プロンプトキャッシュ

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.shannon-ai.com/v1")

handbook = open("handbook.txt").read()  # a long text that stays the same


def ask(question):
    response = client.chat.completions.create(
        model="Kimi-K3-3BIT-REAP",
        messages=[
            {"role": "system", "content": handbook},
            {"role": "user", "content": question},
        ],
    )
    usage = response.usage
    print(usage.prompt_tokens, usage.prompt_tokens_details.cached_tokens)


ask("What is the refund policy?")
ask("Who approves travel?")  # same start: read the second number

import { readFileSync } from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://api.shannon-ai.com/v1" });

const handbook = readFileSync("handbook.txt", "utf8"); // a long text that stays the same

async function ask(question) {
  const response = await client.chat.completions.create({
    model: "Kimi-K3-3BIT-REAP",
    messages: [
      { role: "system", content: handbook },
      { role: "user", content: question },
    ],
  });
  const usage = response.usage;
  console.log(usage.prompt_tokens, usage.prompt_tokens_details.cached_tokens);
}

await ask("What is the refund policy?");
await ask("Who approves travel?"); // same start: read the second number

# handbook.txt is a long text that stays the same. jq builds the JSON body from it
# and prints the usage object of the reply. Run it twice with different questions.
jq -Rs '{
    model: "Kimi-K3-3BIT-REAP",
    messages: [
      {role: "system", content: .},
      {role: "user", content: "What is the refund policy?"}
    ]
  }' handbook.txt \
  | curl -s https://api.shannon-ai.com/v1/chat/completions \
      -H "Authorization: Bearer YOUR_API_KEY" \
      -H "Content-Type: application/json" \
      -d @- \
  | jq .usage

{
  "usage": {
    "prompt_tokens": 20000,
    "completion_tokens": 812,
    "total_tokens": 20812,
    "prompt_tokens_details": {
      "cached_tokens": 18000
    },
    "completion_tokens_details": {
      "reasoning_tokens": 604
    }
  }
}

{
  "usage": {
    "input_tokens": 20000,
    "input_tokens_details": {
      "cached_tokens": 18000
    },
    "output_tokens": 812,
    "output_tokens_details": {
      "reasoning_tokens": 604
    },
    "total_tokens": 20812
  }
}

{
  "usage": {
    "input_tokens": 2000,
    "cache_read_input_tokens": 18000,
    "cache_creation_input_tokens": 0,
    "output_tokens": 812
  }
}