Meta

When using Meta models via AWS Bedrock, llm-exe will make POST requests to https://bedrock-runtime.us-west-2.amazonaws.com/model/{MODEL_ID}/invoke.

Setup

Meta LLama

const llm = useLlm("amazon:meta.chat.v1", {
    model: "meta.llama3-8b-instruct-v1:0", // This is the model id from Bedrock
});

LLama-Specific Options

In addition to the generic options, the following options are available for Meta LLama models on Bedrock.

Option	Type	Default	Description
model	string	—	The Bedrock model id. Must be specified. See AWS Bedrock Docs
temperature	number	undefined	Maps to temperature.
maxTokens	number	2048	Maps to max_gen_len. See AWS Bedrock Docs
topP	number	undefined	Maps to top_p. See AWS Bedrock Docs
awsRegion	string	undefined	AWS Region. Can be set via AWS_REGION environment variable
awsSecretKey	string	undefined	AWS Secret Key. Can be set via AWS_SECRET_ACCESS_KEY environment variable
awsAccessKey	string	undefined	AWS Access Key. Can be set via AWS_ACCESS_KEY_ID environment variable

Model identifiers: model accepts a foundation model id, a cross-region inference profile id, or a full ARN. llm-exe URL-encodes it into the invoke path, so identifiers containing / or : route correctly:

// 1. Foundation model id
useLlm("amazon:meta.chat.v1", { model: "meta.llama3-8b-instruct-v1:0" });

// 2. Cross-region inference profile id
useLlm("amazon:meta.chat.v1", { model: "us.meta.llama3-8b-instruct-v1:0" });

// 3. Full ARN
useLlm("amazon:meta.chat.v1", {
  model: "arn:aws:bedrock:us-east-1:123456789012:inference-profile/us.meta.llama3-8b-instruct-v1:0",
});

Unlike the Anthropic on Bedrock config, no Meta option is gated on the model name, so every identifier form behaves identically here — there is no equivalent of the silent effort drop.