feat(api): enabling fast-mode in claude-opus-4-6

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 34
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/anthropic%2Fanthropic-267f913f89364cb8df3a758335a974b43eb98019a8ceef0a9b0a94ef34c2a3b5.yml
-openapi_spec_hash: aa708f3d3bc54992526cbf5894427446
-config_hash: d56fbaeeb3934b1a3b374590c9837ddd
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/anthropic%2Fanthropic-fee5dc365a4948e68639582c5301d4d0666c7d85a11628d7917e1477f76d3da1.yml
+openapi_spec_hash: d5543958074cd2bd74096cd69f3bb4f9
+config_hash: c4802b6c7f8ffae62f7d73b2ac61e635

src/resources/beta/beta.ts

@@ -245,7 +245,8 @@ export type AnthropicBeta =
   | 'context-1m-2025-08-07'
   | 'context-management-2025-06-27'
   | 'model-context-window-exceeded-2025-08-26'
-  | 'skills-2025-10-02';
+  | 'skills-2025-10-02'
+  | 'fast-mode-2026-02-01';
 
 export interface BetaAPIError {
   message: string;

src/resources/beta/messages/batches.ts

@@ -592,6 +592,12 @@ export namespace BatchCreateParams {
        */
       service_tier?: 'auto' | 'standard_only';
 
+      /**
+       * The inference speed mode for this request. `"fast"` enables high
+       * output-tokens-per-second inference.
+       */
+      speed?: 'standard' | 'fast' | null;
+
       /**
        * Custom text sequences that will cause the model to stop generating.
        *

src/resources/beta/messages/messages.ts

@@ -2907,6 +2907,11 @@ export interface BetaUsage {
    * If the request used the priority, standard, or batch tier.
    */
   service_tier: 'standard' | 'priority' | 'batch' | null;
+
+  /**
+   * The inference speed mode used for this request.
+   */
+  speed: 'standard' | 'fast' | null;
 }
 
 export interface BetaWebFetchBlock {
@@ -3345,6 +3350,12 @@ export interface MessageCreateParamsBase {
    */
   service_tier?: 'auto' | 'standard_only';
 
+  /**
+   * Body param: The inference speed mode for this request. `"fast"` enables high
+   * output-tokens-per-second inference.
+   */
+  speed?: 'standard' | 'fast' | null;
+
   /**
    * Body param: Custom text sequences that will cause the model to stop generating.
    *
@@ -3645,6 +3656,12 @@ export interface MessageCountTokensParams {
    */
   output_format?: BetaJSONOutputFormat | null;
 
+  /**
+   * Body param: The inference speed mode for this request. `"fast"` enables high
+   * output-tokens-per-second inference.
+   */
+  speed?: 'standard' | 'fast' | null;
+
   /**
    * Body param: System prompt.
    *

tests/api-resources/beta/messages/batches.test.ts

@@ -86,6 +86,7 @@ describe('resource batches', () => {
               type: 'json_schema',
             },
             service_tier: 'auto',
+            speed: 'standard',
             stop_sequences: ['string'],
             stream: false,
             system: [

tests/api-resources/beta/messages/messages.test.ts

@@ -75,6 +75,7 @@ describe('resource messages', () => {
         type: 'json_schema',
       },
       service_tier: 'auto',
+      speed: 'standard',
       stop_sequences: ['string'],
       stream: false,
       system: [
@@ -173,6 +174,7 @@ describe('resource messages', () => {
         schema: { foo: 'bar' },
         type: 'json_schema',
       },
+      speed: 'standard',
       system: [
         {
           text: "Today's date is 2024-06-01.",

tests/lib/parser.test.ts

@@ -87,6 +87,7 @@ describe('Beta Parser', () => {
         service_tier: null,
         inference_geo: null,
         iterations: null,
+        speed: null,
       },
       container: null,
     };
@@ -263,6 +264,7 @@ describe('Beta Parser', () => {
         service_tier: null,
         inference_geo: null,
         iterations: null,
+        speed: null,
       },
       container: null,
     };

tests/lib/tools/ToolRunner.test.ts

@@ -112,6 +112,7 @@ function betaMessageToStreamEvents(message: BetaMessage): BetaRawMessageStreamEv
         service_tier: null,
         inference_geo: null,
         iterations: null,
+        speed: null,
       },
     },
   });
@@ -240,6 +241,7 @@ function setupTest(params: Partial<ToolRunnerParams> = {}): SetupTestResult<bool
         service_tier: null,
         inference_geo: null,
         iterations: null,
+        speed: null,
       },
     };
     handleRequest(async () => {
@@ -275,6 +277,7 @@ function setupTest(params: Partial<ToolRunnerParams> = {}): SetupTestResult<bool
         service_tier: null,
         inference_geo: null,
         iterations: null,
+        speed: null,
       },
     };