diff --git a/docs/introduction/prompting.mdx b/docs/introduction/prompting.mdx
index 06f3b608d..1dce693f9 100644
--- a/docs/introduction/prompting.mdx
+++ b/docs/introduction/prompting.mdx
@@ -8,7 +8,7 @@ iconType: "solid"
 To get the best results from Codegen, treat it like a skilled teammate: provide clear, specific instructions and sufficient context. Vague requests lead to ambiguous outcomes.
 
 <Tip>
-  Codegen is based on Anthropic's Claude 3.7. You can prompt it similarly to
+  Codegen is based on Anthropic's Claude 4 Sonnet. You can prompt it similarly to
   ChatGPT or other LLM-based assistants
 </Tip>
 
diff --git a/docs/settings/model-configuration.mdx b/docs/settings/model-configuration.mdx
index a6e0ef771..7bb567f54 100644
--- a/docs/settings/model-configuration.mdx
+++ b/docs/settings/model-configuration.mdx
@@ -24,15 +24,15 @@ As shown in the UI, you can generally configure the following:
   - Anthropic
   - OpenAI
   - Google (Gemini)
-- **LLM Model:** Once a provider is selected, you can choose a specific model from that provider's offerings (e.g., Claude 3.7, GPT-4, Gemini Pro).
+- **LLM Model:** Once a provider is selected, you can choose a specific model from that provider's offerings (e.g., Claude 4 Sonnet, GPT-4, Gemini Pro).
 
 ## Model Recommendation
 
 <Warning>
   While Codegen provides access to a variety of models for experimentation and
-  specific use cases, **we highly encourage the use of Anthropic's Claude 3.7
-  (Haiku)**. Our internal testing and prompt engineering are heavily optimized
-  for Claude 3.7, and it consistently delivers the best performance,
+  specific use cases, **we highly encourage the use of Anthropic's Claude 4 Sonnet**. 
+  Our internal testing and prompt engineering are heavily optimized
+  for Claude 4 Sonnet, and it consistently delivers the best performance,
   reliability, and cost-effectiveness for most software engineering tasks
   undertaken by Codegen agents. Other models are made available primarily for
   users who are curious or have unique, pre-existing workflows.
@@ -47,7 +47,7 @@ For advanced users or those with specific enterprise agreements with LLM provide
 
 <Tip>
   Using the default Codegen-managed LLM configuration (especially with Claude
-  3.7) is recommended for most users to ensure optimal performance and to
+  4 Sonnet) is recommended for most users to ensure optimal performance and to
   benefit from our continuous prompt improvements.
 </Tip>