Skip to content

feat: add service_tier support to BedrockModel #1799

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
BV-Venky wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: add service_tier support to BedrockModel #1799

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions src/strands/models/bedrock.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,6 +93,10 @@ class BedrockConfig(TypedDict, total=False):
model_id: The Bedrock model ID (e.g., "us.anthropic.claude-sonnet-4-20250514-v1:0")
include_tool_result_status: Flag to include status field in tool results.
True includes status, False removes status, "auto" determines based on model_id. Defaults to "auto".
service_tier: Service tier for the request, controlling the trade-off between latency and cost.
Valid values: "default" (standard), "priority" (faster, premium), "flex" (cheaper, slower).
Please check https://docs.aws.amazon.com/bedrock/latest/userguide/service-tiers-inference.html for all
valid tiers.
stop_sequences: List of sequences that will stop generation when encountered
streaming: Flag to enable/disable streaming. Defaults to True.
temperature: Controls randomness in generation (higher = more random)
Expand All @@ -117,6 +121,7 @@ class BedrockConfig(TypedDict, total=False):
max_tokens: int | None
model_id: str
include_tool_result_status: Literal["auto"] | bool | None
service_tier: str | None
stop_sequences: list[str] | None
streaming: bool | None
temperature: float | None
Expand Down Expand Up @@ -243,6 +248,7 @@ def _format_request(
"modelId": self.config["model_id"],
"messages": self._format_bedrock_messages(messages),
"system": system_blocks,
**({"serviceTier": {"type": self.config["service_tier"]}} if self.config.get("service_tier") else {}),
**(
{
"toolConfig": {
Expand Down
14 changes: 14 additions & 0 deletions tests/strands/models/test_bedrock.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -379,6 +379,20 @@ def test_format_request_guardrail_config_without_trace_or_stream_processing_mode
assert tru_request == exp_request


def test_format_request_with_service_tier(model, messages, model_id):
model.update_config(service_tier="flex")
tru_request = model._format_request(messages)
exp_request = {
"inferenceConfig": {},
"modelId": model_id,
"messages": messages,
"serviceTier": {"type": "flex"},
"system": [],
}

assert tru_request == exp_request


def test_format_request_inference_config(model, messages, model_id, inference_config):
model.update_config(**inference_config)
tru_request = model._format_request(messages)
Expand Down