Kimi K3
Kimi K3 is Moonshot's flagship generation and a real step up from the K2 line rather than a point release: a 1M-token context window against 262K on K2.5 and K2.6, and 57 on the Artificial Analysis Intelligence Index, the highest of any model we carry. It is priced to match that, at roughly four times our next-best Kimi, so it sits in flagship territory rather than the value lane the K2 models occupy. Reach for it on long-document reasoning, agentic work and hard analysis where the K2 models run out of room, and stay on K2.6 for high-volume traffic where the cost per task matters more than the last few points of quality.
Pricing
Input
$3.00 / 1M
Output
$15.00 / 1M
Pay only for what you use. No subscriptions, no minimums.
Specs
- Context
- 1M
- Max output
- 400K
- Latency
- Medium
- Category
- Text
- Arabic
- Partial
Quick start
Use any OpenAI-compatible client. Just change base_url and your key.
from openai import OpenAI
client = OpenAI(
api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
base_url="https://api.thalam.ai/v1",
)
response = client.chat.completions.create(
model="moonshotai/kimi-k3",
messages=[
{"role": "user", "content": "Hello from Thalam!"}
],
)
print(response.choices[0].message.content)Similar models
GPT-5.6 Sol
The top tier of OpenAI's GPT-5.6 generation. Frontier reasoning, coding, and agentic work with a 1M-token context and image input.
GPT-5.6 Terra
The balanced tier of OpenAI's GPT-5.6 generation. Same 1M-token context and image input, tuned for everyday production work.