Kimi K2 Thinking
Kimi K2 Thinking is Moonshot's reasoning model. It reasons step by step before it answers. It takes up to 256K tokens of context and writes up to 98.3K per response.
Output price
$1.26
USD / 1M tokens
37% below list price
Add $5, get $5 more on your first top-up.
Same Kimi K2 Thinking. 37% less.
Specs.
- Model ID
- kimi-k2-thinking
- Made by
- Moonshot
- Context window
- 256K tokens
- Max output
- 98.3K tokens
- Endpoint
- /v1/chat/completions
- Billing
- Per token, from one balance
Edge gateways
Requests enter at the gateway nearest your app and go straight to the model, so routing adds very little to each call.
One key, every model
Switch models by changing a string. One prepaid balance covers all of them, billed per token.
Nothing stored
We keep token counts for billing, never your prompts or responses.
Call Kimi K2 Thinking in a minute.
Point any OpenAI-compatible client at our base URL, keep your key in an environment variable, and use the model ID kimi-k2-thinking.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.promptsforless.com/v1",
api_key=os.environ["PFL_API_KEY"],
)
response = client.chat.completions.create(
model="kimi-k2-thinking",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
Cursor guide
OpenCode guide
OpenAI SDK guideMore from Moonshot.
Alibaba
Z.aiQuestions.
How much does Kimi K2 Thinking cost?
$1.26 / 1M tokens output and $0.2961 / 1M tokens input, 37% below Moonshot's list price. You pay per token from a prepaid balance, with no subscription or minimum. We match your first $5 top-up, so you start with $10 of credit.
Is it the real Kimi K2 Thinking?
Yes. Your requests run on Moonshot's Kimi K2 Thinking, not a distilled copy or a substitute. The discount comes from how we buy capacity, not from changing the model.
Which tools can use Kimi K2 Thinking?
Anything that speaks the OpenAI API: set the base URL to our endpoint and use the model ID kimi-k2-thinking. We have setup guides for Cursor, Codex, OpenCode, the OpenAI and Vercel AI SDKs, LangChain and more.
How fast is it?
Requests go through our edge gateways, so the network hop adds very little on top of Kimi K2 Thinking's own generation time. Responses stream back token by token.