kimi-k2.8-for-coding API
Rayu model ID
Credits x3(discount 50%)
Rayu credit charge per 1M tokens
Each bucket is priced on its own and charged from actual usage.
- Input
- 3,000Fresh prompt tokens
- Output
- 5,000Tokens the model generates
- Cache read
- 800Prompt tokens served from cache
- Cache write
- 2,400Prompt tokens written to cache
Worked example
A request with 8,000 input and 2,000 output tokens, before cache discounts.
8,000 input × 3,000 / 1M24 cr
2,000 output × 5,000 / 1M10 cr
Total34 credits
Prompt tokens served from cache are billed at the cache-read rate instead. How tokens are charged
Capabilities
Context window1,000,000 tokens
SupportsReasoningVisionTool calling
Use it in Rayu Code
Signed in on a paid plan, select it in the CLI or VS Code with:
›
/model kimi-for-codingOr run /model and type to filter the picker.
Call kimi-k2.8-for-coding with the Rayu API
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["RAYU_API_KEY"],
base_url="https://gateway.rayucode.com/v1",
)
response = client.chat.completions.create(
model="kimi-for-coding",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Key:
RAYU_API_KEY · Model: · Base: https://gateway.rayucode.com/v1Create an API key
