diff --git a/docs/changelog/117235.yaml b/docs/changelog/117235.yaml
new file mode 100644
index 000000000000..dbf0b4cc1838
--- /dev/null
+++ b/docs/changelog/117235.yaml
@@ -0,0 +1,5 @@
+pr: 117235
+summary: "Deprecate `ChunkingOptions` parameter"
+area: ES|QL
+type: enhancement
+issues: []
diff --git a/server/src/main/java/org/elasticsearch/inference/ChunkingOptions.java b/server/src/main/java/org/elasticsearch/inference/ChunkingOptions.java
deleted file mode 100644
index 5953e2cb44eb..000000000000
--- a/server/src/main/java/org/elasticsearch/inference/ChunkingOptions.java
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
- * or more contributor license agreements. Licensed under the "Elastic License
- * 2.0", the "GNU Affero General Public License v3.0 only", and the "Server Side
- * Public License v 1"; you may not use this file except in compliance with, at
- * your election, the "Elastic License 2.0", the "GNU Affero General Public
- * License v3.0 only", or the "Server Side Public License, v 1".
- */
-
-package org.elasticsearch.inference;
-
-import org.elasticsearch.core.Nullable;
-
-public record ChunkingOptions(@Nullable Integer windowSize, @Nullable Integer span) {
-
-    public boolean settingsArePresent() {
-        return windowSize != null || span != null;
-    }
-}
diff --git a/server/src/main/java/org/elasticsearch/inference/InferenceService.java b/server/src/main/java/org/elasticsearch/inference/InferenceService.java
index c6e09f61befa..4497254aad1f 100644
--- a/server/src/main/java/org/elasticsearch/inference/InferenceService.java
+++ b/server/src/main/java/org/elasticsearch/inference/InferenceService.java
@@ -112,16 +112,11 @@ public interface InferenceService extends Closeable {
     );
 
     /**
-     * Chunk long text according to {@code chunkingOptions} or the
-     * model defaults if {@code chunkingOptions} contains unset
-     * values.
-     *
      * @param model           The model
      * @param query           Inference query, mainly for re-ranking
      * @param input           Inference input
      * @param taskSettings    Settings in the request to override the model's defaults
      * @param inputType       For search, ingest etc
-     * @param chunkingOptions The window and span options to apply
      * @param timeout         The timeout for the request
      * @param listener        Chunked Inference result listener
      */
@@ -131,7 +126,6 @@ public interface InferenceService extends Closeable {
         List<String> input,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     );
diff --git a/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestDenseInferenceServiceExtension.java b/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestDenseInferenceServiceExtension.java
index 2ddc4f6c3e2f..ae11a02d312e 100644
--- a/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestDenseInferenceServiceExtension.java
+++ b/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestDenseInferenceServiceExtension.java
@@ -18,7 +18,6 @@ import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.index.mapper.vectors.DenseVectorFieldMapper;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceExtension;
@@ -140,7 +139,6 @@ public class TestDenseInferenceServiceExtension implements InferenceServiceExten
             List<String> input,
             Map<String, Object> taskSettings,
             InputType inputType,
-            ChunkingOptions chunkingOptions,
             TimeValue timeout,
             ActionListener<List<ChunkedInferenceServiceResults>> listener
         ) {
diff --git a/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestRerankingServiceExtension.java b/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestRerankingServiceExtension.java
index 2075c1b1924b..9320571572f0 100644
--- a/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestRerankingServiceExtension.java
+++ b/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestRerankingServiceExtension.java
@@ -17,7 +17,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceExtension;
@@ -128,7 +127,6 @@ public class TestRerankingServiceExtension implements InferenceServiceExtension
             List<String> input,
             Map<String, Object> taskSettings,
             InputType inputType,
-            ChunkingOptions chunkingOptions,
             TimeValue timeout,
             ActionListener<List<ChunkedInferenceServiceResults>> listener
         ) {
diff --git a/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestSparseInferenceServiceExtension.java b/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestSparseInferenceServiceExtension.java
index 3d6f0ce6eba0..fe0223cce032 100644
--- a/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestSparseInferenceServiceExtension.java
+++ b/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestSparseInferenceServiceExtension.java
@@ -17,7 +17,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceExtension;
@@ -131,7 +130,6 @@ public class TestSparseInferenceServiceExtension implements InferenceServiceExte
             List<String> input,
             Map<String, Object> taskSettings,
             InputType inputType,
-            ChunkingOptions chunkingOptions,
             TimeValue timeout,
             ActionListener<List<ChunkedInferenceServiceResults>> listener
         ) {
diff --git a/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestStreamingCompletionServiceExtension.java b/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestStreamingCompletionServiceExtension.java
index 595b92a6be66..6d7983bc8cb5 100644
--- a/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestStreamingCompletionServiceExtension.java
+++ b/x-pack/plugin/inference/qa/test-service-plugin/src/main/java/org/elasticsearch/xpack/inference/mock/TestStreamingCompletionServiceExtension.java
@@ -19,7 +19,6 @@ import org.elasticsearch.common.xcontent.ChunkedToXContent;
 import org.elasticsearch.common.xcontent.ChunkedToXContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceExtension;
@@ -160,7 +159,6 @@ public class TestStreamingCompletionServiceExtension implements InferenceService
             List<String> input,
             Map<String, Object> taskSettings,
             InputType inputType,
-            ChunkingOptions chunkingOptions,
             TimeValue timeout,
             ActionListener<List<ChunkedInferenceServiceResults>> listener
         ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/action/filter/ShardBulkInferenceActionFilter.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/action/filter/ShardBulkInferenceActionFilter.java
index dd59230e575c..d178e927aa65 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/action/filter/ShardBulkInferenceActionFilter.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/action/filter/ShardBulkInferenceActionFilter.java
@@ -30,7 +30,6 @@ import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.Releasable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.InferenceService;
 import org.elasticsearch.inference.InferenceServiceRegistry;
 import org.elasticsearch.inference.InputType;
@@ -337,16 +336,7 @@ public class ShardBulkInferenceActionFilter implements MappedActionFilter {
                 }
             };
             inferenceProvider.service()
-                .chunkedInfer(
-                    inferenceProvider.model(),
-                    null,
-                    inputs,
-                    Map.of(),
-                    InputType.INGEST,
-                    new ChunkingOptions(null, null),
-                    TimeValue.MAX_VALUE,
-                    completionListener
-                );
+                .chunkedInfer(inferenceProvider.model(), null, inputs, Map.of(), InputType.INGEST, TimeValue.MAX_VALUE, completionListener);
         }
 
         private FieldInferenceResponseAccumulator ensureResponseAccumulatorSlot(int id) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/SenderService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/SenderService.java
index b8a99227cf51..8e2dac1ef9db 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/SenderService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/SenderService.java
@@ -12,7 +12,6 @@ import org.elasticsearch.core.IOUtils;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.InferenceService;
 import org.elasticsearch.inference.InferenceServiceResults;
 import org.elasticsearch.inference.InputType;
@@ -76,13 +75,12 @@ public abstract class SenderService implements InferenceService {
         List<String> input,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
         init();
         // a non-null query is not supported and is dropped by all providers
-        doChunkedInfer(model, new DocumentsOnlyInput(input), taskSettings, inputType, chunkingOptions, timeout, listener);
+        doChunkedInfer(model, new DocumentsOnlyInput(input), taskSettings, inputType, timeout, listener);
     }
 
     protected abstract void doInfer(
@@ -99,7 +97,6 @@ public abstract class SenderService implements InferenceService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     );
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/alibabacloudsearch/AlibabaCloudSearchService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/alibabacloudsearch/AlibabaCloudSearchService.java
index 6d77663f49ec..d7ac7caed7ef 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/alibabacloudsearch/AlibabaCloudSearchService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/alibabacloudsearch/AlibabaCloudSearchService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -289,7 +288,6 @@ public class AlibabaCloudSearchService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/amazonbedrock/AmazonBedrockService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/amazonbedrock/AmazonBedrockService.java
index a69b9d2c7040..48b3c3df03e1 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/amazonbedrock/AmazonBedrockService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/amazonbedrock/AmazonBedrockService.java
@@ -17,7 +17,6 @@ import org.elasticsearch.core.IOUtils;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -114,7 +113,6 @@ public class AmazonBedrockService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/anthropic/AnthropicService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/anthropic/AnthropicService.java
index eba7353f2b12..b3d503de8e3e 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/anthropic/AnthropicService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/anthropic/AnthropicService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -220,7 +219,6 @@ public class AnthropicService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/azureaistudio/AzureAiStudioService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/azureaistudio/AzureAiStudioService.java
index a2f8dc409585..bba331fc0b5d 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/azureaistudio/AzureAiStudioService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/azureaistudio/AzureAiStudioService.java
@@ -16,7 +16,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -107,7 +106,6 @@ public class AzureAiStudioService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/azureopenai/AzureOpenAiService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/azureopenai/AzureOpenAiService.java
index 2f3a935cdf01..16c94dfa9ad9 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/azureopenai/AzureOpenAiService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/azureopenai/AzureOpenAiService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -261,7 +260,6 @@ public class AzureOpenAiService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/cohere/CohereService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/cohere/CohereService.java
index cc67470686a0..b3d8b3b6efce 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/cohere/CohereService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/cohere/CohereService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -260,7 +259,6 @@ public class CohereService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceService.java
index e7ce5903163d..1f08c06edaa9 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceService.java
@@ -16,7 +16,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -109,7 +108,6 @@ public class ElasticInferenceService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalService.java
index 6d124906d65b..2ec3a9d62943 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalService.java
@@ -19,7 +19,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceResults;
@@ -676,11 +675,10 @@ public class ElasticsearchInternalService extends BaseElasticsearchInternalServi
         List<String> input,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
-        chunkedInfer(model, null, input, taskSettings, inputType, chunkingOptions, timeout, listener);
+        chunkedInfer(model, null, input, taskSettings, inputType, timeout, listener);
     }
 
     @Override
@@ -690,7 +688,6 @@ public class ElasticsearchInternalService extends BaseElasticsearchInternalServi
         List<String> input,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioService.java
index 1c01ebbe2c0e..57a8a66a3f3a 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -315,7 +314,6 @@ public class GoogleAiStudioService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/googlevertexai/GoogleVertexAiService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/googlevertexai/GoogleVertexAiService.java
index 204593464a4a..857d475499aa 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/googlevertexai/GoogleVertexAiService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/googlevertexai/GoogleVertexAiService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -213,7 +212,6 @@ public class GoogleVertexAiService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceService.java
index eede14a97523..51cca72f2605 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -116,7 +115,6 @@ public class HuggingFaceService extends HuggingFaceBaseService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/elser/HuggingFaceElserService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/elser/HuggingFaceElserService.java
index a2e22e24172c..75920efa251f 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/elser/HuggingFaceElserService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/elser/HuggingFaceElserService.java
@@ -16,7 +16,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -88,7 +87,6 @@ public class HuggingFaceElserService extends HuggingFaceBaseService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/ibmwatsonx/IbmWatsonxService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/ibmwatsonx/IbmWatsonxService.java
index 592900d117b3..ea263fb77a2d 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/ibmwatsonx/IbmWatsonxService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/ibmwatsonx/IbmWatsonxService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -283,7 +282,6 @@ public class IbmWatsonxService extends SenderService {
         DocumentsOnlyInput input,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/mistral/MistralService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/mistral/MistralService.java
index 2e810c357f8b..fe0edb851902 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/mistral/MistralService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/mistral/MistralService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -95,7 +94,6 @@ public class MistralService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/OpenAiService.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/OpenAiService.java
index 81ab87a46169..20ff1c617d21 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/OpenAiService.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/OpenAiService.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.util.LazyInitializable;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -264,7 +263,6 @@ public class OpenAiService extends SenderService {
         DocumentsOnlyInput inputs,
         Map<String, Object> taskSettings,
         InputType inputType,
-        ChunkingOptions chunkingOptions,
         TimeValue timeout,
         ActionListener<List<ChunkedInferenceServiceResults>> listener
     ) {
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/action/filter/ShardBulkInferenceActionFilterTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/action/filter/ShardBulkInferenceActionFilterTests.java
index 770e6e3cb9cf..2416aeb62ff3 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/action/filter/ShardBulkInferenceActionFilterTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/action/filter/ShardBulkInferenceActionFilterTests.java
@@ -291,7 +291,7 @@ public class ShardBulkInferenceActionFilterTests extends ESTestCase {
             StaticModel model = (StaticModel) invocationOnMock.getArguments()[0];
             List<String> inputs = (List<String>) invocationOnMock.getArguments()[2];
             ActionListener<List<ChunkedInferenceServiceResults>> listener = (ActionListener<
-                List<ChunkedInferenceServiceResults>>) invocationOnMock.getArguments()[7];
+                List<ChunkedInferenceServiceResults>>) invocationOnMock.getArguments()[6];
             Runnable runnable = () -> {
                 List<ChunkedInferenceServiceResults> results = new ArrayList<>();
                 for (String input : inputs) {
@@ -310,7 +310,7 @@ public class ShardBulkInferenceActionFilterTests extends ESTestCase {
             }
             return null;
         };
-        doAnswer(chunkedInferAnswer).when(inferenceService).chunkedInfer(any(), any(), any(), any(), any(), any(), any(), any());
+        doAnswer(chunkedInferAnswer).when(inferenceService).chunkedInfer(any(), any(), any(), any(), any(), any(), any());
 
         Answer<Model> modelAnswer = invocationOnMock -> {
             String inferenceId = (String) invocationOnMock.getArguments()[0];
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/SenderServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/SenderServiceTests.java
index d8402c28cec8..47a96bf78dda 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/SenderServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/SenderServiceTests.java
@@ -12,7 +12,6 @@ import org.elasticsearch.action.ActionListener;
 import org.elasticsearch.action.support.PlainActionFuture;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySettingsConfiguration;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -126,7 +125,6 @@ public class SenderServiceTests extends ESTestCase {
             DocumentsOnlyInput inputs,
             Map<String, Object> taskSettings,
             InputType inputType,
-            ChunkingOptions chunkingOptions,
             TimeValue timeout,
             ActionListener<List<ChunkedInferenceServiceResults>> listener
         ) {
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/alibabacloudsearch/AlibabaCloudSearchServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/alibabacloudsearch/AlibabaCloudSearchServiceTests.java
index b6d29ccab9a4..a154ded39582 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/alibabacloudsearch/AlibabaCloudSearchServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/alibabacloudsearch/AlibabaCloudSearchServiceTests.java
@@ -16,7 +16,6 @@ import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -401,7 +400,6 @@ public class AlibabaCloudSearchServiceTests extends ESTestCase {
                     List.of("foo", "bar"),
                     new HashMap<>(),
                     InputType.INGEST,
-                    new ChunkingOptions(null, null),
                     InferenceAction.Request.DEFAULT_TIMEOUT,
                     listener
                 );
@@ -420,16 +418,7 @@ public class AlibabaCloudSearchServiceTests extends ESTestCase {
             var model = createModelForTaskType(taskType, chunkingSettings);
 
             PlainActionFuture<List<ChunkedInferenceServiceResults>> listener = new PlainActionFuture<>();
-            service.chunkedInfer(
-                model,
-                null,
-                input,
-                new HashMap<>(),
-                InputType.INGEST,
-                new ChunkingOptions(null, null),
-                InferenceAction.Request.DEFAULT_TIMEOUT,
-                listener
-            );
+            service.chunkedInfer(model, null, input, new HashMap<>(), InputType.INGEST, InferenceAction.Request.DEFAULT_TIMEOUT, listener);
 
             var results = listener.actionGet(TIMEOUT);
             assertThat(results, instanceOf(List.class));
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/amazonbedrock/AmazonBedrockServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/amazonbedrock/AmazonBedrockServiceTests.java
index e583e50075ee..35b5642b7a60 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/amazonbedrock/AmazonBedrockServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/amazonbedrock/AmazonBedrockServiceTests.java
@@ -20,7 +20,6 @@ import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -1559,7 +1558,6 @@ public class AmazonBedrockServiceTests extends ESTestCase {
                     List.of("abc", "xyz"),
                     new HashMap<>(),
                     InputType.INGEST,
-                    new ChunkingOptions(null, null),
                     InferenceAction.Request.DEFAULT_TIMEOUT,
                     listener
                 );
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/azureaistudio/AzureAiStudioServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/azureaistudio/AzureAiStudioServiceTests.java
index 76ea7a5bde5c..8636ba8890e8 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/azureaistudio/AzureAiStudioServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/azureaistudio/AzureAiStudioServiceTests.java
@@ -20,7 +20,6 @@ import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -1194,7 +1193,6 @@ public class AzureAiStudioServiceTests extends ESTestCase {
                 List.of("foo", "bar"),
                 new HashMap<>(),
                 InputType.INGEST,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/azureopenai/AzureOpenAiServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/azureopenai/AzureOpenAiServiceTests.java
index dc1970e26a3f..b0c590e237a4 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/azureopenai/AzureOpenAiServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/azureopenai/AzureOpenAiServiceTests.java
@@ -20,7 +20,6 @@ import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -1343,7 +1342,6 @@ public class AzureOpenAiServiceTests extends ESTestCase {
                 List.of("foo", "bar"),
                 new HashMap<>(),
                 InputType.INGEST,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/cohere/CohereServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/cohere/CohereServiceTests.java
index 30f3b344a268..259a32aa6254 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/cohere/CohereServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/cohere/CohereServiceTests.java
@@ -21,7 +21,6 @@ import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.index.mapper.vectors.DenseVectorFieldMapper;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -1451,7 +1450,6 @@ public class CohereServiceTests extends ESTestCase {
                 List.of("foo", "bar"),
                 new HashMap<>(),
                 InputType.UNSPECIFIED,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );
@@ -1543,7 +1541,6 @@ public class CohereServiceTests extends ESTestCase {
                 List.of("foo", "bar"),
                 new HashMap<>(),
                 InputType.UNSPECIFIED,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceServiceTests.java
index 3767ac496d18..d3101099d06c 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceServiceTests.java
@@ -17,7 +17,6 @@ import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.EmptySecretSettings;
 import org.elasticsearch.inference.EmptyTaskSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -461,7 +460,6 @@ public class ElasticInferenceServiceTests extends ESTestCase {
                 List.of("input text"),
                 new HashMap<>(),
                 InputType.INGEST,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalServiceTests.java
index 9a4d0dda8223..306509ea60cf 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalServiceTests.java
@@ -25,7 +25,6 @@ import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.index.mapper.vectors.DenseVectorFieldMapper;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptyTaskSettings;
 import org.elasticsearch.inference.InferenceResults;
@@ -902,7 +901,6 @@ public class ElasticsearchInternalServiceTests extends ESTestCase {
             List.of("foo", "bar"),
             Map.of(),
             InputType.SEARCH,
-            new ChunkingOptions(null, null),
             InferenceAction.Request.DEFAULT_TIMEOUT,
             latchedListener
         );
@@ -973,7 +971,6 @@ public class ElasticsearchInternalServiceTests extends ESTestCase {
             List.of("foo", "bar"),
             Map.of(),
             InputType.SEARCH,
-            new ChunkingOptions(null, null),
             InferenceAction.Request.DEFAULT_TIMEOUT,
             latchedListener
         );
@@ -1044,7 +1041,6 @@ public class ElasticsearchInternalServiceTests extends ESTestCase {
             List.of("foo", "bar"),
             Map.of(),
             InputType.SEARCH,
-            new ChunkingOptions(null, null),
             InferenceAction.Request.DEFAULT_TIMEOUT,
             latchedListener
         );
@@ -1090,7 +1086,6 @@ public class ElasticsearchInternalServiceTests extends ESTestCase {
             List.of("foo", "bar"),
             Map.of(),
             InputType.SEARCH,
-            null,
             InferenceAction.Request.DEFAULT_TIMEOUT,
             ActionListener.wrap(r -> fail("unexpected result"), e -> fail(e.getMessage()))
         );
@@ -1102,7 +1097,6 @@ public class ElasticsearchInternalServiceTests extends ESTestCase {
             List.of("foo", "bar"),
             Map.of(),
             InputType.SEARCH,
-            new ChunkingOptions(256, null),
             InferenceAction.Request.DEFAULT_TIMEOUT,
             ActionListener.wrap(r -> fail("unexpected result"), e -> fail(e.getMessage()))
         );
@@ -1155,7 +1149,6 @@ public class ElasticsearchInternalServiceTests extends ESTestCase {
             List.of("foo", "bar", "baz"),
             Map.of(),
             InputType.SEARCH,
-            new ChunkingOptions(null, null),
             InferenceAction.Request.DEFAULT_TIMEOUT,
             latchedListener
         );
@@ -1228,7 +1221,6 @@ public class ElasticsearchInternalServiceTests extends ESTestCase {
             List.of(input),
             Map.of(),
             InputType.SEARCH,
-            new ChunkingOptions(null, null),
             InferenceAction.Request.DEFAULT_TIMEOUT,
             latchedListener
         );
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioServiceTests.java
index bc8020d8d88f..375c583cce13 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioServiceTests.java
@@ -19,7 +19,6 @@ import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.Strings;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptyTaskSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -870,16 +869,7 @@ public class GoogleAiStudioServiceTests extends ESTestCase {
             webServer.enqueue(new MockResponse().setResponseCode(200).setBody(responseJson));
 
             PlainActionFuture<List<ChunkedInferenceServiceResults>> listener = new PlainActionFuture<>();
-            service.chunkedInfer(
-                model,
-                null,
-                input,
-                new HashMap<>(),
-                InputType.INGEST,
-                new ChunkingOptions(null, null),
-                InferenceAction.Request.DEFAULT_TIMEOUT,
-                listener
-            );
+            service.chunkedInfer(model, null, input, new HashMap<>(), InputType.INGEST, InferenceAction.Request.DEFAULT_TIMEOUT, listener);
 
             var results = listener.actionGet(TIMEOUT);
             assertThat(results, hasSize(2));
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceElserServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceElserServiceTests.java
index df82f1ed393b..8f0e481213cd 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceElserServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceElserServiceTests.java
@@ -15,7 +15,6 @@ import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InputType;
 import org.elasticsearch.test.ESTestCase;
@@ -98,7 +97,6 @@ public class HuggingFaceElserServiceTests extends ESTestCase {
                 List.of("abc"),
                 new HashMap<>(),
                 InputType.INGEST,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceServiceTests.java
index 0ff4bd805ea3..022cbecd1ea6 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/huggingface/HuggingFaceServiceTests.java
@@ -19,7 +19,6 @@ import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -782,7 +781,6 @@ public class HuggingFaceServiceTests extends ESTestCase {
                 List.of("abc"),
                 new HashMap<>(),
                 InputType.INGEST,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );
@@ -838,7 +836,6 @@ public class HuggingFaceServiceTests extends ESTestCase {
                 List.of("abc"),
                 new HashMap<>(),
                 InputType.INGEST,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/ibmwatsonx/IbmWatsonxServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/ibmwatsonx/IbmWatsonxServiceTests.java
index 1261e3834437..5aa826f1d80f 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/ibmwatsonx/IbmWatsonxServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/ibmwatsonx/IbmWatsonxServiceTests.java
@@ -19,7 +19,6 @@ import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.EmptyTaskSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
@@ -686,16 +685,7 @@ public class IbmWatsonxServiceTests extends ESTestCase {
                 getUrl(webServer)
             );
             PlainActionFuture<List<ChunkedInferenceServiceResults>> listener = new PlainActionFuture<>();
-            service.chunkedInfer(
-                model,
-                null,
-                input,
-                new HashMap<>(),
-                InputType.INGEST,
-                new ChunkingOptions(null, null),
-                InferenceAction.Request.DEFAULT_TIMEOUT,
-                listener
-            );
+            service.chunkedInfer(model, null, input, new HashMap<>(), InputType.INGEST, InferenceAction.Request.DEFAULT_TIMEOUT, listener);
 
             var results = listener.actionGet(TIMEOUT);
             assertThat(results, hasSize(2));
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/mistral/MistralServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/mistral/MistralServiceTests.java
index 71e9eac9a663..73bf03fd43ec 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/mistral/MistralServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/mistral/MistralServiceTests.java
@@ -19,7 +19,6 @@ import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -673,7 +672,6 @@ public class MistralServiceTests extends ESTestCase {
                 List.of("abc", "def"),
                 new HashMap<>(),
                 InputType.INGEST,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/openai/OpenAiServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/openai/OpenAiServiceTests.java
index 509a1f8a3d01..76b5d6fee2c5 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/openai/OpenAiServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/openai/OpenAiServiceTests.java
@@ -20,7 +20,6 @@ import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.xcontent.XContentHelper;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.ChunkedInferenceServiceResults;
-import org.elasticsearch.inference.ChunkingOptions;
 import org.elasticsearch.inference.ChunkingSettings;
 import org.elasticsearch.inference.InferenceServiceConfiguration;
 import org.elasticsearch.inference.InferenceServiceResults;
@@ -1558,7 +1557,6 @@ public class OpenAiServiceTests extends ESTestCase {
                 List.of("foo", "bar"),
                 new HashMap<>(),
                 InputType.INGEST,
-                new ChunkingOptions(null, null),
                 InferenceAction.Request.DEFAULT_TIMEOUT,
                 listener
             );