Mintplex-Labs/anything-llm · critical · Error

AWS_BEDROCK_LLM_REGION is required for AWS Bedrock.

Error message

AWS_BEDROCK_LLM_REGION is required for AWS Bedrock.

What it means

Thrown by the AWSBedrockLLM constructor when process.env.AWS_BEDROCK_LLM_REGION is falsy, immediately after the API-key guard. Bedrock endpoints are regional (e.g. us-east-1), so the region is required both for the endpoint URL and for the underlying client. Without it the provider cannot compute a baseURL.

Source

Thrown at server/utils/AiProviders/bedrock/index.js:33

  noSystemPromptModels = [
    "amazon.titan-text-express-v1",
    "amazon.titan-text-lite-v1",
    "cohere.command-text-v14",
    "cohere.command-light-text-v14",
    "us.deepseek.r1-v1:0",
  ];

  noTemperatureModels = [
    "anthropic.claude-opus-4-7",
    "anthropic.claude-opus-4-8",
    "anthropic.claude-sonnet-5",
  ];

  constructor(embedder = null, modelPreference = null) {
    if (!process.env.AWS_BEDROCK_LLM_API_KEY)
      throw new Error("AWS_BEDROCK_LLM_API_KEY is required for AWS Bedrock.");
    if (!process.env.AWS_BEDROCK_LLM_REGION)
      throw new Error("AWS_BEDROCK_LLM_REGION is required for AWS Bedrock.");

    this.className = "AWSBedrockLLM";
    this.model =
      modelPreference || process.env.AWS_BEDROCK_LLM_MODEL_PREFERENCE;
    this.region = process.env.AWS_BEDROCK_LLM_REGION;

    const contextWindowLimit = this.promptWindowLimit();
    this.limits = {
      history: Math.floor(contextWindowLimit * 0.15),
      system: Math.floor(contextWindowLimit * 0.15),
      user: Math.floor(contextWindowLimit * 0.7),
    };

    this.openai = new OpenAIApi({
      apiKey: process.env.AWS_BEDROCK_LLM_API_KEY,
      baseURL: `https://bedrock-mantle.${this.region}.api.aws/v1`,
    });

View on GitHub (pinned to 526360e320)

Solutions

1. Set `AWS_BEDROCK_LLM_REGION=<region>` (e.g. us-east-1, eu-west-1) in .env to match where your Bedrock models are available.
2. Confirm the region actually hosts the model in AWS_BEDROCK_LLM_MODEL_PREFERENCE.
3. Re-save Bedrock credentials in the UI to persist the region.
4. Restart the server after editing .env.

Example fix

// before
// .env
AWS_BEDROCK_LLM_API_KEY=<key>
// no region

// after
AWS_BEDROCK_LLM_API_KEY=<key>
AWS_BEDROCK_LLM_REGION=us-east-1

const region = process.env.AWS_BEDROCK_LLM_REGION;
const VALID_REGIONS = /^(us|eu|ap|ca|sa|af|me)-(central|east|west|north|south|southeast|southwest|northeast)-\d+/;
if (!region || !VALID_REGIONS.test(region)) {
  throw new Error(
    "AWS_BEDROCK_LLM_REGION is missing or malformed (e.g. us-east-1)."
  );
}

/** @param {unknown} r @returns {boolean} */
function isAwsRegion(r) {
  return typeof r === "string" && /^[a-z]{2}-[a-z]+-\d+$/.test(r);
}

try {
  const llm = new AWSBedrockLLM(embedder, modelPref);
} catch (e) {
  if (/AWS_BEDROCK_LLM_REGION is required/.test(e.message)) {
    return { ok: false, reason: "missing-region" };
  }
  throw e;
}

When it happens

Trigger: Constructing AWSBedrockLLM with AWS_BEDROCK_LLM_API_KEY set but AWS_BEDROCK_LLM_REGION missing. Fires at construction, before any chat call.

Common situations: Key pasted but region omitted; region stored under AWS_REGION (the SDK default) instead of the provider-specific AWS_BEDROCK_LLM_REGION; copy-paste missing the region line; wrong region for the deployed model.

Related errors

• AWS_BEDROCK_LLM_API_KEY is required for AWS Bedrock.
• No Anthropic API key was set.
• No ApiPie LLM API key was set.
• No Azure API endpoint was set.
• No Azure API key was set.

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/bf3b587f9da76e66. Report an issue: GitHub.