diff --git a/docs/optimizing/basic_strategies/basic_strategies.md b/docs/optimizing/basic_strategies/basic_strategies.md
index 0ebeb3b049daeb8ce7847f6036ccb31fac2886d8..3db6d39314f20608e2430337050a38a7ceb5ed59 100644
--- a/docs/optimizing/basic_strategies/basic_strategies.md
+++ b/docs/optimizing/basic_strategies/basic_strategies.md
@@ -34,7 +34,7 @@ maxdepth: 1
 Choosing the right embedding model plays a large role in overall performance.
 
 - Maybe you need something better than the default `text-embedding-ada-002` model from OpenAI?
-- Maybe you want to scale to a local sever?
+- Maybe you want to scale to a local server?
 - Maybe you need an embedding model that works well for a specific language?
 
 Beyond OpenAI, many options existing for embedding APIs, running your own embedding model locally, or even hosting your own server.
diff --git a/docs/understanding/evaluating/cost_analysis/usage_pattern.md b/docs/understanding/evaluating/cost_analysis/usage_pattern.md
index 9d77ad34f46771aadb78688605fabb039462609b..acad4fac0cebafb14fac94f9c4bf30b1a98829be 100644
--- a/docs/understanding/evaluating/cost_analysis/usage_pattern.md
+++ b/docs/understanding/evaluating/cost_analysis/usage_pattern.md
@@ -73,7 +73,7 @@ print(
 token_counter.reset_counts()
 ```
 
-6. Run a query, mesaure again
+6. Run a query, measure again
 
 ```python
 query_engine = index.as_query_engine()