@aws-sdk/client-bedrock-runtime 3.696.0 → 3.704.0

package/dist-cjs/index.js

@@ -74,6 +74,7 @@ __export(src_exports, {
   ModelStreamErrorException: () => ModelStreamErrorException,
   ModelTimeoutException: () => ModelTimeoutException,
   PayloadPartFilterSensitiveLog: () => PayloadPartFilterSensitiveLog,
+  PerformanceConfigLatency: () => PerformanceConfigLatency,
   PromptVariableValues: () => PromptVariableValues,
   ResourceNotFoundException: () => ResourceNotFoundException,
   ResponseStream: () => ResponseStream,
@@ -555,6 +556,10 @@ var ConversationRole = {
   ASSISTANT: "assistant",
   USER: "user"
 };
+var PerformanceConfigLatency = {
+  OPTIMIZED: "optimized",
+  STANDARD: "standard"
+};
 var PromptVariableValues;
 ((PromptVariableValues3) => {
   PromptVariableValues3.visit = /* @__PURE__ */ __name((value, visitor) => {
@@ -898,6 +903,7 @@ var se_ConverseCommand = /* @__PURE__ */ __name(async (input, context) => {
       guardrailConfig: (_) => (0, import_smithy_client._json)(_),
       inferenceConfig: (_) => se_InferenceConfiguration(_, context),
       messages: (_) => se_Messages(_, context),
+      performanceConfig: (_) => (0, import_smithy_client._json)(_),
       promptVariables: (_) => (0, import_smithy_client._json)(_),
       system: (_) => (0, import_smithy_client._json)(_),
       toolConfig: (_) => se_ToolConfiguration(_, context)
@@ -921,6 +927,7 @@ var se_ConverseStreamCommand = /* @__PURE__ */ __name(async (input, context) =>
       guardrailConfig: (_) => (0, import_smithy_client._json)(_),
       inferenceConfig: (_) => se_InferenceConfiguration(_, context),
       messages: (_) => se_Messages(_, context),
+      performanceConfig: (_) => (0, import_smithy_client._json)(_),
       promptVariables: (_) => (0, import_smithy_client._json)(_),
       system: (_) => (0, import_smithy_client._json)(_),
       toolConfig: (_) => se_ToolConfiguration(_, context)
@@ -936,7 +943,8 @@ var se_InvokeModelCommand = /* @__PURE__ */ __name(async (input, context) => {
     [_a]: input[_a],
     [_xabt]: input[_t],
     [_xabg]: input[_gI],
-    [_xabg_]: input[_gV]
+    [_xabg_]: input[_gV],
+    [_xabpl]: input[_pCL]
   });
   b.bp("/model/{modelId}/invoke");
   b.p("modelId", () => input.modelId, "{modelId}", false);
@@ -954,7 +962,8 @@ var se_InvokeModelWithResponseStreamCommand = /* @__PURE__ */ __name(async (inpu
     [_xaba]: input[_a],
     [_xabt]: input[_t],
     [_xabg]: input[_gI],
-    [_xabg_]: input[_gV]
+    [_xabg_]: input[_gV],
+    [_xabpl]: input[_pCL]
   });
   b.bp("/model/{modelId}/invoke-with-response-stream");
   b.p("modelId", () => input.modelId, "{modelId}", false);
@@ -995,6 +1004,7 @@ var de_ConverseCommand = /* @__PURE__ */ __name(async (output, context) => {
     additionalModelResponseFields: (_) => de_Document(_, context),
     metrics: import_smithy_client._json,
     output: (_) => de_ConverseOutput((0, import_core2.awsExpectUnion)(_), context),
+    performanceConfig: import_smithy_client._json,
     stopReason: import_smithy_client.expectString,
     trace: (_) => de_ConverseTrace(_, context),
     usage: import_smithy_client._json
@@ -1019,7 +1029,8 @@ var de_InvokeModelCommand = /* @__PURE__ */ __name(async (output, context) => {
   }
   const contents = (0, import_smithy_client.map)({
     $metadata: deserializeMetadata(output),
-    [_cT]: [, output.headers[_ct]]
+    [_cT]: [, output.headers[_ct]],
+    [_pCL]: [, output.headers[_xabpl]]
   });
   const data = await (0, import_smithy_client.collectBody)(output.body, context);
   contents.body = data;
@@ -1031,7 +1042,8 @@ var de_InvokeModelWithResponseStreamCommand = /* @__PURE__ */ __name(async (outp
   }
   const contents = (0, import_smithy_client.map)({
     $metadata: deserializeMetadata(output),
-    [_cT]: [, output.headers[_xabct]]
+    [_cT]: [, output.headers[_xabct]],
+    [_pCL]: [, output.headers[_xabpl]]
   });
   const data = output.body;
   contents.body = de_ResponseStream(data, context);
@@ -1599,6 +1611,7 @@ var de_ConverseOutput = /* @__PURE__ */ __name((output, context) => {
 var de_ConverseStreamMetadataEvent = /* @__PURE__ */ __name((output, context) => {
   return (0, import_smithy_client.take)(output, {
     metrics: import_smithy_client._json,
+    performanceConfig: import_smithy_client._json,
     trace: (_) => de_ConverseStreamTrace(_, context),
     usage: import_smithy_client._json
   });
@@ -1774,11 +1787,13 @@ var _cT = "contentType";
 var _ct = "content-type";
 var _gI = "guardrailIdentifier";
 var _gV = "guardrailVersion";
+var _pCL = "performanceConfigLatency";
 var _t = "trace";
 var _xaba = "x-amzn-bedrock-accept";
 var _xabct = "x-amzn-bedrock-content-type";
 var _xabg = "x-amzn-bedrock-guardrailidentifier";
 var _xabg_ = "x-amzn-bedrock-guardrailversion";
+var _xabpl = "x-amzn-bedrock-performanceconfig-latency";
 var _xabt = "x-amzn-bedrock-trace";
 
 // src/commands/ApplyGuardrailCommand.ts
@@ -1921,6 +1936,7 @@ var BedrockRuntime = _BedrockRuntime;
   ToolResultStatus,
   ContentBlock,
   ConversationRole,
+  PerformanceConfigLatency,
   PromptVariableValues,
   SystemContentBlock,
   ToolChoice,

package/dist-es/models/models_0.js

@@ -263,6 +263,10 @@ export const ConversationRole = {
     ASSISTANT: "assistant",
     USER: "user",
 };
+export const PerformanceConfigLatency = {
+    OPTIMIZED: "optimized",
+    STANDARD: "standard",
+};
 export var PromptVariableValues;
 (function (PromptVariableValues) {
     PromptVariableValues.visit = (value, visitor) => {

package/dist-es/protocols/Aws_restJson1.js

@@ -33,6 +33,7 @@ export const se_ConverseCommand = async (input, context) => {
         guardrailConfig: (_) => _json(_),
         inferenceConfig: (_) => se_InferenceConfiguration(_, context),
         messages: (_) => se_Messages(_, context),
+        performanceConfig: (_) => _json(_),
         promptVariables: (_) => _json(_),
         system: (_) => _json(_),
         toolConfig: (_) => se_ToolConfiguration(_, context),
@@ -54,6 +55,7 @@ export const se_ConverseStreamCommand = async (input, context) => {
         guardrailConfig: (_) => _json(_),
         inferenceConfig: (_) => se_InferenceConfiguration(_, context),
         messages: (_) => se_Messages(_, context),
+        performanceConfig: (_) => _json(_),
         promptVariables: (_) => _json(_),
         system: (_) => _json(_),
         toolConfig: (_) => se_ToolConfiguration(_, context),
@@ -69,6 +71,7 @@ export const se_InvokeModelCommand = async (input, context) => {
         [_xabt]: input[_t],
         [_xabg]: input[_gI],
         [_xabg_]: input[_gV],
+        [_xabpl]: input[_pCL],
     });
     b.bp("/model/{modelId}/invoke");
     b.p("modelId", () => input.modelId, "{modelId}", false);
@@ -87,6 +90,7 @@ export const se_InvokeModelWithResponseStreamCommand = async (input, context) =>
         [_xabt]: input[_t],
         [_xabg]: input[_gI],
         [_xabg_]: input[_gV],
+        [_xabpl]: input[_pCL],
     });
     b.bp("/model/{modelId}/invoke-with-response-stream");
     b.p("modelId", () => input.modelId, "{modelId}", false);
@@ -127,6 +131,7 @@ export const de_ConverseCommand = async (output, context) => {
         additionalModelResponseFields: (_) => de_Document(_, context),
         metrics: _json,
         output: (_) => de_ConverseOutput(__expectUnion(_), context),
+        performanceConfig: _json,
         stopReason: __expectString,
         trace: (_) => de_ConverseTrace(_, context),
         usage: _json,
@@ -152,6 +157,7 @@ export const de_InvokeModelCommand = async (output, context) => {
     const contents = map({
         $metadata: deserializeMetadata(output),
         [_cT]: [, output.headers[_ct]],
+        [_pCL]: [, output.headers[_xabpl]],
     });
     const data = await collectBody(output.body, context);
     contents.body = data;
@@ -164,6 +170,7 @@ export const de_InvokeModelWithResponseStreamCommand = async (output, context) =
     const contents = map({
         $metadata: deserializeMetadata(output),
         [_cT]: [, output.headers[_xabct]],
+        [_pCL]: [, output.headers[_xabpl]],
     });
     const data = output.body;
     contents.body = de_ResponseStream(data, context);
@@ -729,6 +736,7 @@ const de_ConverseOutput = (output, context) => {
 const de_ConverseStreamMetadataEvent = (output, context) => {
     return take(output, {
         metrics: _json,
+        performanceConfig: _json,
         trace: (_) => de_ConverseStreamTrace(_, context),
         usage: _json,
     });
@@ -911,9 +919,11 @@ const _cT = "contentType";
 const _ct = "content-type";
 const _gI = "guardrailIdentifier";
 const _gV = "guardrailVersion";
+const _pCL = "performanceConfigLatency";
 const _t = "trace";
 const _xaba = "x-amzn-bedrock-accept";
 const _xabct = "x-amzn-bedrock-content-type";
 const _xabg = "x-amzn-bedrock-guardrailidentifier";
 const _xabg_ = "x-amzn-bedrock-guardrailversion";
+const _xabpl = "x-amzn-bedrock-performanceconfig-latency";
 const _xabt = "x-amzn-bedrock-trace";

package/dist-types/commands/ApplyGuardrailCommand.d.ts

@@ -165,22 +165,27 @@ declare const ApplyGuardrailCommand_base: {
  * @see {@link BedrockRuntimeClientResolvedConfig | config} for BedrockRuntimeClient's `config` shape.
  *
  * @throws {@link AccessDeniedException} (client fault)
- *  <p>The request is denied because of missing access permissions.</p>
+ *  <p>The request is denied because you do not have sufficient permissions to perform the requested action. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-access-denied">AccessDeniedException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link InternalServerException} (server fault)
- *  <p>An internal server error occurred. Retry your request.</p>
+ *  <p>An internal server error occurred. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-internal-failure">InternalFailure</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ResourceNotFoundException} (client fault)
- *  <p>The specified resource ARN was not found. Check the ARN and try your request again.</p>
+ *  <p>The specified resource ARN was not found. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-resource-not-found">ResourceNotFound</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ServiceQuotaExceededException} (client fault)
  *  <p>Your request exceeds the service quota for your account. You can view your quotas at <a href="https://docs.aws.amazon.com/servicequotas/latest/userguide/gs-request-quota.html">Viewing service quotas</a>. You can resubmit your request later.</p>
  *
  * @throws {@link ThrottlingException} (client fault)
- *  <p>Your request was throttled because of service-wide limitations. Resubmit your request later or in a different region. You can also purchase <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-throughput.html">Provisioned Throughput</a> to increase the rate or number of tokens you can process.</p>
+ *  <p>Your request was denied due to exceeding the account quotas for <i>Amazon Bedrock</i>. For
+ *          troubleshooting this error, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-throttling-exception">ThrottlingException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ValidationException} (client fault)
- *  <p>Input validation failed. Check your request parameters and retry the request.</p>
+ *  <p>The input fails to satisfy the constraints specified by <i>Amazon Bedrock</i>. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-validation-error">ValidationError</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link BedrockRuntimeServiceException}
  * <p>Base exception class for all service exceptions from BedrockRuntime service.</p>

package/dist-types/commands/ConverseCommand.d.ts

@@ -42,6 +42,15 @@ declare const ConverseCommand_base: {
  *          <p>For example code, see <i>Converse API examples</i> in the <i>Amazon Bedrock User Guide</i>.
  *       </p>
  *          <p>This operation requires permission for the <code>bedrock:InvokeModel</code> action. </p>
+ *          <important>
+ *             <p>To deny all inference access to resources that you specify in the modelId field, you
+ *          need to deny access to the <code>bedrock:InvokeModel</code> and
+ *          <code>bedrock:InvokeModelWithResponseStream</code> actions. Doing this also denies
+ *          access to the resource through the base inference actions (<a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html">InvokeModel</a> and <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html">InvokeModelWithResponseStream</a>). For more information see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/security_iam_id-based-policy-examples.html#security_iam_id-based-policy-examples-deny-inference">Deny access for inference on specific models</a>.
+ *       </p>
+ *          </important>
+ *          <p>For troubleshooting some of the common errors you might encounter when using the <code>Converse</code> API,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html">Troubleshooting Amazon Bedrock API Error Codes</a> in the Amazon Bedrock User Guide</p>
  * @example
  * Use a bare-bones client and the command you need to make an API call.
  * ```javascript
@@ -164,6 +173,9 @@ declare const ConverseCommand_base: {
  *   additionalModelResponseFieldPaths: [ // AdditionalModelResponseFieldPaths
  *     "STRING_VALUE",
  *   ],
+ *   performanceConfig: { // PerformanceConfiguration
+ *     latency: "standard" || "optimized",
+ *   },
  * };
  * const command = new ConverseCommand(input);
  * const response = await client.send(command);
@@ -410,6 +422,9 @@ declare const ConverseCommand_base: {
  * //       },
  * //     },
  * //   },
+ * //   performanceConfig: { // PerformanceConfiguration
+ * //     latency: "standard" || "optimized",
+ * //   },
  * // };
  *
  * ```
@@ -421,34 +436,40 @@ declare const ConverseCommand_base: {
  * @see {@link BedrockRuntimeClientResolvedConfig | config} for BedrockRuntimeClient's `config` shape.
  *
  * @throws {@link AccessDeniedException} (client fault)
- *  <p>The request is denied because of missing access permissions.</p>
+ *  <p>The request is denied because you do not have sufficient permissions to perform the requested action. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-access-denied">AccessDeniedException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link InternalServerException} (server fault)
- *  <p>An internal server error occurred. Retry your request.</p>
+ *  <p>An internal server error occurred. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-internal-failure">InternalFailure</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ModelErrorException} (client fault)
  *  <p>The request failed due to an error while processing the model.</p>
  *
  * @throws {@link ModelNotReadyException} (client fault)
  *  <p>The model specified in the request is not ready to serve inference requests. The AWS SDK
- *            will automatically retry the operation up to 5 times. For information about configuring
- *            automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
- *            reference guide.</p>
+ *          will automatically retry the operation up to 5 times. For information about configuring
+ *          automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
+ *       reference guide.</p>
  *
  * @throws {@link ModelTimeoutException} (client fault)
  *  <p>The request took too long to process. Processing time exceeded the model timeout length.</p>
  *
  * @throws {@link ResourceNotFoundException} (client fault)
- *  <p>The specified resource ARN was not found. Check the ARN and try your request again.</p>
+ *  <p>The specified resource ARN was not found. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-resource-not-found">ResourceNotFound</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ServiceUnavailableException} (server fault)
- *  <p>The service isn't currently available. Try again later.</p>
+ *  <p>The service isn't currently available. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-service-unavailable">ServiceUnavailable</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ThrottlingException} (client fault)
- *  <p>Your request was throttled because of service-wide limitations. Resubmit your request later or in a different region. You can also purchase <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-throughput.html">Provisioned Throughput</a> to increase the rate or number of tokens you can process.</p>
+ *  <p>Your request was denied due to exceeding the account quotas for <i>Amazon Bedrock</i>. For
+ *          troubleshooting this error, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-throttling-exception">ThrottlingException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ValidationException} (client fault)
- *  <p>Input validation failed. Check your request parameters and retry the request.</p>
+ *  <p>The input fails to satisfy the constraints specified by <i>Amazon Bedrock</i>. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-validation-error">ValidationError</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link BedrockRuntimeServiceException}
  * <p>Base exception class for all service exceptions from BedrockRuntime service.</p>

package/dist-types/commands/ConverseStreamCommand.d.ts

@@ -48,6 +48,15 @@ declare const ConverseStreamCommand_base: {
  *          <p>For example code, see <i>Conversation streaming example</i> in the <i>Amazon Bedrock User Guide</i>.
  *       </p>
  *          <p>This operation requires permission for the <code>bedrock:InvokeModelWithResponseStream</code> action.</p>
+ *          <important>
+ *             <p>To deny all inference access to resources that you specify in the modelId field, you
+ *          need to deny access to the <code>bedrock:InvokeModel</code> and
+ *          <code>bedrock:InvokeModelWithResponseStream</code> actions. Doing this also denies
+ *          access to the resource through the base inference actions (<a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html">InvokeModel</a> and <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html">InvokeModelWithResponseStream</a>). For more information see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/security_iam_id-based-policy-examples.html#security_iam_id-based-policy-examples-deny-inference">Deny access for inference on specific models</a>.
+ *       </p>
+ *          </important>
+ *          <p>For troubleshooting some of the common errors you might encounter when using the <code>ConverseStream</code> API,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html">Troubleshooting Amazon Bedrock API Error Codes</a> in the Amazon Bedrock User Guide</p>
  * @example
  * Use a bare-bones client and the command you need to make an API call.
  * ```javascript
@@ -171,6 +180,9 @@ declare const ConverseStreamCommand_base: {
  *   additionalModelResponseFieldPaths: [ // AdditionalModelResponseFieldPaths
  *     "STRING_VALUE",
  *   ],
+ *   performanceConfig: { // PerformanceConfiguration
+ *     latency: "standard" || "optimized",
+ *   },
  * };
  * const command = new ConverseStreamCommand(input);
  * const response = await client.send(command);
@@ -386,6 +398,9 @@ declare const ConverseStreamCommand_base: {
  * //           },
  * //         },
  * //       },
+ * //       performanceConfig: { // PerformanceConfiguration
+ * //         latency: "standard" || "optimized",
+ * //       },
  * //     },
  * //     internalServerException: { // InternalServerException
  * //       message: "STRING_VALUE",
@@ -416,34 +431,40 @@ declare const ConverseStreamCommand_base: {
  * @see {@link BedrockRuntimeClientResolvedConfig | config} for BedrockRuntimeClient's `config` shape.
  *
  * @throws {@link AccessDeniedException} (client fault)
- *  <p>The request is denied because of missing access permissions.</p>
+ *  <p>The request is denied because you do not have sufficient permissions to perform the requested action. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-access-denied">AccessDeniedException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link InternalServerException} (server fault)
- *  <p>An internal server error occurred. Retry your request.</p>
+ *  <p>An internal server error occurred. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-internal-failure">InternalFailure</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ModelErrorException} (client fault)
  *  <p>The request failed due to an error while processing the model.</p>
  *
  * @throws {@link ModelNotReadyException} (client fault)
  *  <p>The model specified in the request is not ready to serve inference requests. The AWS SDK
- *            will automatically retry the operation up to 5 times. For information about configuring
- *            automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
- *            reference guide.</p>
+ *          will automatically retry the operation up to 5 times. For information about configuring
+ *          automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
+ *       reference guide.</p>
  *
  * @throws {@link ModelTimeoutException} (client fault)
  *  <p>The request took too long to process. Processing time exceeded the model timeout length.</p>
  *
  * @throws {@link ResourceNotFoundException} (client fault)
- *  <p>The specified resource ARN was not found. Check the ARN and try your request again.</p>
+ *  <p>The specified resource ARN was not found. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-resource-not-found">ResourceNotFound</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ServiceUnavailableException} (server fault)
- *  <p>The service isn't currently available. Try again later.</p>
+ *  <p>The service isn't currently available. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-service-unavailable">ServiceUnavailable</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ThrottlingException} (client fault)
- *  <p>Your request was throttled because of service-wide limitations. Resubmit your request later or in a different region. You can also purchase <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-throughput.html">Provisioned Throughput</a> to increase the rate or number of tokens you can process.</p>
+ *  <p>Your request was denied due to exceeding the account quotas for <i>Amazon Bedrock</i>. For
+ *          troubleshooting this error, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-throttling-exception">ThrottlingException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ValidationException} (client fault)
- *  <p>Input validation failed. Check your request parameters and retry the request.</p>
+ *  <p>The input fails to satisfy the constraints specified by <i>Amazon Bedrock</i>. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-validation-error">ValidationError</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link BedrockRuntimeServiceException}
  * <p>Base exception class for all service exceptions from BedrockRuntime service.</p>

package/dist-types/commands/InvokeModelCommand.d.ts

@@ -45,6 +45,15 @@ declare const InvokeModelCommand_base: {
  *          <p>For example code, see <i>Invoke model code examples</i> in the <i>Amazon Bedrock User Guide</i>.
  *       </p>
  *          <p>This operation requires permission for the <code>bedrock:InvokeModel</code> action.</p>
+ *          <important>
+ *             <p>To deny all inference access to resources that you specify in the modelId field, you
+ *          need to deny access to the <code>bedrock:InvokeModel</code> and
+ *             <code>bedrock:InvokeModelWithResponseStream</code> actions. Doing this also denies
+ *          access to the resource through the Converse API actions (<a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html">Converse</a> and <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html">ConverseStream</a>). For more information see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/security_iam_id-based-policy-examples.html#security_iam_id-based-policy-examples-deny-inference">Deny access for inference on specific models</a>.
+ *             </p>
+ *          </important>
+ *          <p>For troubleshooting some of the common errors you might encounter when using the <code>InvokeModel</code> API,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html">Troubleshooting Amazon Bedrock API Error Codes</a> in the Amazon Bedrock User Guide</p>
  * @example
  * Use a bare-bones client and the command you need to make an API call.
  * ```javascript
@@ -59,12 +68,14 @@ declare const InvokeModelCommand_base: {
  *   trace: "ENABLED" || "DISABLED",
  *   guardrailIdentifier: "STRING_VALUE",
  *   guardrailVersion: "STRING_VALUE",
+ *   performanceConfigLatency: "standard" || "optimized",
  * };
  * const command = new InvokeModelCommand(input);
  * const response = await client.send(command);
  * // { // InvokeModelResponse
  * //   body: new Uint8Array(), // required
  * //   contentType: "STRING_VALUE", // required
+ * //   performanceConfigLatency: "standard" || "optimized",
  * // };
  *
  * ```
@@ -76,37 +87,43 @@ declare const InvokeModelCommand_base: {
  * @see {@link BedrockRuntimeClientResolvedConfig | config} for BedrockRuntimeClient's `config` shape.
  *
  * @throws {@link AccessDeniedException} (client fault)
- *  <p>The request is denied because of missing access permissions.</p>
+ *  <p>The request is denied because you do not have sufficient permissions to perform the requested action. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-access-denied">AccessDeniedException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link InternalServerException} (server fault)
- *  <p>An internal server error occurred. Retry your request.</p>
+ *  <p>An internal server error occurred. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-internal-failure">InternalFailure</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ModelErrorException} (client fault)
  *  <p>The request failed due to an error while processing the model.</p>
  *
  * @throws {@link ModelNotReadyException} (client fault)
  *  <p>The model specified in the request is not ready to serve inference requests. The AWS SDK
- *            will automatically retry the operation up to 5 times. For information about configuring
- *            automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
- *            reference guide.</p>
+ *          will automatically retry the operation up to 5 times. For information about configuring
+ *          automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
+ *       reference guide.</p>
  *
  * @throws {@link ModelTimeoutException} (client fault)
  *  <p>The request took too long to process. Processing time exceeded the model timeout length.</p>
  *
  * @throws {@link ResourceNotFoundException} (client fault)
- *  <p>The specified resource ARN was not found. Check the ARN and try your request again.</p>
+ *  <p>The specified resource ARN was not found. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-resource-not-found">ResourceNotFound</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ServiceQuotaExceededException} (client fault)
  *  <p>Your request exceeds the service quota for your account. You can view your quotas at <a href="https://docs.aws.amazon.com/servicequotas/latest/userguide/gs-request-quota.html">Viewing service quotas</a>. You can resubmit your request later.</p>
  *
  * @throws {@link ServiceUnavailableException} (server fault)
- *  <p>The service isn't currently available. Try again later.</p>
+ *  <p>The service isn't currently available. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-service-unavailable">ServiceUnavailable</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ThrottlingException} (client fault)
- *  <p>Your request was throttled because of service-wide limitations. Resubmit your request later or in a different region. You can also purchase <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-throughput.html">Provisioned Throughput</a> to increase the rate or number of tokens you can process.</p>
+ *  <p>Your request was denied due to exceeding the account quotas for <i>Amazon Bedrock</i>. For
+ *          troubleshooting this error, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-throttling-exception">ThrottlingException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ValidationException} (client fault)
- *  <p>Input validation failed. Check your request parameters and retry the request.</p>
+ *  <p>The input fails to satisfy the constraints specified by <i>Amazon Bedrock</i>. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-validation-error">ValidationError</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link BedrockRuntimeServiceException}
  * <p>Base exception class for all service exceptions from BedrockRuntime service.</p>

package/dist-types/commands/InvokeModelWithResponseStreamCommand.d.ts

@@ -43,6 +43,15 @@ declare const InvokeModelWithResponseStreamCommand_base: {
  *          example</i> in the <i>Amazon Bedrock User Guide</i>.
  *       </p>
  *          <p>This operation requires permissions to perform the <code>bedrock:InvokeModelWithResponseStream</code> action. </p>
+ *          <important>
+ *             <p>To deny all inference access to resources that you specify in the modelId field, you
+ *          need to deny access to the <code>bedrock:InvokeModel</code> and
+ *             <code>bedrock:InvokeModelWithResponseStream</code> actions. Doing this also denies
+ *          access to the resource through the Converse API actions (<a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html">Converse</a> and <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html">ConverseStream</a>). For more information see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/security_iam_id-based-policy-examples.html#security_iam_id-based-policy-examples-deny-inference">Deny access for inference on specific models</a>.
+ *             </p>
+ *          </important>
+ *          <p>For troubleshooting some of the common errors you might encounter when using the <code>InvokeModelWithResponseStream</code> API,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html">Troubleshooting Amazon Bedrock API Error Codes</a> in the Amazon Bedrock User Guide</p>
  * @example
  * Use a bare-bones client and the command you need to make an API call.
  * ```javascript
@@ -57,6 +66,7 @@ declare const InvokeModelWithResponseStreamCommand_base: {
  *   trace: "ENABLED" || "DISABLED",
  *   guardrailIdentifier: "STRING_VALUE",
  *   guardrailVersion: "STRING_VALUE",
+ *   performanceConfigLatency: "standard" || "optimized",
  * };
  * const command = new InvokeModelWithResponseStreamCommand(input);
  * const response = await client.send(command);
@@ -87,6 +97,7 @@ declare const InvokeModelWithResponseStreamCommand_base: {
  * //     },
  * //   },
  * //   contentType: "STRING_VALUE", // required
+ * //   performanceConfigLatency: "standard" || "optimized",
  * // };
  *
  * ```
@@ -98,19 +109,21 @@ declare const InvokeModelWithResponseStreamCommand_base: {
  * @see {@link BedrockRuntimeClientResolvedConfig | config} for BedrockRuntimeClient's `config` shape.
  *
  * @throws {@link AccessDeniedException} (client fault)
- *  <p>The request is denied because of missing access permissions.</p>
+ *  <p>The request is denied because you do not have sufficient permissions to perform the requested action. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-access-denied">AccessDeniedException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link InternalServerException} (server fault)
- *  <p>An internal server error occurred. Retry your request.</p>
+ *  <p>An internal server error occurred. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-internal-failure">InternalFailure</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ModelErrorException} (client fault)
  *  <p>The request failed due to an error while processing the model.</p>
  *
  * @throws {@link ModelNotReadyException} (client fault)
  *  <p>The model specified in the request is not ready to serve inference requests. The AWS SDK
- *            will automatically retry the operation up to 5 times. For information about configuring
- *            automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
- *            reference guide.</p>
+ *          will automatically retry the operation up to 5 times. For information about configuring
+ *          automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
+ *       reference guide.</p>
  *
  * @throws {@link ModelStreamErrorException} (client fault)
  *  <p>An error occurred while streaming the response. Retry your request.</p>
@@ -119,19 +132,23 @@ declare const InvokeModelWithResponseStreamCommand_base: {
  *  <p>The request took too long to process. Processing time exceeded the model timeout length.</p>
  *
  * @throws {@link ResourceNotFoundException} (client fault)
- *  <p>The specified resource ARN was not found. Check the ARN and try your request again.</p>
+ *  <p>The specified resource ARN was not found. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-resource-not-found">ResourceNotFound</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ServiceQuotaExceededException} (client fault)
  *  <p>Your request exceeds the service quota for your account. You can view your quotas at <a href="https://docs.aws.amazon.com/servicequotas/latest/userguide/gs-request-quota.html">Viewing service quotas</a>. You can resubmit your request later.</p>
  *
  * @throws {@link ServiceUnavailableException} (server fault)
- *  <p>The service isn't currently available. Try again later.</p>
+ *  <p>The service isn't currently available. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-service-unavailable">ServiceUnavailable</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ThrottlingException} (client fault)
- *  <p>Your request was throttled because of service-wide limitations. Resubmit your request later or in a different region. You can also purchase <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-throughput.html">Provisioned Throughput</a> to increase the rate or number of tokens you can process.</p>
+ *  <p>Your request was denied due to exceeding the account quotas for <i>Amazon Bedrock</i>. For
+ *          troubleshooting this error, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-throttling-exception">ThrottlingException</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link ValidationException} (client fault)
- *  <p>Input validation failed. Check your request parameters and retry the request.</p>
+ *  <p>The input fails to satisfy the constraints specified by <i>Amazon Bedrock</i>. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-validation-error">ValidationError</a> in the Amazon Bedrock User Guide</p>
  *
  * @throws {@link BedrockRuntimeServiceException}
  * <p>Base exception class for all service exceptions from BedrockRuntime service.</p>

package/dist-types/models/models_0.d.ts

@@ -2,7 +2,8 @@ import { ExceptionOptionType as __ExceptionOptionType } from "@smithy/smithy-cli
 import { DocumentType as __DocumentType } from "@smithy/types";
 import { BedrockRuntimeServiceException as __BaseException } from "./BedrockRuntimeServiceException";
 /**
- * <p>The request is denied because of missing access permissions.</p>
+ * <p>The request is denied because you do not have sufficient permissions to perform the requested action. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-access-denied">AccessDeniedException</a> in the Amazon Bedrock User Guide</p>
  * @public
  */
 export declare class AccessDeniedException extends __BaseException {
@@ -681,7 +682,8 @@ export interface ApplyGuardrailResponse {
     guardrailCoverage?: GuardrailCoverage | undefined;
 }
 /**
- * <p>An internal server error occurred. Retry your request.</p>
+ * <p>An internal server error occurred. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-internal-failure">InternalFailure</a> in the Amazon Bedrock User Guide</p>
  * @public
  */
 export declare class InternalServerException extends __BaseException {
@@ -693,7 +695,8 @@ export declare class InternalServerException extends __BaseException {
     constructor(opts: __ExceptionOptionType<InternalServerException, __BaseException>);
 }
 /**
- * <p>The specified resource ARN was not found. Check the ARN and try your request again.</p>
+ * <p>The specified resource ARN was not found. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-resource-not-found">ResourceNotFound</a> in the Amazon Bedrock User Guide</p>
  * @public
  */
 export declare class ResourceNotFoundException extends __BaseException {
@@ -717,7 +720,8 @@ export declare class ServiceQuotaExceededException extends __BaseException {
     constructor(opts: __ExceptionOptionType<ServiceQuotaExceededException, __BaseException>);
 }
 /**
- * <p>Your request was throttled because of service-wide limitations. Resubmit your request later or in a different region. You can also purchase <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-throughput.html">Provisioned Throughput</a> to increase the rate or number of tokens you can process.</p>
+ * <p>Your request was denied due to exceeding the account quotas for <i>Amazon Bedrock</i>. For
+ *          troubleshooting this error, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-throttling-exception">ThrottlingException</a> in the Amazon Bedrock User Guide</p>
  * @public
  */
 export declare class ThrottlingException extends __BaseException {
@@ -729,7 +733,8 @@ export declare class ThrottlingException extends __BaseException {
     constructor(opts: __ExceptionOptionType<ThrottlingException, __BaseException>);
 }
 /**
- * <p>Input validation failed. Check your request parameters and retry the request.</p>
+ * <p>The input fails to satisfy the constraints specified by <i>Amazon Bedrock</i>. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-validation-error">ValidationError</a> in the Amazon Bedrock User Guide</p>
  * @public
  */
 export declare class ValidationException extends __BaseException {
@@ -1322,6 +1327,29 @@ export interface Message {
      */
     content: ContentBlock[] | undefined;
 }
+/**
+ * @public
+ * @enum
+ */
+export declare const PerformanceConfigLatency: {
+    readonly OPTIMIZED: "optimized";
+    readonly STANDARD: "standard";
+};
+/**
+ * @public
+ */
+export type PerformanceConfigLatency = (typeof PerformanceConfigLatency)[keyof typeof PerformanceConfigLatency];
+/**
+ * <p>Performance settings for a model.</p>
+ * @public
+ */
+export interface PerformanceConfiguration {
+    /**
+     * <p>To use a latency-optimized version of the model, set to <code>optimized</code>.</p>
+     * @public
+     */
+    latency?: PerformanceConfigLatency | undefined;
+}
 /**
  * <p>Contains a map of variables in a prompt from Prompt management to an object containing the values to fill in for them when running model invocation. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management-how.html">How Prompt management works</a>.</p>
  * @public
@@ -1601,7 +1629,7 @@ export interface ConverseRequest {
      *                <p>If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html">Use a custom model in Amazon Bedrock</a> in the Amazon Bedrock User Guide.</p>
      *             </li>
      *             <li>
-     *                <p>To include a prompt that was defined in Prompt management, specify the ARN of the prompt version to use.</p>
+     *                <p>To include a prompt that was defined in <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html">Prompt management</a>, specify the ARN of the prompt version to use.</p>
      *             </li>
      *          </ul>
      *          <p>The Converse API doesn't support <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html">imported models</a>.</p>
@@ -1660,7 +1688,7 @@ export interface ConverseRequest {
      *          ]</code>
      *          </p>
      *          <p>For information about the JSON Pointer syntax, see the
-     *         <a href="https://datatracker.ietf.org/doc/html/rfc6901">Internet Engineering Task Force (IETF)</a> documentation.</p>
+     *          <a href="https://datatracker.ietf.org/doc/html/rfc6901">Internet Engineering Task Force (IETF)</a> documentation.</p>
      *          <p>
      *             <code>Converse</code> and <code>ConverseStream</code> reject an empty JSON Pointer or incorrectly structured
      *          JSON Pointer with a <code>400</code> error code. if the JSON Pointer is valid, but the requested
@@ -1668,6 +1696,11 @@ export interface ConverseRequest {
      * @public
      */
     additionalModelResponseFieldPaths?: string[] | undefined;
+    /**
+     * <p>Model performance settings for the request.</p>
+     * @public
+     */
+    performanceConfig?: PerformanceConfiguration | undefined;
 }
 /**
  * <p>Metrics for a call to <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html">Converse</a>.</p>
@@ -1815,6 +1848,11 @@ export interface ConverseResponse {
      * @public
      */
     trace?: ConverseTrace | undefined;
+    /**
+     * <p>Model performance settings for the request.</p>
+     * @public
+     */
+    performanceConfig?: PerformanceConfiguration | undefined;
 }
 /**
  * <p>The request failed due to an error while processing the model.</p>
@@ -1840,9 +1878,9 @@ export declare class ModelErrorException extends __BaseException {
 }
 /**
  * <p>The model specified in the request is not ready to serve inference requests. The AWS SDK
- *            will automatically retry the operation up to 5 times. For information about configuring
- *            automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
- *            reference guide.</p>
+ *          will automatically retry the operation up to 5 times. For information about configuring
+ *          automatic retries, see <a href="https://docs.aws.amazon.com/sdkref/latest/guide/feature-retry-behavior.html">Retry behavior</a> in the <i>AWS SDKs and Tools</i>
+ *       reference guide.</p>
  * @public
  */
 export declare class ModelNotReadyException extends __BaseException {
@@ -1867,7 +1905,8 @@ export declare class ModelTimeoutException extends __BaseException {
     constructor(opts: __ExceptionOptionType<ModelTimeoutException, __BaseException>);
 }
 /**
- * <p>The service isn't currently available. Try again later.</p>
+ * <p>The service isn't currently available. For troubleshooting this error,
+ *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-service-unavailable">ServiceUnavailable</a> in the Amazon Bedrock User Guide</p>
  * @public
  */
 export declare class ServiceUnavailableException extends __BaseException {
@@ -1939,7 +1978,7 @@ export interface ConverseStreamRequest {
      *                <p>If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html">Use a custom model in Amazon Bedrock</a> in the Amazon Bedrock User Guide.</p>
      *             </li>
      *             <li>
-     *                <p>To include a prompt that was defined in Prompt management, specify the ARN of the prompt version to use.</p>
+     *                <p>To include a prompt that was defined in <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html">Prompt management</a>, specify the ARN of the prompt version to use.</p>
      *             </li>
      *          </ul>
      *          <p>The Converse API doesn't support <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html">imported models</a>.</p>
@@ -1998,7 +2037,7 @@ export interface ConverseStreamRequest {
      *          ]</code>
      *          </p>
      *          <p>For information about the JSON Pointer syntax, see the
-     *         <a href="https://datatracker.ietf.org/doc/html/rfc6901">Internet Engineering Task Force (IETF)</a> documentation.</p>
+     *          <a href="https://datatracker.ietf.org/doc/html/rfc6901">Internet Engineering Task Force (IETF)</a> documentation.</p>
      *          <p>
      *             <code>Converse</code> and <code>ConverseStream</code> reject an empty JSON Pointer or incorrectly structured
      *          JSON Pointer with a <code>400</code> error code. if the JSON Pointer is valid, but the requested
@@ -2006,6 +2045,11 @@ export interface ConverseStreamRequest {
      * @public
      */
     additionalModelResponseFieldPaths?: string[] | undefined;
+    /**
+     * <p>Model performance settings for the request.</p>
+     * @public
+     */
+    performanceConfig?: PerformanceConfiguration | undefined;
 }
 /**
  * <p>The delta for a tool use block.</p>
@@ -2218,6 +2262,11 @@ export interface ConverseStreamMetadataEvent {
      * @public
      */
     trace?: ConverseStreamTrace | undefined;
+    /**
+     * <p>Model performance configuration metadata for the conversation stream event.</p>
+     * @public
+     */
+    performanceConfig?: PerformanceConfiguration | undefined;
 }
 /**
  * <p>An error occurred while streaming the response. Retry your request.</p>
@@ -2431,7 +2480,8 @@ export declare namespace ConverseStreamOutput {
         $unknown?: never;
     }
     /**
-     * <p>The service isn't currently available. Try again later.</p>
+     * <p>The service isn't currently available. For troubleshooting this error,
+     *          see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html#ts-service-unavailable">ServiceUnavailable</a> in the Amazon Bedrock User Guide</p>
      * @public
      */
     interface ServiceUnavailableExceptionMember {
@@ -2525,12 +2575,15 @@ export interface InvokeModelRequest {
     accept?: string | undefined;
     /**
      * <p>The unique identifier of the model to invoke to run inference.</p>
-     *          <p>The <code>modelId</code> to provide depends on the type of model that you use:</p>
+     *          <p>The <code>modelId</code> to provide depends on the type of model or throughput that you use:</p>
      *          <ul>
      *             <li>
      *                <p>If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns">Amazon Bedrock base model IDs (on-demand throughput)</a> in the Amazon Bedrock User Guide.</p>
      *             </li>
      *             <li>
+     *                <p>If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html">Supported Regions and models for cross-region inference</a> in the Amazon Bedrock User Guide.</p>
+     *             </li>
+     *             <li>
      *                <p>If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html">Run inference using a Provisioned Throughput</a> in the Amazon Bedrock User Guide.</p>
      *             </li>
      *             <li>
@@ -2571,6 +2624,11 @@ export interface InvokeModelRequest {
      * @public
      */
     guardrailVersion?: string | undefined;
+    /**
+     * <p>Model performance settings for the request.</p>
+     * @public
+     */
+    performanceConfigLatency?: PerformanceConfigLatency | undefined;
 }
 /**
  * @public
@@ -2586,6 +2644,11 @@ export interface InvokeModelResponse {
      * @public
      */
     contentType: string | undefined;
+    /**
+     * <p>Model performance settings for the request.</p>
+     * @public
+     */
+    performanceConfigLatency?: PerformanceConfigLatency | undefined;
 }
 /**
  * @public
@@ -2610,12 +2673,15 @@ export interface InvokeModelWithResponseStreamRequest {
     accept?: string | undefined;
     /**
      * <p>The unique identifier of the model to invoke to run inference.</p>
-     *          <p>The <code>modelId</code> to provide depends on the type of model that you use:</p>
+     *          <p>The <code>modelId</code> to provide depends on the type of model or throughput that you use:</p>
      *          <ul>
      *             <li>
      *                <p>If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns">Amazon Bedrock base model IDs (on-demand throughput)</a> in the Amazon Bedrock User Guide.</p>
      *             </li>
      *             <li>
+     *                <p>If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html">Supported Regions and models for cross-region inference</a> in the Amazon Bedrock User Guide.</p>
+     *             </li>
+     *             <li>
      *                <p>If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html">Run inference using a Provisioned Throughput</a> in the Amazon Bedrock User Guide.</p>
      *             </li>
      *             <li>
@@ -2656,6 +2722,11 @@ export interface InvokeModelWithResponseStreamRequest {
      * @public
      */
     guardrailVersion?: string | undefined;
+    /**
+     * <p>Model performance settings for the request.</p>
+     * @public
+     */
+    performanceConfigLatency?: PerformanceConfigLatency | undefined;
 }
 /**
  * <p>Payload content included in the response.</p>
@@ -2762,7 +2833,7 @@ export declare namespace ResponseStream {
         $unknown?: never;
     }
     /**
-     * <p>The service isn't currently available. Try again later.</p>
+     * <p>The service isn't available. Try again later.</p>
      * @public
      */
     interface ServiceUnavailableExceptionMember {
@@ -2814,6 +2885,11 @@ export interface InvokeModelWithResponseStreamResponse {
      * @public
      */
     contentType: string | undefined;
+    /**
+     * <p>Model performance settings for the request.</p>
+     * @public
+     */
+    performanceConfigLatency?: PerformanceConfigLatency | undefined;
 }
 /**
  * @internal

package/dist-types/ts3.4/models/models_0.d.ts

@@ -562,6 +562,15 @@ export interface Message {
   role: ConversationRole | undefined;
   content: ContentBlock[] | undefined;
 }
+export declare const PerformanceConfigLatency: {
+  readonly OPTIMIZED: "optimized";
+  readonly STANDARD: "standard";
+};
+export type PerformanceConfigLatency =
+  (typeof PerformanceConfigLatency)[keyof typeof PerformanceConfigLatency];
+export interface PerformanceConfiguration {
+  latency?: PerformanceConfigLatency | undefined;
+}
 export type PromptVariableValues =
   | PromptVariableValues.TextMember
   | PromptVariableValues.$UnknownMember;
@@ -703,6 +712,7 @@ export interface ConverseRequest {
   additionalModelRequestFields?: __DocumentType | undefined;
   promptVariables?: Record<string, PromptVariableValues> | undefined;
   additionalModelResponseFieldPaths?: string[] | undefined;
+  performanceConfig?: PerformanceConfiguration | undefined;
 }
 export interface ConverseMetrics {
   latencyMs: number | undefined;
@@ -754,6 +764,7 @@ export interface ConverseResponse {
   metrics: ConverseMetrics | undefined;
   additionalModelResponseFields?: __DocumentType | undefined;
   trace?: ConverseTrace | undefined;
+  performanceConfig?: PerformanceConfiguration | undefined;
 }
 export declare class ModelErrorException extends __BaseException {
   readonly name: "ModelErrorException";
@@ -808,6 +819,7 @@ export interface ConverseStreamRequest {
   additionalModelRequestFields?: __DocumentType | undefined;
   promptVariables?: Record<string, PromptVariableValues> | undefined;
   additionalModelResponseFieldPaths?: string[] | undefined;
+  performanceConfig?: PerformanceConfiguration | undefined;
 }
 export interface ToolUseBlockDelta {
   input: string | undefined;
@@ -889,6 +901,7 @@ export interface ConverseStreamMetadataEvent {
   usage: TokenUsage | undefined;
   metrics: ConverseStreamMetrics | undefined;
   trace?: ConverseStreamTrace | undefined;
+  performanceConfig?: PerformanceConfiguration | undefined;
 }
 export declare class ModelStreamErrorException extends __BaseException {
   readonly name: "ModelStreamErrorException";
@@ -1113,10 +1126,12 @@ export interface InvokeModelRequest {
   trace?: Trace | undefined;
   guardrailIdentifier?: string | undefined;
   guardrailVersion?: string | undefined;
+  performanceConfigLatency?: PerformanceConfigLatency | undefined;
 }
 export interface InvokeModelResponse {
   body: Uint8Array | undefined;
   contentType: string | undefined;
+  performanceConfigLatency?: PerformanceConfigLatency | undefined;
 }
 export interface InvokeModelWithResponseStreamRequest {
   body?: Uint8Array | undefined;
@@ -1126,6 +1141,7 @@ export interface InvokeModelWithResponseStreamRequest {
   trace?: Trace | undefined;
   guardrailIdentifier?: string | undefined;
   guardrailVersion?: string | undefined;
+  performanceConfigLatency?: PerformanceConfigLatency | undefined;
 }
 export interface PayloadPart {
   bytes?: Uint8Array | undefined;
@@ -1235,6 +1251,7 @@ export declare namespace ResponseStream {
 export interface InvokeModelWithResponseStreamResponse {
   body: AsyncIterable<ResponseStream> | undefined;
   contentType: string | undefined;
+  performanceConfigLatency?: PerformanceConfigLatency | undefined;
 }
 export declare const ConverseRequestFilterSensitiveLog: (
   obj: ConverseRequest

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@aws-sdk/client-bedrock-runtime",
   "description": "AWS SDK for JavaScript Bedrock Runtime Client for Node.js, Browser and React Native",
-  "version": "3.696.0",
+  "version": "3.704.0",
   "scripts": {
     "build": "concurrently 'yarn:build:cjs' 'yarn:build:es' 'yarn:build:types'",
     "build:cjs": "node ../../scripts/compilation/inline client-bedrock-runtime",
@@ -20,10 +20,10 @@
   "dependencies": {
     "@aws-crypto/sha256-browser": "5.2.0",
     "@aws-crypto/sha256-js": "5.2.0",
-    "@aws-sdk/client-sso-oidc": "3.696.0",
-    "@aws-sdk/client-sts": "3.696.0",
+    "@aws-sdk/client-sso-oidc": "3.699.0",
+    "@aws-sdk/client-sts": "3.699.0",
     "@aws-sdk/core": "3.696.0",
-    "@aws-sdk/credential-provider-node": "3.696.0",
+    "@aws-sdk/credential-provider-node": "3.699.0",
     "@aws-sdk/middleware-host-header": "3.696.0",
     "@aws-sdk/middleware-logger": "3.696.0",
     "@aws-sdk/middleware-recursion-detection": "3.696.0",