diff --git a/docling/datamodel/pipeline_options.py b/docling/datamodel/pipeline_options.py
index a24df89..1d35227 100644
--- a/docling/datamodel/pipeline_options.py
+++ b/docling/datamodel/pipeline_options.py
@@ -225,6 +225,7 @@ class PictureDescriptionApiOptions(PictureDescriptionBaseOptions):
     headers: Dict[str, str] = {}
     params: Dict[str, Any] = {}
     timeout: float = 20
+    concurrency: int = 1
 
     prompt: str = "Describe this image in a few sentences."
     provenance: str = ""
@@ -295,6 +296,7 @@ class ApiVlmOptions(BaseVlmOptions):
     params: Dict[str, Any] = {}
     scale: float = 2.0
     timeout: float = 60
+    concurrency: int = 1
     response_format: ResponseFormat
 
 
diff --git a/docling/models/api_vlm_model.py b/docling/models/api_vlm_model.py
index f7e82b5..60bc6fc 100644
--- a/docling/models/api_vlm_model.py
+++ b/docling/models/api_vlm_model.py
@@ -1,4 +1,5 @@
 from collections.abc import Iterable
+from concurrent.futures import ThreadPoolExecutor
 
 from docling.datamodel.base_models import Page, VlmPrediction
 from docling.datamodel.document import ConversionResult
@@ -27,6 +28,7 @@ class ApiVlmModel(BasePageModel):
                 )
 
             self.timeout = self.vlm_options.timeout
+            self.concurrency = self.vlm_options.concurrency
             self.prompt_content = (
                 f"This is a page from a document.\n{self.vlm_options.prompt}"
             )
@@ -38,10 +40,10 @@ class ApiVlmModel(BasePageModel):
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
-        for page in page_batch:
+        def _vlm_request(page):
             assert page._backend is not None
             if not page._backend.is_valid():
-                yield page
+                return page
             else:
                 with TimeRecorder(conv_res, "vlm"):
                     assert page.size is not None
@@ -63,4 +65,7 @@ class ApiVlmModel(BasePageModel):
 
                     page.predictions.vlm_response = VlmPrediction(text=page_tags)
 
-                yield page
+                return page
+
+        with ThreadPoolExecutor(max_workers=self.concurrency) as executor:
+            yield from executor.map(_vlm_request, page_batch)
diff --git a/docling/models/picture_description_api_model.py b/docling/models/picture_description_api_model.py
index 44bb5e2..eb331b2 100644
--- a/docling/models/picture_description_api_model.py
+++ b/docling/models/picture_description_api_model.py
@@ -1,4 +1,5 @@
 from collections.abc import Iterable
+from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
 from typing import Optional, Type, Union
 
@@ -37,6 +38,7 @@ class PictureDescriptionApiModel(PictureDescriptionBaseModel):
             accelerator_options=accelerator_options,
         )
         self.options: PictureDescriptionApiOptions
+        self.concurrency = self.options.concurrency
 
         if self.enabled:
             if not enable_remote_services:
@@ -48,8 +50,8 @@ class PictureDescriptionApiModel(PictureDescriptionBaseModel):
     def _annotate_images(self, images: Iterable[Image.Image]) -> Iterable[str]:
         # Note: technically we could make a batch request here,
         # but not all APIs will allow for it. For example, vllm won't allow more than 1.
-        for image in images:
-            yield api_image_request(
+        def _api_request(image):
+            return api_image_request(
                 image=image,
                 prompt=self.options.prompt,
                 url=self.options.url,
@@ -57,3 +59,6 @@ class PictureDescriptionApiModel(PictureDescriptionBaseModel):
                 headers=self.options.headers,
                 **self.options.params,
             )
+
+        with ThreadPoolExecutor(max_workers=self.concurrency) as executor:
+            yield from executor.map(_api_request, images)