Kimi K2 Thinking API
moonshotai/kimi-k2-thinking
Call Kimi K2 Thinking through UberLLM’s OpenAI-compatible API — from $0.6000/M input and $2.50/M output, routed automatically to the cheapest healthy provider. kimi · 262,144 token context. No inference markup.
Kimi K2 Thinking pricing & providers
| Provider | Input / 1M | Output / 1M |
|---|---|---|
| OpenRouterbest | $0.6000 | $2.50 |
| Surplus Intelligence | $0.6000 | $2.50 |
How to use Kimi K2 Thinking with the OpenAI SDK
Already using OpenAI or OpenRouter? Change one line — the base URL — and call Kimi K2 Thinking 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-k2-thinking",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Kimi K2 Thinking API — FAQ
How much does the Kimi K2 Thinking API cost?
Kimi K2 Thinking costs from $0.6000 per million input tokens and $2.50 per million output tokens through UberLLM, which routes to the cheapest healthy provider. There is no inference markup.
How do I call Kimi K2 Thinking 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-k2-thinking". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.
Is Kimi K2 Thinking OpenAI-compatible on UberLLM?
Yes. Every model on UberLLM — including Kimi K2 Thinking — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.