Add support for ServiceTier

[sebsto]

Add support for service tier

Amazon Bedrock offers three service tiers for model inference: Priority, Standard, and Flex. The Priority tier delivers the fastest response times for a price premium over standard on-demand pricing. It is best suited for mission-critical applications like customer-facing chatbots and real-time language translation services. The Standard tier provides consistent performance for everyday AI tasks, ideal for content generation, text analysis, and routine document processing. For workloads that can handle longer processing times, the Flex tier offers cost-effective processing for a pricing discount, perfect for model evaluations, content summarization, agentic workflows.

New API

Converse

let bedrock = try await BedrockService(
    region: .uswest2,
)

var builder = try ConverseRequestBuilder(with: .openai_gpt_oss_20b)
    .withPrompt("Who are you?")
    .withServiceTier(.priority)

var reply = try await bedrock.converse(with: builder)

InvokeModel (text)

let bedrock = try await BedrockService(
    region: .uswest2,
)

let textCompletion = try await bedrock.completeText(
    "Who are you?",
    with: .openai_gpt_oss_20b,
    serviceTier: .default
)

Doc:
https://docs.aws.amazon.com/bedrock/latest/userguide/service-tiers-inference.html

Launch:
https://aws.amazon.com/blogs/aws/new-amazon-bedrock-service-tiers-help-you-match-ai-workload-performance-with-cost/

[sebsto]

Changes

• Updated ConverseRequest and InvokeModelRequest to include serviceTier parameter
• Enhanced ConverseRequestBuilder with service tier configuration
• Modified text generation methods across all model providers (Nova, Titan, Anthropic, DeepSeek, Llama, OpenAI) to support service tier (according to each model support status)
• Updated Parameters class with service tier handling

Dependencies

• Upgraded aws-sdk-swift from 1.5.51 to 1.6.3
• Upgraded smithy-swift from 0.158.0 to 0.173.0
• Upgraded swift-argument-parser from 1.6.1 to 1.6.2
• Upgraded aws-crt-swift from 0.53.0 to 0.54.2

Examples

• Added service tier usage example in OpenAI converse example
• Updated test cases to reflect new service tier parameter