Amazon Bedrock
A RocketRide LLM node that connects Amazon Bedrock-hosted foundation models to a pipeline.
What it does
Provides an llm invoke connection backed by Amazon Bedrock. It is used primarily by
agents and other nodes that need an LLM, and can also be wired directly via lanes:
text arriving on the questions lane is answered on the answers lane.
Uses langchain-aws (ChatBedrock) on top of boto3 / botocore. The chat client is
created once per pipeline run with a fixed temperature of 0; the output token cap is
taken from the model's configured output-token limit. Token counts are estimated at
about four characters a token, so no tokenizer package is needed. The estimate feeds
the size warnings and nodes that cut documents to fit the model (such as
summarization and preprocessor_llm); text that packs more tokens into fewer
characters, such as code, may count low.
The node automatically prepends a cross-region inference prefix to the model ID based on
the configured AWS region: eu. for eu* regions, apac. for ap* regions, and us.
otherwise (for example, meta.llama3-3-70b-instruct-v1:0 becomes
us.meta.llama3-3-70b-instruct-v1:0 in us-east-1). Model IDs that are ARNs or already
carry a us. / eu. / apac. prefix are left untouched.
When you save the node configuration, it is validated with a minimal live API call
("Hi") against the selected model, so credential, model, and region problems surface
immediately instead of at pipeline runtime.
Lanes
| Lane in | Lane out | Description |
|---|---|---|
questions | answers | Send a question directly, receive a generated answer |
Profiles
Default: Llama 3.3 70B Instruct (meta_llama3_3-70b).
| Profile | Model ID | Context tokens |
|---|---|---|
| Llama 3.3 70B Instruct (default) | meta.llama3-3-70b-instruct-v1:0 | 128,000 |
| Llama 4 Scout 17B Instruct | meta.llama4-scout-17b-instruct-v1:0 | 3,500,000 |
| Llama 4 Maverick 17B Instruct | meta.llama4-maverick-17b-instruct-v1:0 | 1,000,000 |
| Nova 2 Lite | amazon.nova-2-lite-v1:0 | 1,000,000 |
| Claude Sonnet 4.5 | anthropic.claude-sonnet-4-5-20250929-v1:0 | 200,000 |
| Claude Opus 4.5 | anthropic.claude-opus-4-5-20251101-v1:0 | 200,000 |
View 16 more models
| Profile | Model ID | Context tokens |
|---|---|---|
| Custom | (user-specified) | 256,000 (editable) |
| Claude Haiku 4.5 | anthropic.claude-haiku-4-5-20251001-v1:0 | 200,000 |
| Jamba 1.5 Large | ai21.jamba-1-5-large-v1:0 | 256,000 |
| Jamba 1.5 Mini | ai21.jamba-1-5-mini-v1:0 | 256,000 |
| Titan Text Express | amazon.titan-text-express-v1 | 8,192 |
| Claude Sonnet 3.7 | anthropic.claude-3-7-sonnet-20250219-v1:0 | 200,000 |
| Claude Haiku 3.5 | anthropic.claude-3-5-haiku-20241022-v1:0 | 200,000 |
| Claude Opus 4 | anthropic.claude-opus-4-20250514-v1:0 | 200,000 |
| Command R+ | cohere.command-r-plus-v1:0 | 128,000 |
| Command R | cohere.command-r-v1:0 | 128,000 |
| Llama 3.1 8B Instruct | meta.llama3-1-8b-instruct-v1:0 | 128,000 |
| Llama 3.1 70B Instruct | meta.llama3-1-70b-instruct-v1:0 | 128,000 |
| Llama 3.2 1B Instruct | meta.llama3-2-1b-instruct-v1:0 | 128,000 |
| Llama 3.2 3B Instruct | meta.llama3-2-3b-instruct-v1:0 | 128,000 |
| Llama 3.2 11B Vision Instruct | meta.llama3-2-11b-instruct-v1:0 | 128,000 |
| Llama 3.2 90B Vision Instruct | meta.llama3-2-90b-instruct-v1:0 | 128,000 |
All built-in profiles default to region us-east-1.
Configuration
Choose a built-in profile and the AWS region where that model is available. The profile supplies the model identifier and context limit; most pipelines do not need to edit those values.
Custom models
Select Custom to use a Bedrock model not listed above. Provide its full
provider-prefixed model ID (for example,
anthropic.claude-3-7-sonnet-20250219-v1:0) or an ARN for a custom or
provisioned model, plus the model's total token limit and its output limit (4,096
by default; raise it for models that reason before answering). Bare model names without a
provider prefix produce a save-time warning. See the
Bedrock model IDs reference
for available identifiers.
Prompt caching
Claude models on Bedrock can reuse the start of a prompt they have already read, at
a tenth of the input price. Bedrock does this on its own, but only as best effort;
a cache_control marker makes that start eligible on every call. When a question sets
cachePrefix (the RocketRide Wave agent does on every planning call), the node splits
the prompt into two text blocks: the start that stays the same between calls (role,
instructions, examples, history), marked for caching, and the rest (context,
documents, goals, questions). The model reads the same text either way. Questions
without the flag are sent as one block, as before.
The marker goes only to Claude models that support it: every Claude from 4 on, Claude 3.7 Sonnet and Claude 3.5 Haiku. Bedrock rejects it for the older Claude models, so they, and models from other providers, get the plain prompt. A prefix shorter than the model's minimum (from 512 to 4,096 tokens depending on the model; see the Bedrock prompt caching guide) is simply not cached, at no extra cost. Nova caches repeated prompt starts on its own (best effort) and gets no marker.
Cache reads and writes are metered separately from fresh input tokens.
Authentication
Provide an AWS access key ID and secret access key with permission to invoke the chosen Bedrock model in the configured region. Credentials are passed directly to the Bedrock client and are not persisted by the node.
Save-time validation performs a minimal test invocation and reports provider errors
verbatim. One gotcha: Bedrock returns a ValidationException (HTTP 400) when the
region does not match your account or model availability, while incorrect keys
surface as different error types. If you see a ValidationException during validation,
verify the AWS region first.
Schema
| Field | Type | Description | Default |
|---|---|---|---|
bedrock.profile | string | Model LLM model | "meta_llama3_3-70b" |
model | string | Model Bedrock LLM model name or ARN for custom or provisioned models | |
modelOutputTokens | integer | Output Tokens Most tokens the model may write in one reply (at least 1,024). Leave it empty to keep the node's default. Reasoning models count their thinking against this limit: set it well above the reply you expect, or they can spend it all thinking and return nothing. It cannot exceed Tokens; a larger value is lowered to it. | |
modelTotalTokens | number | Tokens Total Tokens |
Dependencies
langchain-awslangchain-corelangchainpackagingboto3botocore