×
Run Kimi K3.1 Pro on Runpod
Kimi K3.1 Pro, now on Runpod Public Endpoints.
from openai import OpenAI client = OpenAI( base_url="https://api.runpod.ai/v2/ moonshot-kimi/openai/v1", api_key=os.environ["RUNPOD_API_KEY"], ) client.chat.completions.create( model="kimi-k3.1-pro", messages=[...], )
Model details
Kimi K3.1 Pro Highspeed: $4.00 / 1M input tokens, $20.00 / 1M output tokens
Switch between Pro and Highspeed with one string in your request.
Example usage
Kimi K3.1 Pro is available now as a Runpod Public Endpoint. It speaks the OpenAI Chat Completions format, so point your existing client at Runpod and pass model kimi-k3.1-pro. Swap in kimi-k3.1-pro-highspeed to run the faster variant.
Using the OpenAI SDK pointed at Runpod's OpenAI compatible base URL.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.runpod.ai/v2/moonshot-kimi/openai/v1",
api_key=os.environ["RUNPOD_API_KEY"],
)
completion = client.chat.completions.create(
model="kimi-k3.1-pro",
messages=[
{"role": "system", "content": "You are Kimi."},
{"role": "user", "content": "What is Runpod?"},
],
max_tokens=2048,
temperature=1,
reasoning_effort="low",
)
print(completion.choices[0].message.content)Swap model for "kimi-k3.1-pro-highspeed" to run the faster variant.
A direct HTTPS request to the OpenAI compatible endpoint.
curl https://api.runpod.ai/v2/moonshot-kimi/openai/v1/chat/completions \
-H "Authorization: Bearer $RUNPOD_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3.1-pro",
"messages": [
{"role": "system", "content": "You are Kimi."},
{"role": "user", "content": "What is Runpod?"}
]
}'Swap model for "kimi-k3.1-pro-highspeed" to run the faster variant.
Request flow
How a Kimi K3.1 Pro request flows on Runpod
Point your OpenAI client at the Runpod endpoint, Runpod routes the call to Kimi K3.1 Pro, and tokens stream back to your app.
Kimi K3.1 Pro and K3.1 Pro Highspeed
Kimi K3.1 Pro and K3.1 Pro Highspeed run on the same Runpod endpoint, so you choose which one you want per request. K3.1 Pro is built for long-horizon tasks like coding a full project. Highspeed runs 2 to 3 times faster for latency-sensitive work like interactive coding tools and agent loops. Start on K3.1 Pro, then move to Highspeed once latency matters. The switch is one string in your request, so you can test both on your own workload.
Kimi K3.1 Pro
Quality and long-horizon work.
$2.00 / 1M input tokens$10.00 / 1M output tokens
Kimi K3.1 Pro Highspeed
2 to 3 times faster for interactive and agent loops.
$4.00 / 1M input tokens$20.00 / 1M output tokens
Related models
Build what’s next.
Build, train, and scale AI workloads on Runpod with cloud GPUs, Serverless, and Clusters.
