mastra-ai/mastra · error

Expected format ${gatewayPrefix}/model, but got ${routerId}

Error message

Expected format ${gatewayPrefix}/model, but got ${routerId}

What it means

Gateways without a separate provider segment (e.g. "amazon-bedrock") use a 2-part router id "gateway/model". When the id has exactly 2 parts and the first matches the gatewayPrefix, the second part (model id) must be non-empty; otherwise the function throws because it cannot resolve an empty model.

Source

Thrown at packages/core/src/llm/model/gateway-resolver.ts:34

  if (gatewayPrefix === 'azure-openai') {
    const modelId = idParts.slice(1).join('/');
    if (!modelId) {
      throw new Error(`Expected format azure-openai/deployment-name, but got ${routerId}`);
    }
    return {
      providerId: 'azure-openai',
      modelId, // Deployment name
    };
  }

  // Provider-equals-gateway: a gateway whose provider id is the same as its
  // gateway id (e.g. amazon-bedrock) uses a 2-part router id (gateway/model),
  // because there is no separate provider segment to namespace. Catalog ids
  // for such gateways are always two parts (model ids contain no slashes).
  if (gatewayPrefix && idParts.length === 2 && idParts[0] === gatewayPrefix) {
    const modelId = idParts[1];
    if (!modelId) {
      throw new Error(`Expected format ${gatewayPrefix}/model, but got ${routerId}`);
    }
    return {
      providerId: gatewayPrefix,
      modelId,
    };
  }

  // Standard 3-part format for other prefixed gateways (Netlify, etc.)
  if (gatewayPrefix && idParts.length < 3) {
    throw new Error(
      `Expected atleast 3 id parts ${gatewayPrefix}/provider/model, but only saw ${idParts.length} in ${routerId}`,
    );
  }

  const providerId = idParts.at(gatewayPrefix ? 1 : 0);
  const modelId = idParts.slice(gatewayPrefix ? 2 : 1).join(`/`);

  if (!routerId.includes(`/`) || !providerId || !modelId) {

View on GitHub (pinned to 75dd419e61)

Solutions

1. Supply the model id: "amazon-bedrock/your-model-id".
2. Guard the model value is non-empty before constructing the router id.
3. Strip trailing slashes when composing ids from base path + model.

Example fix

// before
parseModelRouterId(`amazon-bedrock/${modelId}`, "amazon-bedrock"); // modelId === ""
// after
if (!modelId) throw new Error("modelId is required");
parseModelRouterId(`amazon-bedrock/${modelId}`, "amazon-bedrock");

const modelId = 'embed-model-id';
if (!modelId) throw new Error('Model id is required for gateway router id');
const routerId = `amazon-bedrock/${modelId}`;
parseModelRouterId(routerId, 'amazon-bedrock');

const isValidGatewayModelId = (id, prefix) => id.startsWith(`${prefix}/`) && Boolean(id.split('/')[1]);

try {
  const { providerId, modelId } = parseModelRouterId(routerId, 'amazon-bedrock');
} catch (e) {
  if (e instanceof Error && e.message.includes(`${gatewayPrefix}/model`)) {
    console.error(`Empty model segment in router id: "${routerId}"`);
  } else throw e;
}

When it happens

Trigger: parseModelRouterId("amazon-bedrock/", "amazon-bedrock") — gateway-prefixed id whose model segment after the slash is empty.

Common situations: Model variable empty/undefined during string interpolation; trailing slash left from path joining; data migrated with truncated ids.

Related errors

• Expected ${gatewayPrefix}/ in model router ID ${routerId}
• Linear project source id is invalid.
• Expected format azure-openai/deployment-name, but got ${rout
• Expected atleast 3 id parts ${gatewayPrefix}/provider/model,
• Attempted to parse provider/model from ${routerId} but this

AI-assisted analysis of mastra-ai/mastra@75dd419e61 (2026-08-30). Data as JSON: /api/errors/f3d5c844abe4b4e5. Report an issue: GitHub.