Amazon Bedrock의 GPT-5.6 리전 간 추론

from aws_bedrock_token_generator import provide_token
from openai import OpenAI

region = "us-east-1"
# Point the OpenAI SDK at Amazon Bedrock's OpenAI-compatible endpoint for your Region.
provide_token() generates a short-term Amazon Bedrock API key from your current AWS credentials (valid up to 12 hours), so no static key needs to be stored.
client = OpenAI(
    base_url= f"https://bedrock-runtime.{region}.amazonaws.com/openai/v1",
    api_key=provide_token(region=region),
)
# Use the global inference profile ID for GPT-5.6 Terra.
model_id = "global.openai.gpt-5.6-terra"
response = client.responses.create(
    model=model_id,
    input="Summarize the difference between horizontal and vertical scaling in two sentences.",
    max_output_tokens=512,
)
print(response.output_text)

response = client.chat.completions.create(
    # For US Geo CRIS, use "us.openai.gpt-5.6-terra".
    # Other variants: gpt-5.6-sol, gpt-5.6-luna
    model="global.openai.gpt-5.6-terra",
    messages=[
        {"role": "user", "content": "In one sentence, what is cross-Region inference in Amazon Bedrock?",}
    ],
    max_completion_tokens=2000,
    reasoning_effort="low",
)
print(response.choices[0].message.content)

import boto3
client = boto3.client("bedrock-runtime", region_name="us-east-1")
model_id = "global.openai.gpt-5.6-terra"
response = client.converse(
    modelId=model_id,
    messages=[{"role": "user", "content": [{"text": "List three common uses for a message queue."}]}],
    inferenceConfig={"maxTokens": 512},
)
print(response["output"]["message"]["content"][0]["text"])

stream_response = client.converse_stream(
    modelId=model_id,
    messages=[{"role": "user", "content": [{"text": "List three common uses for a message queue."}]}],
    inferenceConfig={"maxTokens": 512},
)
for event in stream_response["stream"]:
    if "contentBlockDelta" in event:
        print(event["contentBlockDelta"]["delta"]["text"], end="")

completion = client.chat.completions.create(
    model=model_id,
    messages=[
        {
            "role": "system",
            "content": [
                {
                    "type": "text",
                    "text": support_policy_manual,
                    "prompt_cache_breakpoint": {"mode": "explicit"},
                }
            ],
        },
        {"role": "user", "content": "A customer wants a refund for a damaged laptop. What must I verify first?"},
    ],
    max_completion_tokens=300,
    prompt_cache_key="support-policy-v1",
)

# To confirm that caching is working, check the usage object of each response.
details = completion.usage.prompt_tokens_details
print("Cached tokens:", details.cached_tokens)
print("Written tokens:", details.cache_write_tokens)