Amazon Bedrock で一般提供になった Moonshot AI の Kimi K3 を試してみた

aws bedrock list-foundation-models \
  --by-provider "Moonshot AI" \
  --region us-east-1 \
  --query "modelSummaries[?modelId=='moonshotai.kimi-k3']"

# 出力例
[
    {
        "modelArn": "arn:aws:bedrock:us-east-1::foundation-model/moonshotai.kimi-k3",
        "modelId": "moonshotai.kimi-k3",
        "modelName": "Kimi K3",
        "providerName": "Moonshot AI",
        "inputModalities": [
            "TEXT",
            "IMAGE"
        ],
        "outputModalities": [
            "TEXT"
        ],
        "responseStreamingSupported": true,
        "customizationsSupported": [],
        "inferenceTypesSupported": [
            "INFERENCE_PROFILE"
        ],
        "modelLifecycle": {
            "status": "ACTIVE",
            "startOfLifeTime": "2026-08-27T16:00:00+00:00"
        }
    }
]

aws bedrock list-inference-profiles \
  --region us-east-1 \
  --query "inferenceProfileSummaries[?contains(inferenceProfileId,'kimi-k3')].[inferenceProfileId,description]"

# 出力例
[
    [
        "global.moonshotai.kimi-k3",
        "Routes requests to Kimi K3 globally across all supported AWS Regions."
    ],
    [
        "us.moonshotai.kimi-k3",
        "Routes requests to Kimi K3 in us-east-1, us-east-2, us-west-2."
    ]
]

aws bedrock-runtime converse \
  --region us-east-1 \
  --model-id us.moonshotai.kimi-k3 \
  --messages '[{"role":"user","content":[{"text":"Say ok"}]}]' \
  --inference-config '{"maxTokens":512}'

# 出力例
{
    "output": {
        "message": {
            "role": "assistant",
            "content": [
                {
                    "reasoningContent": {
                        "reasoningText": {
                            "text": "The user just said \"Say ok\". This is a very simple request. They want me to say \"ok\". There's nothing harmful about this, nothing complex. It's just a simple instruction.\n\nThe format should be minimal - just \"ok\" or \"OK\" would be appropriate. No need for lengthy explanation or anything else. The user asked me to say something specific, and I should just do it."
                        }
                    }
                },
                {
                    "text": "Ok"
                }
            ]
        }
    },
    "stopReason": "end_turn",
    "usage": {
        "inputTokens": 87,
        "outputTokens": 97,
        "totalTokens": 184,
        "cacheReadInputTokens": 0,
        "cacheWriteInputTokens": 0
    },
    "metrics": {
        "latencyMs": 873
    }
}

# 出力例
An error occurred (ValidationException) when calling the Converse operation: Invocation of model ID moonshotai.kimi-k3 with on-demand throughput isn’t supported. Retry your request with the ID or ARN of an inference profile that contains this model.

# 出力例（reasoning_content は途中を省略）
{"choices":[{"finish_reason":"stop","index":0,"message":{"annotations":[],"content":"Ok","role":"assistant","refusal":null,"reasoning_content":"The user has just said \"Say ok\". ..."}}],"created":1789950731,"id":"chatcmpl-omohbqkp5p4qpfcw3rt4vcf6kr3pekhyyapb6weddehtodajjnaa","model":"us.moonshotai.kimi-k3","object":"chat.completion","service_tier":"default","usage":{"completion_tokens":141,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":125,"rejected_prediction_tokens":0},"prompt_tokens":87,"prompt_tokens_details":{"audio_tokens":0,"cache_write_tokens":0,"cached_tokens":0},"total_tokens":228},"system_fingerprint":null}

{"model":"us.moonshotai.kimi-k3","input":"Say ok","store":false}

curl --silent --show-error \
  --aws-sigv4 'aws:amz:us-east-1:bedrock' \
  --user "$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY" \
  -H "x-amz-security-token: $AWS_SESSION_TOKEN" \
  -H 'Content-Type: application/json' \
  --data-binary @$HOME/kimi-k3-bedrock/responses-body.json \
  https://bedrock-runtime.us-east-1.amazonaws.com/openai/v1/responses

# 出力例（usage の抜粋）
{
  "input_tokens": 87,
  "input_tokens_details": {
    "cache_write_tokens": 0,
    "cached_tokens": 0
  },
  "output_tokens": 120,
  "output_tokens_details": {
    "reasoning_tokens": 104
  },
  "total_tokens": 207
}

import os

import httpx
from botocore.auth import SigV4Auth
from botocore.awsrequest import AWSRequest
from botocore.credentials import Credentials
from openai import OpenAI

REGION = "us-east-1"
SIGNING_SERVICE = "bedrock"

credentials = Credentials(
    os.environ["AWS_ACCESS_KEY_ID"],
    os.environ["AWS_SECRET_ACCESS_KEY"],
    os.environ.get("AWS_SESSION_TOKEN"),
)


class SigV4Signer(httpx.Auth):
    """OpenAI SDK が送る HTTP リクエストに SigV4 署名を付ける"""

    requires_request_body = True

    def auth_flow(self, request):
        aws_request = AWSRequest(
            method=request.method,
            url=str(request.url),
            data=request.content,
            headers={"content-type": request.headers.get("content-type", "application/json")},
        )
        SigV4Auth(credentials, SIGNING_SERVICE, REGION).add_auth(aws_request)
        for key, value in aws_request.headers.items():
            request.headers[key] = value
        yield request


client = OpenAI(
    api_key="unused-sigv4",
    base_url=f"https://bedrock-runtime.{REGION}.amazonaws.com/openai/v1",
    http_client=httpx.Client(auth=SigV4Signer(), timeout=300.0),
)

import json

from sigv4_openai import client

MODEL_ID = "us.moonshotai.kimi-k3"

response = client.chat.completions.create(
    model=MODEL_ID,
    messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}],
)
print("=== content ===")
print(response.choices[0].message.content)
print("=== usage ===")
print(json.dumps(response.usage.model_dump(), indent=2))

cd ~/kimi-k3-bedrock
uv run --python 3.12 --with openai --with botocore --with httpx python chat_completions.py

# 出力例（抜粋）
=== content ===
# Amazon Bedrock Overview

Amazon Bedrock is a fully managed AWS service for building generative AI applications. It provides access to foundation models (FMs) from multiple providers through a single, unified API—without requiring you to manage any infrastructure.

## Key Features

### 1. Broad Model Selection
...

=== usage ===
{
  "completion_tokens": 2240,
  "prompt_tokens": 95,
  "total_tokens": 2335,
  "completion_tokens_details": {
    "accepted_prediction_tokens": 0,
    "audio_tokens": 0,
    "reasoning_tokens": 1577,
    "rejected_prediction_tokens": 0,
    "text_tokens": null
  },
  ...
}

import json
import time

from sigv4_openai import client

MODEL_ID = "us.moonshotai.kimi-k3"

# キャッシュ対象にする 1,024 トークン以上の固定プロンプト
SYSTEM_PROMPT = "You are a support agent for the fictional service 'Kumo Notes'.\n" + "\n".join(
    f"Rule {i}: When a customer asks about topic {i}, answer politely in one sentence and cite rule {i}."
    for i in range(1, 121)
)


def ask(question):
    start = time.time()
    resp = client.responses.create(
        model=MODEL_ID,
        store=False,
        extra_body={"prompt_cache_options": {"mode": "explicit"}},
        input=[
            {
                "type": "message",
                "role": "system",
                "content": [
                    {
                        "type": "input_text",
                        "text": SYSTEM_PROMPT,
                        "prompt_cache_breakpoint": {"mode": "explicit"},
                    }
                ],
            },
            {
                "type": "message",
                "role": "user",
                "content": [{"type": "input_text", "text": question}],
            },
        ],
    )
    print(f"--- {question} ({time.time() - start:.2f}s)")
    print(resp.output_text)
    print(json.dumps(resp.usage.model_dump(), indent=2))


ask("Tell me about topic 7.")
ask("Tell me about topic 42.")

cd ~/kimi-k3-bedrock
uv run --python 3.12 --with openai --with botocore --with httpx python prompt_caching.py

# 出力例
--- Tell me about topic 7. (2.53s)
Thank you for asking about topic 7 — Kumo Notes is happy to help, and we're glad to assist you with any related questions, as per Rule 7.
{
  "input_tokens": 2997,
  "input_tokens_details": {
    "cache_write_tokens": 2972,
    "cached_tokens": 0
  },
  "output_tokens": 212,
  "output_tokens_details": {
    "reasoning_tokens": 163
  },
  "total_tokens": 3209
}
--- Tell me about topic 42. (3.70s)
Thank you for asking about topic 42 — I'm happy to help with any specific questions you have about it, as provided under rule 42.
{
  "input_tokens": 2997,
  "input_tokens_details": {
    "cache_write_tokens": 0,
    "cached_tokens": 2972
  },
  "output_tokens": 507,
  "output_tokens_details": {
    "reasoning_tokens": 463
  },
  "total_tokens": 3504
}

curl --silent --show-error \
  --aws-sigv4 'aws:amz:us-east-1:bedrock-mantle' \
  --user "$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY" \
  -H "x-amz-security-token: $AWS_SESSION_TOKEN" \
  -H 'Content-Type: application/json' \
  --data-binary '{"model":"moonshotai.kimi-k3","input":"Say ok","store":false}' \
  https://bedrock-mantle.us-east-1.api.aws/v1/responses

# 出力例
{"error":{"code":"not_found_error","message":"The model 'moonshotai.kimi-k3' does not exist","param":null,"type":"invalid_request_error"}}