Models / Kimi pricing
Kimi API pricing
4 Kimi models from Moonshot AI on one key, per million tokens. Input 40% to 70% under Moonshot AI's list price, output 40% to 70%. Lowest price: Kimi K2.5, $0.27 in and $1.35 out.
Prices · per million tokens, USD, next to Moonshot AI's list price
| Model | Input | Cached input | Output | Under list |
|---|---|---|---|---|
| Kimi K3kimi-k3 | $0.90list $3.00 | $0.09list $0.30 | $4.50list $15.00 | 70% in · 70% out |
| Kimi K2.7 Codekimi-k2.7-code | $0.426list $0.71 | $0.09list $0.15 | $2.10list $3.50 | 40% in · 40% out |
| Kimi K2.6kimi-k2.6 | $0.57list $0.95 | $0.096list $0.16 | $2.40list $4.00 | 40% in · 40% out |
| Kimi K2.5kimi-k2.5 | $0.27list $0.45 | $0.042list $0.07 | $1.35list $2.25 | 40% in · 40% out |
List price: Moonshot AI's published rate, read October 2026. Live from GET https://api.uplinkswitch.com/v1/catalog.
Call them · same base URL and key for every model
Python · OpenAI SDK
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)TypeScript · OpenAI SDK
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'kimi-k3',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);Questions
- Which Kimi model costs the least?
- Kimi K2.5 (kimi-k2.5): $0.27 per million input tokens and $1.35 per million output tokens.
- How far under Moonshot AI's list price is it?
- Input runs 40% to 70% under Moonshot AI's list price, output 40% to 70%, depending on the model. Each row above shows both prices.
- Is there a subscription?
- No. Prepaid credit from $10, with no subscription or monthly fee. Each top-up locks your prices for 30 days.
- How is cached input billed?
- At the cached rate in the table. A model with no cached rate bills cached tokens at its input rate.
- Are there rate limits?
- Every key carries a request-per-minute limit and a concurrency limit.