diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiActionCreator.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiActionCreator.java
index a7767ab4e764b..4afe8a3411dbc 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiActionCreator.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiActionCreator.java
@@ -16,12 +16,12 @@
 import org.elasticsearch.xpack.inference.external.http.sender.Sender;
 import org.elasticsearch.xpack.inference.external.http.sender.TruncatingRequestManager;
 import org.elasticsearch.xpack.inference.external.http.sender.UnifiedChatInput;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiChatCompletionResponseEntity;
 import org.elasticsearch.xpack.inference.external.openai.OpenAiChatCompletionResponseHandler;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiEmbeddingsRequest;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiEmbeddingsResponseEntity;
 import org.elasticsearch.xpack.inference.external.openai.OpenAiResponseHandler;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiEmbeddingsRequest;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiUnifiedChatCompletionRequest;
-import org.elasticsearch.xpack.inference.external.response.openai.OpenAiChatCompletionResponseEntity;
-import org.elasticsearch.xpack.inference.external.response.openai.OpenAiEmbeddingsResponseEntity;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiUnifiedChatCompletionRequest;
 import org.elasticsearch.xpack.inference.services.ServiceComponents;
 import org.elasticsearch.xpack.inference.services.openai.completion.OpenAiChatCompletionModel;
 import org.elasticsearch.xpack.inference.services.openai.embeddings.OpenAiEmbeddingsModel;
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/AzureOpenAiEmbeddingsRequestManager.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/AzureOpenAiEmbeddingsRequestManager.java
index fc39bd4af96d4..9e88f69c89db7 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/AzureOpenAiEmbeddingsRequestManager.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/AzureOpenAiEmbeddingsRequestManager.java
@@ -16,8 +16,8 @@
 import org.elasticsearch.xpack.inference.external.azureopenai.AzureOpenAiResponseHandler;
 import org.elasticsearch.xpack.inference.external.http.retry.RequestSender;
 import org.elasticsearch.xpack.inference.external.http.retry.ResponseHandler;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiEmbeddingsResponseEntity;
 import org.elasticsearch.xpack.inference.external.request.azureopenai.AzureOpenAiEmbeddingsRequest;
-import org.elasticsearch.xpack.inference.external.response.openai.OpenAiEmbeddingsResponseEntity;
 import org.elasticsearch.xpack.inference.services.azureopenai.embeddings.AzureOpenAiEmbeddingsModel;
 
 import java.util.List;
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/ElasticInferenceServiceUnifiedCompletionRequestManager.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/ElasticInferenceServiceUnifiedCompletionRequestManager.java
index 226f00f56c7f4..65e7e1704e37b 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/ElasticInferenceServiceUnifiedCompletionRequestManager.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/ElasticInferenceServiceUnifiedCompletionRequestManager.java
@@ -16,8 +16,8 @@
 import org.elasticsearch.xpack.inference.external.elastic.ElasticInferenceServiceUnifiedChatCompletionResponseHandler;
 import org.elasticsearch.xpack.inference.external.http.retry.RequestSender;
 import org.elasticsearch.xpack.inference.external.http.retry.ResponseHandler;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiChatCompletionResponseEntity;
 import org.elasticsearch.xpack.inference.external.request.elastic.ElasticInferenceServiceUnifiedChatCompletionRequest;
-import org.elasticsearch.xpack.inference.external.response.openai.OpenAiChatCompletionResponseEntity;
 import org.elasticsearch.xpack.inference.services.elastic.completion.ElasticInferenceServiceCompletionModel;
 import org.elasticsearch.xpack.inference.telemetry.TraceContext;
 
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiChatCompletionResponseEntity.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiChatCompletionResponseEntity.java
similarity index 52%
rename from x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiChatCompletionResponseEntity.java
rename to x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiChatCompletionResponseEntity.java
index daf4e6578240e..6acc1f22f06ee 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiChatCompletionResponseEntity.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiChatCompletionResponseEntity.java
@@ -5,11 +5,11 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.response.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
-import org.elasticsearch.common.xcontent.LoggingDeprecationHandler;
+import org.elasticsearch.xcontent.ConstructingObjectParser;
+import org.elasticsearch.xcontent.ParseField;
 import org.elasticsearch.xcontent.XContentFactory;
-import org.elasticsearch.xcontent.XContentParser;
 import org.elasticsearch.xcontent.XContentParserConfiguration;
 import org.elasticsearch.xcontent.XContentType;
 import org.elasticsearch.xpack.core.inference.results.ChatCompletionResults;
@@ -19,14 +19,10 @@
 import java.io.IOException;
 import java.util.List;
 
-import static org.elasticsearch.common.xcontent.XContentParserUtils.ensureExpectedToken;
-import static org.elasticsearch.xpack.inference.external.response.XContentUtils.moveToFirstToken;
-import static org.elasticsearch.xpack.inference.external.response.XContentUtils.positionParserAtTokenAfterField;
+import static org.elasticsearch.xcontent.ConstructingObjectParser.constructorArg;
 
 public class OpenAiChatCompletionResponseEntity {
 
-    private static final String FAILED_TO_FIND_FIELD_TEMPLATE = "Failed to find required field [%s] in OpenAI chat completions response";
-
     /**
      * Parses the OpenAI chat completion response.
      * For a request like:
@@ -71,32 +67,51 @@ public class OpenAiChatCompletionResponseEntity {
      */
 
     public static ChatCompletionResults fromResponse(Request request, HttpResult response) throws IOException {
-        var parserConfig = XContentParserConfiguration.EMPTY.withDeprecationHandler(LoggingDeprecationHandler.INSTANCE);
-        try (XContentParser jsonParser = XContentFactory.xContent(XContentType.JSON).createParser(parserConfig, response.body())) {
-            moveToFirstToken(jsonParser);
-
-            XContentParser.Token token = jsonParser.currentToken();
-            ensureExpectedToken(XContentParser.Token.START_OBJECT, token, jsonParser);
-
-            positionParserAtTokenAfterField(jsonParser, "choices", FAILED_TO_FIND_FIELD_TEMPLATE);
+        try (var p = XContentFactory.xContent(XContentType.JSON).createParser(XContentParserConfiguration.EMPTY, response.body())) {
+            return CompletionResult.PARSER.apply(p, null).toChatCompletionResults();
+        }
+    }
 
-            jsonParser.nextToken();
-            ensureExpectedToken(XContentParser.Token.START_OBJECT, jsonParser.currentToken(), jsonParser);
+    public record CompletionResult(List<Choice> choices) {
+        @SuppressWarnings("unchecked")
+        public static final ConstructingObjectParser<CompletionResult, Void> PARSER = new ConstructingObjectParser<>(
+            CompletionResult.class.getSimpleName(),
+            true,
+            args -> new CompletionResult((List<Choice>) args[0])
+        );
 
-            positionParserAtTokenAfterField(jsonParser, "message", FAILED_TO_FIND_FIELD_TEMPLATE);
+        static {
+            PARSER.declareObjectArray(constructorArg(), Choice.PARSER::apply, new ParseField("choices"));
+        }
 
-            token = jsonParser.currentToken();
+        public ChatCompletionResults toChatCompletionResults() {
+            return new ChatCompletionResults(
+                choices.stream().map(choice -> new ChatCompletionResults.Result(choice.message.content)).toList()
+            );
+        }
+    }
 
-            ensureExpectedToken(XContentParser.Token.START_OBJECT, token, jsonParser);
+    public record Choice(Message message) {
+        public static final ConstructingObjectParser<Choice, Void> PARSER = new ConstructingObjectParser<>(
+            Choice.class.getSimpleName(),
+            true,
+            args -> new Choice((Message) args[0])
+        );
 
-            positionParserAtTokenAfterField(jsonParser, "content", FAILED_TO_FIND_FIELD_TEMPLATE);
+        static {
+            PARSER.declareObject(constructorArg(), Message.PARSER::apply, new ParseField("message"));
+        }
+    }
 
-            XContentParser.Token contentToken = jsonParser.currentToken();
-            ensureExpectedToken(XContentParser.Token.VALUE_STRING, contentToken, jsonParser);
-            String content = jsonParser.text();
+    public record Message(String content) {
+        public static final ConstructingObjectParser<Message, Void> PARSER = new ConstructingObjectParser<>(
+            Message.class.getSimpleName(),
+            true,
+            args -> new Message((String) args[0])
+        );
 
-            return new ChatCompletionResults(List.of(new ChatCompletionResults.Result(content)));
+        static {
+            PARSER.declareString(constructorArg(), new ParseField("content"));
         }
     }
-
 }
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequest.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequest.java
similarity index 94%
rename from x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequest.java
rename to x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequest.java
index dfd4330713d61..b177227cc3b28 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequest.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequest.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.apache.http.HttpHeaders;
 import org.apache.http.client.methods.HttpPost;
@@ -21,8 +21,8 @@
 import java.nio.charset.StandardCharsets;
 import java.util.Objects;
 
+import static org.elasticsearch.xpack.inference.external.openai.OpenAiUtils.createOrgHeader;
 import static org.elasticsearch.xpack.inference.external.request.RequestUtils.createAuthBearerHeader;
-import static org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils.createOrgHeader;
 
 public class OpenAiEmbeddingsRequest implements Request {
 
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequestEntity.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequestEntity.java
similarity index 95%
rename from x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequestEntity.java
rename to x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequestEntity.java
index 0e0e92bf8dd61..94d41002fea01 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequestEntity.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequestEntity.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.xcontent.ToXContentObject;
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsResponseEntity.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsResponseEntity.java
new file mode 100644
index 0000000000000..c5d48066f9a83
--- /dev/null
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsResponseEntity.java
@@ -0,0 +1,107 @@
+/*
+ * 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; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+package org.elasticsearch.xpack.inference.external.openai;
+
+import org.elasticsearch.xcontent.ConstructingObjectParser;
+import org.elasticsearch.xcontent.ParseField;
+import org.elasticsearch.xcontent.XContentFactory;
+import org.elasticsearch.xcontent.XContentParserConfiguration;
+import org.elasticsearch.xcontent.XContentType;
+import org.elasticsearch.xpack.core.inference.results.TextEmbeddingFloatResults;
+import org.elasticsearch.xpack.inference.external.http.HttpResult;
+import org.elasticsearch.xpack.inference.external.request.Request;
+
+import java.io.IOException;
+import java.util.List;
+
+import static org.elasticsearch.xcontent.ConstructingObjectParser.constructorArg;
+
+public class OpenAiEmbeddingsResponseEntity {
+    /**
+     * Parses the OpenAI json response.
+     * For a request like:
+     *
+     * <pre>
+     *     <code>
+     *        {
+     *            "inputs": ["hello this is my name", "I wish I was there!"]
+     *        }
+     *     </code>
+     * </pre>
+     *
+     * The response would look like:
+     *
+     * <pre>
+     * <code>
+     * {
+     *  "object": "list",
+     *  "data": [
+     *      {
+     *          "object": "embedding",
+     *          "embedding": [
+     *              -0.009327292,
+     *              .... (1536 floats total for ada-002)
+     *              -0.0028842222,
+     *          ],
+     *          "index": 0
+     *      },
+     *      {
+     *          "object": "embedding",
+     *          "embedding": [ ... ],
+     *          "index": 1
+     *      }
+     *  ],
+     *  "model": "text-embedding-ada-002",
+     *  "usage": {
+     *      "prompt_tokens": 8,
+     *      "total_tokens": 8
+     *  }
+     * }
+     * </code>
+     * </pre>
+     */
+    public static TextEmbeddingFloatResults fromResponse(Request request, HttpResult response) throws IOException {
+        try (var p = XContentFactory.xContent(XContentType.JSON).createParser(XContentParserConfiguration.EMPTY, response.body())) {
+            return EmbeddingFloatResult.PARSER.apply(p, null).toTextEmbeddingFloatResults();
+        }
+    }
+
+    public record EmbeddingFloatResult(List<EmbeddingFloatResultEntry> embeddingResults) {
+        @SuppressWarnings("unchecked")
+        public static final ConstructingObjectParser<EmbeddingFloatResult, Void> PARSER = new ConstructingObjectParser<>(
+            EmbeddingFloatResult.class.getSimpleName(),
+            true,
+            args -> new EmbeddingFloatResult((List<EmbeddingFloatResultEntry>) args[0])
+        );
+
+        static {
+            PARSER.declareObjectArray(constructorArg(), EmbeddingFloatResultEntry.PARSER::apply, new ParseField("data"));
+        }
+
+        public TextEmbeddingFloatResults toTextEmbeddingFloatResults() {
+            return new TextEmbeddingFloatResults(
+                embeddingResults.stream().map(entry -> TextEmbeddingFloatResults.Embedding.of(entry.embedding)).toList()
+            );
+        }
+    }
+
+    public record EmbeddingFloatResultEntry(List<Float> embedding) {
+        @SuppressWarnings("unchecked")
+        public static final ConstructingObjectParser<EmbeddingFloatResultEntry, Void> PARSER = new ConstructingObjectParser<>(
+            EmbeddingFloatResultEntry.class.getSimpleName(),
+            true,
+            args -> new EmbeddingFloatResultEntry((List<Float>) args[0])
+        );
+
+        static {
+            PARSER.declareFloatArray(constructorArg(), new ParseField("embedding"));
+        }
+    }
+
+    private OpenAiEmbeddingsResponseEntity() {}
+}
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiRequest.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiRequest.java
similarity index 84%
rename from x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiRequest.java
rename to x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiRequest.java
index 7a630108cfcdf..71341a7d3e5d9 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiRequest.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiRequest.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.elasticsearch.xpack.inference.external.request.Request;
 
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequest.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequest.java
similarity index 94%
rename from x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequest.java
rename to x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequest.java
index 84f90e9027323..5e5934b051598 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequest.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequest.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.apache.http.HttpHeaders;
 import org.apache.http.client.methods.HttpPost;
@@ -21,8 +21,8 @@
 import java.nio.charset.StandardCharsets;
 import java.util.Objects;
 
+import static org.elasticsearch.xpack.inference.external.openai.OpenAiUtils.createOrgHeader;
 import static org.elasticsearch.xpack.inference.external.request.RequestUtils.createAuthBearerHeader;
-import static org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils.createOrgHeader;
 
 public class OpenAiUnifiedChatCompletionRequest implements Request {
 
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequestEntity.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequestEntity.java
similarity index 96%
rename from x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequestEntity.java
rename to x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequestEntity.java
index b80100c9e2f79..41900a96d9e7a 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequestEntity.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequestEntity.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.elasticsearch.common.Strings;
 import org.elasticsearch.xcontent.ToXContentObject;
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUtils.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUtils.java
similarity index 92%
rename from x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUtils.java
rename to x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUtils.java
index 1199f8a4f0230..c7fb0102146a7 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUtils.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUtils.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.apache.http.Header;
 import org.apache.http.message.BasicHeader;
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/azureaistudio/AzureAiStudioChatCompletionResponseEntity.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/azureaistudio/AzureAiStudioChatCompletionResponseEntity.java
index abf2c4877307c..d4fc20997596f 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/azureaistudio/AzureAiStudioChatCompletionResponseEntity.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/azureaistudio/AzureAiStudioChatCompletionResponseEntity.java
@@ -15,10 +15,10 @@
 import org.elasticsearch.xcontent.XContentType;
 import org.elasticsearch.xpack.core.inference.results.ChatCompletionResults;
 import org.elasticsearch.xpack.inference.external.http.HttpResult;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiChatCompletionResponseEntity;
 import org.elasticsearch.xpack.inference.external.request.Request;
 import org.elasticsearch.xpack.inference.external.request.azureaistudio.AzureAiStudioChatCompletionRequest;
 import org.elasticsearch.xpack.inference.external.response.BaseResponseEntity;
-import org.elasticsearch.xpack.inference.external.response.openai.OpenAiChatCompletionResponseEntity;
 
 import java.io.IOException;
 import java.util.List;
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/azureaistudio/AzureAiStudioEmbeddingsResponseEntity.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/azureaistudio/AzureAiStudioEmbeddingsResponseEntity.java
index 3fce1ec7920f5..f693de54164ad 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/azureaistudio/AzureAiStudioEmbeddingsResponseEntity.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/azureaistudio/AzureAiStudioEmbeddingsResponseEntity.java
@@ -9,9 +9,9 @@
 
 import org.elasticsearch.inference.InferenceServiceResults;
 import org.elasticsearch.xpack.inference.external.http.HttpResult;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiEmbeddingsResponseEntity;
 import org.elasticsearch.xpack.inference.external.request.Request;
 import org.elasticsearch.xpack.inference.external.response.BaseResponseEntity;
-import org.elasticsearch.xpack.inference.external.response.openai.OpenAiEmbeddingsResponseEntity;
 
 import java.io.IOException;
 
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/mistral/MistralEmbeddingsResponseEntity.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/mistral/MistralEmbeddingsResponseEntity.java
index 01de92c20a3f1..d703091d3b370 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/mistral/MistralEmbeddingsResponseEntity.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/mistral/MistralEmbeddingsResponseEntity.java
@@ -9,9 +9,9 @@
 
 import org.elasticsearch.inference.InferenceServiceResults;
 import org.elasticsearch.xpack.inference.external.http.HttpResult;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiEmbeddingsResponseEntity;
 import org.elasticsearch.xpack.inference.external.request.Request;
 import org.elasticsearch.xpack.inference.external.response.BaseResponseEntity;
-import org.elasticsearch.xpack.inference.external.response.openai.OpenAiEmbeddingsResponseEntity;
 
 import java.io.IOException;
 
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiEmbeddingsResponseEntity.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiEmbeddingsResponseEntity.java
deleted file mode 100644
index bda5741af2038..0000000000000
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiEmbeddingsResponseEntity.java
+++ /dev/null
@@ -1,110 +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; you may not use this file except in compliance with the Elastic License
- * 2.0.
- *
- * this file was contributed to by a generative AI
- */
-
-package org.elasticsearch.xpack.inference.external.response.openai;
-
-import org.elasticsearch.common.xcontent.LoggingDeprecationHandler;
-import org.elasticsearch.xcontent.XContentFactory;
-import org.elasticsearch.xcontent.XContentParser;
-import org.elasticsearch.xcontent.XContentParserConfiguration;
-import org.elasticsearch.xcontent.XContentType;
-import org.elasticsearch.xpack.core.inference.results.TextEmbeddingFloatResults;
-import org.elasticsearch.xpack.inference.external.http.HttpResult;
-import org.elasticsearch.xpack.inference.external.request.Request;
-import org.elasticsearch.xpack.inference.external.response.XContentUtils;
-
-import java.io.IOException;
-import java.util.List;
-
-import static org.elasticsearch.common.xcontent.XContentParserUtils.ensureExpectedToken;
-import static org.elasticsearch.common.xcontent.XContentParserUtils.parseList;
-import static org.elasticsearch.xpack.inference.external.response.XContentUtils.consumeUntilObjectEnd;
-import static org.elasticsearch.xpack.inference.external.response.XContentUtils.moveToFirstToken;
-import static org.elasticsearch.xpack.inference.external.response.XContentUtils.positionParserAtTokenAfterField;
-
-public class OpenAiEmbeddingsResponseEntity {
-    private static final String FAILED_TO_FIND_FIELD_TEMPLATE = "Failed to find required field [%s] in OpenAI embeddings response";
-
-    /**
-     * Parses the OpenAI json response.
-     * For a request like:
-     *
-     * <pre>
-     *     <code>
-     *        {
-     *            "inputs": ["hello this is my name", "I wish I was there!"]
-     *        }
-     *     </code>
-     * </pre>
-     *
-     * The response would look like:
-     *
-     * <pre>
-     * <code>
-     * {
-     *  "object": "list",
-     *  "data": [
-     *      {
-     *          "object": "embedding",
-     *          "embedding": [
-     *              -0.009327292,
-     *              .... (1536 floats total for ada-002)
-     *              -0.0028842222,
-     *          ],
-     *          "index": 0
-     *      },
-     *      {
-     *          "object": "embedding",
-     *          "embedding": [ ... ],
-     *          "index": 1
-     *      }
-     *  ],
-     *  "model": "text-embedding-ada-002",
-     *  "usage": {
-     *      "prompt_tokens": 8,
-     *      "total_tokens": 8
-     *  }
-     * }
-     * </code>
-     * </pre>
-     */
-    public static TextEmbeddingFloatResults fromResponse(Request request, HttpResult response) throws IOException {
-        var parserConfig = XContentParserConfiguration.EMPTY.withDeprecationHandler(LoggingDeprecationHandler.INSTANCE);
-
-        try (XContentParser jsonParser = XContentFactory.xContent(XContentType.JSON).createParser(parserConfig, response.body())) {
-            moveToFirstToken(jsonParser);
-
-            XContentParser.Token token = jsonParser.currentToken();
-            ensureExpectedToken(XContentParser.Token.START_OBJECT, token, jsonParser);
-
-            positionParserAtTokenAfterField(jsonParser, "data", FAILED_TO_FIND_FIELD_TEMPLATE);
-
-            List<TextEmbeddingFloatResults.Embedding> embeddingList = parseList(
-                jsonParser,
-                OpenAiEmbeddingsResponseEntity::parseEmbeddingObject
-            );
-
-            return new TextEmbeddingFloatResults(embeddingList);
-        }
-    }
-
-    private static TextEmbeddingFloatResults.Embedding parseEmbeddingObject(XContentParser parser) throws IOException {
-        ensureExpectedToken(XContentParser.Token.START_OBJECT, parser.currentToken(), parser);
-
-        positionParserAtTokenAfterField(parser, "embedding", FAILED_TO_FIND_FIELD_TEMPLATE);
-
-        List<Float> embeddingValuesList = parseList(parser, XContentUtils::parseFloat);
-        // parse and discard the rest of the object
-        consumeUntilObjectEnd(parser);
-
-        return TextEmbeddingFloatResults.Embedding.of(embeddingValuesList);
-    }
-
-    private OpenAiEmbeddingsResponseEntity() {}
-}
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 8df3dc01b4fbe..1b29c0c97e2b0 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
@@ -38,9 +38,9 @@
 import org.elasticsearch.xpack.inference.external.http.sender.HttpRequestSender;
 import org.elasticsearch.xpack.inference.external.http.sender.InferenceInputs;
 import org.elasticsearch.xpack.inference.external.http.sender.UnifiedChatInput;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiChatCompletionResponseEntity;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiUnifiedChatCompletionRequest;
 import org.elasticsearch.xpack.inference.external.openai.OpenAiUnifiedChatCompletionResponseHandler;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiUnifiedChatCompletionRequest;
-import org.elasticsearch.xpack.inference.external.response.openai.OpenAiChatCompletionResponseEntity;
 import org.elasticsearch.xpack.inference.services.ConfigurationParseContext;
 import org.elasticsearch.xpack.inference.services.SenderService;
 import org.elasticsearch.xpack.inference.services.ServiceComponents;
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/completion/OpenAiChatCompletionModel.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/completion/OpenAiChatCompletionModel.java
index 9b1d27d569cc8..8427519530c44 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/completion/OpenAiChatCompletionModel.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/completion/OpenAiChatCompletionModel.java
@@ -15,7 +15,7 @@
 import org.elasticsearch.inference.UnifiedCompletionRequest;
 import org.elasticsearch.xpack.inference.external.action.ExecutableAction;
 import org.elasticsearch.xpack.inference.external.action.openai.OpenAiActionVisitor;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiUtils;
 import org.elasticsearch.xpack.inference.services.ConfigurationParseContext;
 import org.elasticsearch.xpack.inference.services.openai.OpenAiModel;
 import org.elasticsearch.xpack.inference.services.openai.OpenAiService;
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/embeddings/OpenAiEmbeddingsModel.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/embeddings/OpenAiEmbeddingsModel.java
index e1265fe12b1fa..588b12efe5c8e 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/embeddings/OpenAiEmbeddingsModel.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/openai/embeddings/OpenAiEmbeddingsModel.java
@@ -15,7 +15,7 @@
 import org.elasticsearch.inference.TaskType;
 import org.elasticsearch.xpack.inference.external.action.ExecutableAction;
 import org.elasticsearch.xpack.inference.external.action.openai.OpenAiActionVisitor;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiUtils;
 import org.elasticsearch.xpack.inference.services.ConfigurationParseContext;
 import org.elasticsearch.xpack.inference.services.openai.OpenAiModel;
 import org.elasticsearch.xpack.inference.services.openai.OpenAiService;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/azureopenai/AzureOpenAiActionCreatorTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/azureopenai/AzureOpenAiActionCreatorTests.java
index df124c35a4689..593bac8209333 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/azureopenai/AzureOpenAiActionCreatorTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/azureopenai/AzureOpenAiActionCreatorTests.java
@@ -219,7 +219,7 @@ public void testCreate_AzureOpenAiEmbeddingsModel_FailsFromInvalidResponseFormat
             PlainActionFuture<InferenceServiceResults> listener = new PlainActionFuture<>();
             action.execute(new DocumentsOnlyInput(List.of("abc")), InferenceAction.Request.DEFAULT_TIMEOUT, listener);
 
-            var failureCauseMessage = "Failed to find required field [data] in OpenAI embeddings response";
+            var failureCauseMessage = "Required [data]";
             var thrownException = expectThrows(ElasticsearchStatusException.class, () -> listener.actionGet(TIMEOUT));
             assertThat(
                 thrownException.getMessage(),
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiActionCreatorTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiActionCreatorTests.java
index 2b2c9d0c3260d..49f401a7e9681 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiActionCreatorTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiActionCreatorTests.java
@@ -40,7 +40,7 @@
 import static org.elasticsearch.xpack.inference.external.http.Utils.getUrl;
 import static org.elasticsearch.xpack.inference.external.http.retry.RetrySettingsTests.buildSettingsWithRetryFields;
 import static org.elasticsearch.xpack.inference.external.http.sender.HttpRequestSenderTests.createSender;
-import static org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils.ORGANIZATION_HEADER;
+import static org.elasticsearch.xpack.inference.external.openai.OpenAiUtils.ORGANIZATION_HEADER;
 import static org.elasticsearch.xpack.inference.results.ChatCompletionResultsTests.buildExpectationCompletion;
 import static org.elasticsearch.xpack.inference.results.TextEmbeddingResultsTests.buildExpectationFloat;
 import static org.elasticsearch.xpack.inference.services.ServiceComponentsTests.createWithEmptySettings;
@@ -273,7 +273,7 @@ public void testCreate_OpenAiEmbeddingsModel_FailsFromInvalidResponseFormat() th
             PlainActionFuture<InferenceServiceResults> listener = new PlainActionFuture<>();
             action.execute(new DocumentsOnlyInput(List.of("abc")), InferenceAction.Request.DEFAULT_TIMEOUT, listener);
 
-            var failureCauseMessage = "Failed to find required field [data] in OpenAI embeddings response";
+            var failureCauseMessage = "Required [data]";
             var thrownException = expectThrows(ElasticsearchStatusException.class, () -> listener.actionGet(TIMEOUT));
             assertThat(
                 thrownException.getMessage(),
@@ -533,7 +533,7 @@ public void testCreate_OpenAiChatCompletionModel_FailsFromInvalidResponseFormat(
             PlainActionFuture<InferenceServiceResults> listener = new PlainActionFuture<>();
             action.execute(new ChatCompletionInput(List.of("abc")), InferenceAction.Request.DEFAULT_TIMEOUT, listener);
 
-            var failureCauseMessage = "Failed to find required field [choices] in OpenAI chat completions response";
+            var failureCauseMessage = "Required [choices]";
             var thrownException = expectThrows(ElasticsearchStatusException.class, () -> listener.actionGet(TIMEOUT));
             assertThat(
                 thrownException.getMessage(),
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiChatCompletionActionTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiChatCompletionActionTests.java
index d29e19a7902ba..c5aae64238888 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiChatCompletionActionTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiChatCompletionActionTests.java
@@ -33,7 +33,7 @@
 import org.elasticsearch.xpack.inference.external.http.sender.HttpRequestSenderTests;
 import org.elasticsearch.xpack.inference.external.http.sender.Sender;
 import org.elasticsearch.xpack.inference.external.http.sender.UnifiedChatInput;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiUnifiedChatCompletionRequest;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiUnifiedChatCompletionRequest;
 import org.elasticsearch.xpack.inference.logging.ThrottlerManager;
 import org.junit.After;
 import org.junit.Before;
@@ -51,7 +51,7 @@
 import static org.elasticsearch.xpack.inference.external.http.Utils.entityAsMap;
 import static org.elasticsearch.xpack.inference.external.http.Utils.getUrl;
 import static org.elasticsearch.xpack.inference.external.http.sender.HttpRequestSenderTests.createSender;
-import static org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils.ORGANIZATION_HEADER;
+import static org.elasticsearch.xpack.inference.external.openai.OpenAiUtils.ORGANIZATION_HEADER;
 import static org.elasticsearch.xpack.inference.results.ChatCompletionResultsTests.buildExpectationCompletion;
 import static org.elasticsearch.xpack.inference.services.ServiceComponentsTests.createWithEmptySettings;
 import static org.elasticsearch.xpack.inference.services.openai.completion.OpenAiChatCompletionModelTests.createCompletionModel;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiEmbeddingsActionTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiEmbeddingsActionTests.java
index 799804482e2f6..5d732a4416a90 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiEmbeddingsActionTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/action/openai/OpenAiEmbeddingsActionTests.java
@@ -29,7 +29,7 @@
 import org.elasticsearch.xpack.inference.external.http.sender.HttpRequestSender;
 import org.elasticsearch.xpack.inference.external.http.sender.Sender;
 import org.elasticsearch.xpack.inference.external.http.sender.TruncatingRequestManager;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiEmbeddingsRequest;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiEmbeddingsRequest;
 import org.elasticsearch.xpack.inference.logging.ThrottlerManager;
 import org.elasticsearch.xpack.inference.services.ServiceComponentsTests;
 import org.junit.After;
@@ -45,7 +45,7 @@
 import static org.elasticsearch.xpack.inference.external.action.openai.OpenAiActionCreator.EMBEDDINGS_HANDLER;
 import static org.elasticsearch.xpack.inference.external.http.Utils.entityAsMap;
 import static org.elasticsearch.xpack.inference.external.http.Utils.getUrl;
-import static org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils.ORGANIZATION_HEADER;
+import static org.elasticsearch.xpack.inference.external.openai.OpenAiUtils.ORGANIZATION_HEADER;
 import static org.elasticsearch.xpack.inference.results.TextEmbeddingResultsTests.buildExpectationFloat;
 import static org.elasticsearch.xpack.inference.services.openai.embeddings.OpenAiEmbeddingsModelTests.createModel;
 import static org.hamcrest.Matchers.containsString;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/HttpRequestSenderTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/HttpRequestSenderTests.java
index 9d7bcab3d9b51..5a8c66da1dfa3 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/HttpRequestSenderTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/HttpRequestSenderTests.java
@@ -48,7 +48,7 @@
 import static org.elasticsearch.xpack.inference.Utils.mockClusterServiceEmpty;
 import static org.elasticsearch.xpack.inference.external.http.Utils.entityAsMap;
 import static org.elasticsearch.xpack.inference.external.http.Utils.getUrl;
-import static org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils.ORGANIZATION_HEADER;
+import static org.elasticsearch.xpack.inference.external.openai.OpenAiUtils.ORGANIZATION_HEADER;
 import static org.elasticsearch.xpack.inference.results.TextEmbeddingResultsTests.buildExpectationFloat;
 import static org.elasticsearch.xpack.inference.services.elastic.ElasticInferenceService.ELASTIC_INFERENCE_SERVICE_IDENTIFIER;
 import static org.hamcrest.Matchers.equalTo;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/OpenAiEmbeddingsRequestManagerTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/OpenAiEmbeddingsRequestManagerTests.java
index b4dd269d872ea..c04139b38c5dd 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/OpenAiEmbeddingsRequestManagerTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/OpenAiEmbeddingsRequestManagerTests.java
@@ -10,7 +10,7 @@
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.threadpool.ThreadPool;
 import org.elasticsearch.xpack.inference.common.TruncatorTests;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiEmbeddingsRequest;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiEmbeddingsRequest;
 
 import static org.elasticsearch.xpack.inference.external.action.openai.OpenAiActionCreator.EMBEDDINGS_HANDLER;
 import static org.elasticsearch.xpack.inference.services.openai.embeddings.OpenAiEmbeddingsModelTests.createModel;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiChatCompletionResponseEntityTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiChatCompletionResponseEntityTests.java
similarity index 87%
rename from x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiChatCompletionResponseEntityTests.java
rename to x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiChatCompletionResponseEntityTests.java
index 5604d6573144e..9925ec13bb6ac 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiChatCompletionResponseEntityTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiChatCompletionResponseEntityTests.java
@@ -5,11 +5,11 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.response.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.apache.http.HttpResponse;
-import org.elasticsearch.common.ParsingException;
 import org.elasticsearch.test.ESTestCase;
+import org.elasticsearch.xcontent.XContentParseException;
 import org.elasticsearch.xpack.core.inference.results.ChatCompletionResults;
 import org.elasticsearch.xpack.inference.external.http.HttpResult;
 import org.elasticsearch.xpack.inference.external.request.Request;
@@ -17,6 +17,7 @@
 import java.io.IOException;
 import java.nio.charset.StandardCharsets;
 
+import static org.hamcrest.Matchers.containsString;
 import static org.hamcrest.Matchers.is;
 import static org.mockito.Mockito.mock;
 
@@ -86,14 +87,14 @@ public void testFromResponse_FailsWhenChoicesFieldIsNotPresent() {
             """;
 
         var thrownException = expectThrows(
-            IllegalStateException.class,
+            IllegalArgumentException.class,
             () -> OpenAiChatCompletionResponseEntity.fromResponse(
                 mock(Request.class),
                 new HttpResult(mock(HttpResponse.class), responseJson.getBytes(StandardCharsets.UTF_8))
             )
         );
 
-        assertThat(thrownException.getMessage(), is("Failed to find required field [choices] in OpenAI chat completions response"));
+        assertThat(thrownException.getMessage(), is("Required [choices]"));
     }
 
     public void testFromResponse_FailsWhenChoicesFieldNotAnArray() {
@@ -124,17 +125,14 @@ public void testFromResponse_FailsWhenChoicesFieldNotAnArray() {
             """;
 
         var thrownException = expectThrows(
-            ParsingException.class,
+            XContentParseException.class,
             () -> OpenAiChatCompletionResponseEntity.fromResponse(
                 mock(Request.class),
                 new HttpResult(mock(HttpResponse.class), responseJson.getBytes(StandardCharsets.UTF_8))
             )
         );
 
-        assertThat(
-            thrownException.getMessage(),
-            is("Failed to parse object: expecting token of type [START_OBJECT] but found [FIELD_NAME]")
-        );
+        assertThat(thrownException.getMessage(), containsString("[CompletionResult] failed to parse field [choices]"));
     }
 
     public void testFromResponse_FailsWhenMessageDoesNotExist() {
@@ -165,14 +163,14 @@ public void testFromResponse_FailsWhenMessageDoesNotExist() {
             """;
 
         var thrownException = expectThrows(
-            IllegalStateException.class,
+            XContentParseException.class,
             () -> OpenAiChatCompletionResponseEntity.fromResponse(
                 mock(Request.class),
                 new HttpResult(mock(HttpResponse.class), responseJson.getBytes(StandardCharsets.UTF_8))
             )
         );
 
-        assertThat(thrownException.getMessage(), is("Failed to find required field [message] in OpenAI chat completions response"));
+        assertThat(thrownException.getMessage(), containsString("[CompletionResult] failed to parse field [choices]"));
     }
 
     public void testFromResponse_FailsWhenMessageValueIsAString() {
@@ -200,16 +198,13 @@ public void testFromResponse_FailsWhenMessageValueIsAString() {
             """;
 
         var thrownException = expectThrows(
-            ParsingException.class,
+            XContentParseException.class,
             () -> OpenAiChatCompletionResponseEntity.fromResponse(
                 mock(Request.class),
                 new HttpResult(mock(HttpResponse.class), responseJson.getBytes(StandardCharsets.UTF_8))
             )
         );
 
-        assertThat(
-            thrownException.getMessage(),
-            is("Failed to parse object: expecting token of type [START_OBJECT] but found [VALUE_STRING]")
-        );
+        assertThat(thrownException.getMessage(), containsString("[CompletionResult] failed to parse field [choices]"));
     }
 }
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequestEntityTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequestEntityTests.java
similarity index 97%
rename from x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequestEntityTests.java
rename to x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequestEntityTests.java
index ea76a87f78f62..a7b420027a102 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequestEntityTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequestEntityTests.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.elasticsearch.common.Strings;
 import org.elasticsearch.test.ESTestCase;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequestTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequestTests.java
similarity index 97%
rename from x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequestTests.java
rename to x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequestTests.java
index e80cdc848a1e4..37069f0cc7e4c 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiEmbeddingsRequestTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsRequestTests.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.apache.http.HttpHeaders;
 import org.apache.http.client.methods.HttpPost;
@@ -21,7 +21,7 @@
 import java.util.List;
 
 import static org.elasticsearch.xpack.inference.external.http.Utils.entityAsMap;
-import static org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils.ORGANIZATION_HEADER;
+import static org.elasticsearch.xpack.inference.external.openai.OpenAiUtils.ORGANIZATION_HEADER;
 import static org.elasticsearch.xpack.inference.services.openai.embeddings.OpenAiEmbeddingsModel.buildDefaultUri;
 import static org.hamcrest.Matchers.aMapWithSize;
 import static org.hamcrest.Matchers.instanceOf;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiEmbeddingsResponseEntityTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsResponseEntityTests.java
similarity index 91%
rename from x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiEmbeddingsResponseEntityTests.java
rename to x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsResponseEntityTests.java
index b5300f852e726..19e51fbb69647 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/response/openai/OpenAiEmbeddingsResponseEntityTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiEmbeddingsResponseEntityTests.java
@@ -5,11 +5,11 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.response.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.apache.http.HttpResponse;
-import org.elasticsearch.common.ParsingException;
 import org.elasticsearch.test.ESTestCase;
+import org.elasticsearch.xcontent.XContentParseException;
 import org.elasticsearch.xpack.core.inference.results.TextEmbeddingFloatResults;
 import org.elasticsearch.xpack.inference.external.http.HttpResult;
 import org.elasticsearch.xpack.inference.external.request.Request;
@@ -18,6 +18,7 @@
 import java.nio.charset.StandardCharsets;
 import java.util.List;
 
+import static org.hamcrest.Matchers.containsString;
 import static org.hamcrest.Matchers.is;
 import static org.mockito.Mockito.mock;
 
@@ -124,14 +125,14 @@ public void testFromResponse_FailsWhenDataFieldIsNotPresent() {
             """;
 
         var thrownException = expectThrows(
-            IllegalStateException.class,
+            IllegalArgumentException.class,
             () -> OpenAiEmbeddingsResponseEntity.fromResponse(
                 mock(Request.class),
                 new HttpResult(mock(HttpResponse.class), responseJson.getBytes(StandardCharsets.UTF_8))
             )
         );
 
-        assertThat(thrownException.getMessage(), is("Failed to find required field [data] in OpenAI embeddings response"));
+        assertThat(thrownException.getMessage(), is("Required [data]"));
     }
 
     public void testFromResponse_FailsWhenDataFieldNotAnArray() {
@@ -157,17 +158,14 @@ public void testFromResponse_FailsWhenDataFieldNotAnArray() {
             """;
 
         var thrownException = expectThrows(
-            ParsingException.class,
+            XContentParseException.class,
             () -> OpenAiEmbeddingsResponseEntity.fromResponse(
                 mock(Request.class),
                 new HttpResult(mock(HttpResponse.class), responseJson.getBytes(StandardCharsets.UTF_8))
             )
         );
 
-        assertThat(
-            thrownException.getMessage(),
-            is("Failed to parse object: expecting token of type [START_ARRAY] but found [START_OBJECT]")
-        );
+        assertThat(thrownException.getMessage(), containsString("[EmbeddingFloatResult] failed to parse field [data]"));
     }
 
     public void testFromResponse_FailsWhenEmbeddingsDoesNotExist() {
@@ -193,14 +191,14 @@ public void testFromResponse_FailsWhenEmbeddingsDoesNotExist() {
             """;
 
         var thrownException = expectThrows(
-            IllegalStateException.class,
+            XContentParseException.class,
             () -> OpenAiEmbeddingsResponseEntity.fromResponse(
                 mock(Request.class),
                 new HttpResult(mock(HttpResponse.class), responseJson.getBytes(StandardCharsets.UTF_8))
             )
         );
 
-        assertThat(thrownException.getMessage(), is("Failed to find required field [embedding] in OpenAI embeddings response"));
+        assertThat(thrownException.getMessage(), containsString("[EmbeddingFloatResult] failed to parse field [data]"));
     }
 
     public void testFromResponse_FailsWhenEmbeddingValueIsAString() {
@@ -225,17 +223,14 @@ public void testFromResponse_FailsWhenEmbeddingValueIsAString() {
             """;
 
         var thrownException = expectThrows(
-            ParsingException.class,
+            XContentParseException.class,
             () -> OpenAiEmbeddingsResponseEntity.fromResponse(
                 mock(Request.class),
                 new HttpResult(mock(HttpResponse.class), responseJson.getBytes(StandardCharsets.UTF_8))
             )
         );
 
-        assertThat(
-            thrownException.getMessage(),
-            is("Failed to parse object: expecting token of type [VALUE_NUMBER] but found [VALUE_STRING]")
-        );
+        assertThat(thrownException.getMessage(), containsString("[EmbeddingFloatResult] failed to parse field [data]"));
     }
 
     public void testFromResponse_SucceedsWhenEmbeddingValueIsInt() throws IOException {
@@ -318,17 +313,14 @@ public void testFromResponse_FailsWhenEmbeddingValueIsAnObject() {
             """;
 
         var thrownException = expectThrows(
-            ParsingException.class,
+            XContentParseException.class,
             () -> OpenAiEmbeddingsResponseEntity.fromResponse(
                 mock(Request.class),
                 new HttpResult(mock(HttpResponse.class), responseJson.getBytes(StandardCharsets.UTF_8))
             )
         );
 
-        assertThat(
-            thrownException.getMessage(),
-            is("Failed to parse object: expecting token of type [VALUE_NUMBER] but found [START_OBJECT]")
-        );
+        assertThat(thrownException.getMessage(), containsString("[EmbeddingFloatResult] failed to parse field [data]"));
     }
 
     public void testFieldsInDifferentOrderServer() throws IOException {
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequestEntityTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequestEntityTests.java
similarity index 97%
rename from x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequestEntityTests.java
rename to x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequestEntityTests.java
index ee0cdad5d552e..bc7c62bb85b11 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequestEntityTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequestEntityTests.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.elasticsearch.common.Strings;
 import org.elasticsearch.inference.UnifiedCompletionRequest;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequestTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequestTests.java
similarity index 97%
rename from x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequestTests.java
rename to x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequestTests.java
index 7b15ab5abed88..e583dbb85583b 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/openai/OpenAiUnifiedChatCompletionRequestTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/openai/OpenAiUnifiedChatCompletionRequestTests.java
@@ -5,7 +5,7 @@
  * 2.0.
  */
 
-package org.elasticsearch.xpack.inference.external.request.openai;
+package org.elasticsearch.xpack.inference.external.openai;
 
 import org.apache.http.HttpHeaders;
 import org.apache.http.client.methods.HttpPost;
@@ -21,7 +21,7 @@
 import java.util.Map;
 
 import static org.elasticsearch.xpack.inference.external.http.Utils.entityAsMap;
-import static org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils.ORGANIZATION_HEADER;
+import static org.elasticsearch.xpack.inference.external.openai.OpenAiUtils.ORGANIZATION_HEADER;
 import static org.elasticsearch.xpack.inference.services.openai.completion.OpenAiChatCompletionModel.buildDefaultUri;
 import static org.hamcrest.Matchers.aMapWithSize;
 import static org.hamcrest.Matchers.instanceOf;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/elastic/ElasticInferenceServiceUnifiedChatCompletionRequestEntityTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/elastic/ElasticInferenceServiceUnifiedChatCompletionRequestEntityTests.java
index 068e84fae35df..ed88a4796c746 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/elastic/ElasticInferenceServiceUnifiedChatCompletionRequestEntityTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/request/elastic/ElasticInferenceServiceUnifiedChatCompletionRequestEntityTests.java
@@ -14,7 +14,7 @@
 import org.elasticsearch.xcontent.XContentBuilder;
 import org.elasticsearch.xcontent.json.JsonXContent;
 import org.elasticsearch.xpack.inference.external.http.sender.UnifiedChatInput;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiUnifiedChatCompletionRequestEntity;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiUnifiedChatCompletionRequestEntity;
 import org.elasticsearch.xpack.inference.services.openai.completion.OpenAiChatCompletionModel;
 
 import java.io.IOException;
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/unified/UnifiedChatCompletionRequestEntityTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/unified/UnifiedChatCompletionRequestEntityTests.java
index 024b7aa532d90..fe92ee725dd89 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/unified/UnifiedChatCompletionRequestEntityTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/unified/UnifiedChatCompletionRequestEntityTests.java
@@ -15,7 +15,7 @@
 import org.elasticsearch.xcontent.XContentBuilder;
 import org.elasticsearch.xcontent.json.JsonXContent;
 import org.elasticsearch.xpack.inference.external.http.sender.UnifiedChatInput;
-import org.elasticsearch.xpack.inference.external.request.openai.OpenAiUnifiedChatCompletionRequestEntity;
+import org.elasticsearch.xpack.inference.external.openai.OpenAiUnifiedChatCompletionRequestEntity;
 import org.elasticsearch.xpack.inference.services.openai.completion.OpenAiChatCompletionModel;
 
 import java.io.IOException;
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 4aff8732ed9ab..a522b83a4a67b 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
@@ -80,7 +80,7 @@
 import static org.elasticsearch.xpack.inference.chunking.ChunkingSettingsTests.createRandomChunkingSettingsMap;
 import static org.elasticsearch.xpack.inference.external.http.Utils.entityAsMap;
 import static org.elasticsearch.xpack.inference.external.http.Utils.getUrl;
-import static org.elasticsearch.xpack.inference.external.request.openai.OpenAiUtils.ORGANIZATION_HEADER;
+import static org.elasticsearch.xpack.inference.external.openai.OpenAiUtils.ORGANIZATION_HEADER;
 import static org.elasticsearch.xpack.inference.results.TextEmbeddingResultsTests.buildExpectationFloat;
 import static org.elasticsearch.xpack.inference.services.ServiceComponentsTests.createWithEmptySettings;
 import static org.elasticsearch.xpack.inference.services.openai.completion.OpenAiChatCompletionModelTests.createCompletionModel;