Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot's post-trained successor to Kimi K3. It keeps the 1M-token context window and the native understanding of images and video, and adds Moonshot's latest training for long-horizon coding, agentic knowledge work and research over long documents, with reasoning, function calling and structured outputs. Reach for it where K3 fits today: long-context reasoning and multi-step agent work. Stay on K2.6 for high-volume traffic where the cost per task matters more than the last points of quality.
Pricing
Input
$2.00 / 1M
Output
$10.00 / 1M
Pay only for what you use. No subscriptions, no monthly minimum.
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-k3.1-pro",
messages=[
{"role": "user", "content": "Hello from Thalam!"}
],
)
print(response.choices[0].message.content)Similar models
GPT-6 Astra
OpenAI's GPT-6 generation. Frontier reasoning with a 1M-token context, image input, and adjustable reasoning effort.
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.