Amazon Bedrock 推出 Moonshot AI 的 Kimi K3

英文标题：Introducing Kimi K3 on Amazon Bedrock

Moonshot AI 的开放权重模型 Kimi K3 现已登陆 Amazon Bedrock，面向编程和知识工作场景提供原生视觉能力与 100 万 token 上下文窗口。Moonshot AI 称，该模型拥有 2.8 万亿参数，并较 Kimi K2 实现约 2.5 倍的扩展效率提升。Kimi K3 是 Amazon Bedrock 首个支持显式 Prompt 缓存的开放权重模型，可在复用上下文时降低延迟和输入成本。开发者可通过 OpenAI 兼容的 Responses 与 Chat Completions API、Bedrock Invoke 和 Converse API，以及 OpenCode、Hermes Agent 等工具调用该模型。

1.3 MB 101.1 KB 124.1 KB 345.0 KB 141.2 KB 346.5 KB 16.8 KB 22.6 KB 17.1 KB 19.7 KB 15.9 KB 198.2 KB

from aws_bedrock_token_generator import provide_token
from openai import OpenAI

region = "us-west-2"
oai_client = OpenAI(
    api_key=provide_token(region=region),
    base_url=f"https://bedrock-runtime.{region}.amazonaws.com/openai/v1",
)

resp = oai_client.responses.create(
    input="What is Byte-Pair Encoding, in AI?",
    model="global.moonshotai.kimi-k3",
)
print(resp.output_text)

resp = oai_client.responses.create(
    model="global.moonshotai.kimi-k3",
    # Enable explicit caching mode:
    extra_body={"prompt_cache_options": {"mode": "explicit"}},
    input=[
        {
            "type": "message",
            "role": "system",
            "content": [
                {
                    "type": "input_text",
                    "text": SYSTEM_PROMPT,
                    # A long, static system prompt is a great target for caching:
                    "prompt_cache_breakpoint": {"mode": "explicit"},
                },
            ]
        },
        {
            "type": "message",
            "role": "user",
            "content": [
                {
                    "type": "input_text",
                    "text": USER_INPUT,
                    # Multiple breakpoints can also be defined, for layered cache:
                    "prompt_cache_breakpoint": {"mode": "explicit"},
                },
            ],
        },
    ],
)
if resp.usage.input_tokens_details.cached_tokens:
    print("Hit cache!")

{
    "$schema": "https://opencode.ai/config.json",
    "model": "amazon-bedrock/global.moonshotai.kimi-k3",
    "provider": {
        "amazon-bedrock": {
            "options": {
                "region": "us-west-2",
                "profile": "PLACEHOLDER-YOUR-AWS-PROFILE-NAME"
            }
        }
    }
}

from aws_bedrock_token_generator import provide_token
from openai import OpenAI

region = "us-west-2"
oai_client = OpenAI(
    api_key=provide_token(region=region),
    base_url=f"https://bedrock-runtime.{region}.amazonaws.com/openai/v1",
)

resp = oai_client.responses.create(
    input="What is Byte-Pair Encoding, in AI?",
    model="global.moonshotai.kimi-k3",
)
print(resp.output_text)

resp = oai_client.responses.create(
    model="global.moonshotai.kimi-k3",
    # Enable explicit caching mode:
    extra_body={"prompt_cache_options": {"mode": "explicit"}},
    input=[
        {
            "type": "message",
            "role": "system",
            "content": [
                {
                    "type": "input_text",
                    "text": SYSTEM_PROMPT,
                    # A long, static system prompt is a great target for caching:
                    "prompt_cache_breakpoint": {"mode": "explicit"},
                },
            ]
        },
        {
            "type": "message",
            "role": "user",
            "content": [
                {
                    "type": "input_text",
                    "text": USER_INPUT,
                    # Multiple breakpoints can also be defined, for layered cache:
                    "prompt_cache_breakpoint": {"mode": "explicit"},
                },
            ],
        },
    ],
)
if resp.usage.input_tokens_details.cached_tokens:
    print("Hit cache!")

{
    "$schema": "https://opencode.ai/config.json",
    "model": "amazon-bedrock/global.moonshotai.kimi-k3",
    "provider": {
        "amazon-bedrock": {
            "options": {
                "region": "us-west-2",
                "profile": "PLACEHOLDER-YOUR-AWS-PROFILE-NAME"
            }
        }
    }
}