 | $0.042 | $1.35 | $0.45 | $0.07 | $2.25 |
USD per million tokens. Ours from the live catalog; list is the price on Moonshot AI's pricing page, the read date on each model page.
The lowest price here is Kimi K2.5: $0.27 in and $1.35 out.
Two requests, worked
A chat turn of 2,000 input and 500 output tokens, and a long-document request of 50,000 input and 2,000 output. Both sizes are assumptions; nothing is counted at the cached rate.
| Model | Chat turn, list | Chat turn, here | Long document, list | Long document, here |
|---|---|---|---|---|
| Kimi K3 | $0.0135 | $0.0041 | $0.18 | $0.054 |
| Kimi K2.7 Code | $0.0032 | $0.0019 | $0.0425 | $0.0255 |
| Kimi K2.5 | $0.002 | $0.0012 | $0.027 | $0.0162 |
Input tokens times the input rate plus output tokens times the output rate, per million.
Kimi K3: $0.90 in and $4.50 out here, against $3.00 and $15.00 at list, 70% under on input and 70% on output.
Kimi K2.7 Code: $0.426 in and $2.10 out here, against $0.71 and $3.50 at list, 40% under on input and 40% on output.
Kimi K2.5: $0.27 in and $1.35 out here, against $0.45 and $2.25 at list, 40% under on input and 40% on output.
Cached input
When a request repeats a prefix the API has seen, such as a long system prompt or a document, the response reports those tokens as cached and they bill at the cached rate in the first table. A model with no cached rate bills them at its input rate.
Calling it
Point the SDK at our base URL with your key. Every Kimi id in the table works with the same two values.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="kimi-k3",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)More in the SDK guide.
Questions
Is there a subscription? No. Credit is prepaid from $10, and each top-up locks your prices for 30 days. New accounts start with $1 free.
Which Kimi model should I use? Kimi K3 for the hardest prompts. K2.7 Code for coding agents and edits. K2.5 has the lowest price in the family, so it fits chat and summaries. Run the same prompt on each and compare.
Where is the full price list? On the Kimi pricing page, and every other model on the Models page. To see what your own usage would cost, re-price an export on the savings page.