Kimi 3.1P
Kimi
Great for coding and software development.Less suited to cybersecurity work.
The same balance for chat and API.
Pay-as-you-go prices.
Prices in USD per 1 million tokens. Cache amounts are displayed rounded to two decimals.
- Input / 1M
- $0.43
- Output / 1M
- $2.15
- Cache / 1M
- $0.05
This page refreshes prices from the catalog. Your final charge depends on tokens actually used.
Compare all models- Context window
- 1,048,576
- Maximum output
- 131,072
- Rate limits
- No fixed RPM or TPM quota is guaranteed. Capacity is shared and requests may receive HTTP 429. Reduce concurrency and retry with backoff.
Standard model specifications, checked on 2 November 2026. Fallback versions can have different limits. Unknown values are not inferred from the base model.
Ready for your API client.
Use this ID in your OpenAI-compatible client. The example is already set to Kimi 3.1P Uncensured AI.
kimi-k3.1-pro-uncensoredfrom openai import OpenAI
import os
client = OpenAI(
base_url="https://uncensuredai.com/v1",
api_key=os.environ["UNCENSURED_API_KEY"]
)
response = client.chat.completions.create(
model="kimi-k3.1-pro-uncensored",
messages=[{
"role": "user",
"content": "Let’s build this idea."
}],
max_tokens=512
)
print(response.choices[0].message.content)Set UNCENSURED_API_KEY to a key from your console.
In the apps you choose.
Start with a request that represents the work you want to do. For coding, follow the OpenCode guide; for phone chat, choose OpenCat on iPhone or Chatbox on Android. Compare other catalog models using the same API key.