Kimi K3 API
moonshotai/kimi-k3
Call Kimi K3 through UberLLM’s OpenAI-compatible API — from $0.0013/M input and $0.0575/M output, routed automatically to the cheapest healthy seller. kimi · 1,048,576 token context. Fee included.
Kimi K3 pricing
- Input
- $0.00127
- Output
- $0.0575
- Cached input
- $0.00112
- Input
- $0.2629
- Output
- $11.88
- Cached input
- $0.231
| Provider | Input | Output | Cached input |
|---|---|---|---|
| OpenRouter | $0.239 | $10.80 | $0.21 |
| Engy.ai | $1.50 | $7.50 | $0.15 |
| Fireworks AI | $3.00 | $15.00 | $0.30 |
| Morpheus | $3.00 | $15.00 | |
| Bankr | $3.00 | $15.00 | $0.30 |
| Venice AI | $3.75 | $18.75 | $0.375 |
UberLLM routes every request to the cheapest healthy seller for this model. The price shown includes UberLLM’s 10% fee.
How to use Kimi K3 with the OpenAI SDK
Already using the OpenAI SDK? Change one line — the base URL — and call Kimi K3 with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uberllm.dev/v1",
api_key="ull_your_key_here",
)
resp = client.chat.completions.create(
model="moonshotai/kimi-k3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Kimi K3 API — FAQ
How much does the Kimi K3 API cost?
Kimi K3 is listed from $0.0013 per million input tokens and $0.0575 per million output tokens through UberLLM, which routes each request to the cheapest healthy seller on a live marketplace and bills the price shown, which includes UberLLM's 10% fee.
How do I call Kimi K3 via API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "moonshotai/kimi-k3". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.
Is Kimi K3 OpenAI-compatible on UberLLM?
Yes. Every model on UberLLM — including Kimi K3 — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.