diff --git a/docs/python-api.md b/docs/python-api.md
index ae135a68..72011e84 100644
--- a/docs/python-api.md
+++ b/docs/python-api.md
@@ -54,7 +54,7 @@ response = model.prompt(
 
 ### Attachments
 
-Model that accept multi-modal input (images, audio, video etc) can be passed attachments using the `attachments=` keyword argument. This accepts a list of `llm.Attachment()` instances.
+Models that accept multi-modal input (images, audio, video etc) can be passed attachments using the `attachments=` keyword argument. This accepts a list of `llm.Attachment()` instances.
 
 This example shows two attachments - one from a file path and one from a URL:
 ```python
@@ -69,7 +69,18 @@ response = model.prompt(
     ]
 )
 ```
-Use `llm.Attachment(content=b"binary image content here")` to pass binary content directly.
+Use `llm.Attachment(content=b"binary image content here")` to pass binary content directly. You may optionqlly specify a content type - if tou do not it will be detected automatically:
+
+```python
+image = llm.Attachment(
+    content=b"...",
+    type="image/png"
+)
+response = model.prompt(
+    "extract text",
+    attachments=[image]
+)
+```
 
 ### Model options
 
@@ -206,4 +217,4 @@ Here the `default=` parameter specifies the value that should be returned if the
 
 ### set_default_embedding_model(alias) and get_default_embedding_model()
 
-These two methods work the same as `set_default_model()` and `get_default_model()` but for the default {ref}`embedding model <embeddings>` instead.
\ No newline at end of file
+These two methods work the same as `set_default_model()` and `get_default_model()` but for the default {ref}`embedding model <embeddings>` instead.