diff --git a/client/src/api/schema/schema.ts b/client/src/api/schema/schema.ts
index 0659ad0d08d9..0e1e42008a65 100644
--- a/client/src/api/schema/schema.ts
+++ b/client/src/api/schema/schema.ts
@@ -127,7 +127,7 @@ export interface paths {
     "/api/datasets/{dataset_id}": {
         /**
          * Displays information about and/or content of a dataset.
-         * @description **Note**: Due to the multipurpose nature of this endpoint, which can receive a wild variety of parameters
+         * @description **Note**: Due to the multipurpose nature of this endpoint, which can receive a wide variety of parameters
          * and return different kinds of responses, the documentation here will be limited.
          * To get more information please check the source code.
          */
@@ -14366,18 +14366,22 @@ export interface operations {
     show_api_datasets__dataset_id__get: {
         /**
          * Displays information about and/or content of a dataset.
-         * @description **Note**: Due to the multipurpose nature of this endpoint, which can receive a wild variety of parameters
+         * @description **Note**: Due to the multipurpose nature of this endpoint, which can receive a wide variety of parameters
          * and return different kinds of responses, the documentation here will be limited.
          * To get more information please check the source code.
          */
         parameters: {
             /** @description The type of information about the dataset to be requested. */
             /** @description The type of information about the dataset to be requested. Each of these values may require additional parameters in the request and may return different responses. */
+            /** @description Maximum number of items to return. Currently only applies to `data_type=raw_data` requests */
+            /** @description Starts at the beginning skip the first ( offset - 1 ) items and begin returning at the Nth item. Currently only applies to `data_type=raw_data` requests */
             /** @description View to be passed to the serializer */
             /** @description Comma-separated list of keys to be passed to the serializer */
             query?: {
                 hda_ldda?: components["schemas"]["DatasetSourceType"];
                 data_type?: components["schemas"]["RequestDataType"] | null;
+                limit?: number | null;
+                offset?: number | null;
                 view?: string | null;
                 keys?: string | null;
             };
diff --git a/lib/galaxy/datatypes/dataproviders/base.py b/lib/galaxy/datatypes/dataproviders/base.py
index c1239f86b9ff..2f9445615d9e 100644
--- a/lib/galaxy/datatypes/dataproviders/base.py
+++ b/lib/galaxy/datatypes/dataproviders/base.py
@@ -12,6 +12,7 @@
 from collections import deque
 from typing import Dict
 
+from galaxy.exceptions import RequestParameterInvalidException
 from . import exceptions
 
 log = logging.getLogger(__name__)
@@ -36,6 +37,7 @@ def stop( self ): self.endpoint = source.tell(); raise StopIteration()
         Building a giant list by sweeping all possible dprov classes doesn't make sense
     For now - I'm burying them in the class __init__s - but I don't like that
 """
+MAX_LIMIT = 10000
 
 
 # ----------------------------------------------------------------------------- base classes
@@ -233,21 +235,20 @@ class LimitedOffsetDataProvider(FilteredDataProvider):
     settings = {"limit": "int", "offset": "int"}
 
     # TODO: may want to squash this into DataProvider
-    def __init__(self, source, offset=0, limit=None, **kwargs):
+    def __init__(self, source, offset=0, limit=MAX_LIMIT, **kwargs):
         """
         :param offset:  the number of data to skip before providing.
         :param limit:   the final number of data to provide.
         """
         super().__init__(source, **kwargs)
 
-        # how many valid data to skip before we start outputing data - must be positive
-        #   (diff to support neg. indeces - must be pos.)
-        self.offset = max(offset, 0)
+        # how many valid data to skip before we start outputting data - must be positive
+        self.offset = offset
 
-        # how many valid data to return - must be positive (None indicates no limit)
+        # how many valid data to return - must be positive
+        if limit is None:
+            limit = MAX_LIMIT
         self.limit = limit
-        if self.limit is not None:
-            self.limit = max(self.limit, 0)
 
     def __iter__(self):
         """
diff --git a/lib/galaxy/webapps/galaxy/api/datasets.py b/lib/galaxy/webapps/galaxy/api/datasets.py
index 53006b4ee8c1..7f4dc8ca66d4 100644
--- a/lib/galaxy/webapps/galaxy/api/datasets.py
+++ b/lib/galaxy/webapps/galaxy/api/datasets.py
@@ -71,6 +71,10 @@
     RequestDataType,
     UpdateObjectStoreIdPayload,
 )
+from .common import (
+    LimitQueryParam,
+    OffsetQueryParam,
+)
 
 log = logging.getLogger(__name__)
 
@@ -432,18 +436,35 @@ def show(
                 "may return different responses."
             ),
         ),
+        limit: Annotated[
+            Optional[int],
+            Query(
+                ge=1,
+                le=10000,
+                description="Maximum number of items to return. Currently only applies to `data_type=raw_data` requests",
+            ),
+        ] = None,
+        offset: Annotated[
+            Optional[int],
+            Query(
+                ge=0,
+                description="Starts at the beginning skip the first ( offset - 1 ) items and begin returning at the Nth item. Currently only applies to `data_type=raw_data` requests",
+            ),
+        ] = 0,
         serialization_params: SerializationParams = Depends(query_serialization_params),
     ):
         """
-        **Note**: Due to the multipurpose nature of this endpoint, which can receive a wild variety of parameters
+        **Note**: Due to the multipurpose nature of this endpoint, which can receive a wide variety of parameters
         and return different kinds of responses, the documentation here will be limited.
         To get more information please check the source code.
         """
-        exclude_params = {"hda_ldda", "data_type"}
+        exclude_params = {"hda_ldda", "data_type", "limit", "offset"}
         exclude_params.update(SerializationParams.model_fields.keys())
         extra_params = get_query_parameters_from_request_excluding(request, exclude_params)
 
-        return self.service.show(trans, dataset_id, hda_ldda, serialization_params, data_type, **extra_params)
+        return self.service.show(
+            trans, dataset_id, hda_ldda, serialization_params, data_type, limit=limit, offset=offset, **extra_params
+        )
 
     @router.get(
         "/api/datasets/{dataset_id}/content/{content_type}",