diff --git a/server/src/cursor/model_catalog.rs b/server/src/cursor/model_catalog.rs
index 2a7364e..aefe280 100644
--- a/server/src/cursor/model_catalog.rs
+++ b/server/src/cursor/model_catalog.rs
@@ -14,7 +14,7 @@ use crate::{
         proxy::{self, CursorProxy},
         CursorSessionRegistry,
     },
-    model::ProviderModel,
+    model::{format_token_count, parse_token_count, ProviderModel},
     Error, Result,
 };
 
@@ -214,7 +214,7 @@ fn context_options(model: &ProviderModel) -> Vec<(String, String)> {
         let value = tokens.to_string();
         let duplicate = contexts
             .iter()
-            .any(|(existing, _)| parse_context_tokens(existing) == Some(tokens));
+            .any(|(existing, _)| parse_token_count(existing) == Some(tokens));
         if !duplicate {
             contexts.push((value, format!("{} (Custom)", format_token_count(tokens))));
         }
@@ -222,26 +222,6 @@ fn context_options(model: &ProviderModel) -> Vec<(String, String)> {
     contexts
 }
 
-fn parse_context_tokens(value: &str) -> Option<u64> {
-    let value = value.trim().to_ascii_lowercase();
-    let (number, multiplier) = match value.chars().last()? {
-        'k' => (&value[..value.len() - 1], 1_000),
-        'm' => (&value[..value.len() - 1], 1_000_000),
-        _ => (value.as_str(), 1),
-    };
-    number.parse::<u64>().ok()?.checked_mul(multiplier)
-}
-
-fn format_token_count(tokens: u64) -> String {
-    if tokens >= 1_000_000 && tokens.is_multiple_of(1_000_000) {
-        format!("{}M", tokens / 1_000_000)
-    } else if tokens >= 1_000 && tokens.is_multiple_of(1_000) {
-        format!("{}K", tokens / 1_000)
-    } else {
-        tokens.to_string()
-    }
-}
-
 pub async fn available_models(
     State(registry): State<CursorSessionRegistry>,
     Extension(proxy): Extension<CursorProxy>,
diff --git a/server/src/cursor/request/model.rs b/server/src/cursor/request/model.rs
index 16f0972..2af1442 100644
--- a/server/src/cursor/request/model.rs
+++ b/server/src/cursor/request/model.rs
@@ -1,6 +1,9 @@
 use crate::{
     cursor::proto::agent::v1 as pb,
-    model::{ModelLatency, ModelSpec, ReasoningSpec, SubagentKind, SubagentModelOverride},
+    model::{
+        parse_token_count, ModelLatency, ModelSpec, ReasoningSpec, SubagentKind,
+        SubagentModelOverride,
+    },
     Error, Result,
 };
 
@@ -136,16 +139,6 @@ fn parse_bool(parameter: &pb::requested_model::ModelParameterValue) -> Result<bo
     }
 }
 
-fn parse_token_count(value: &str) -> Option<u64> {
-    let value = value.trim().to_ascii_lowercase();
-    let (number, multiplier) = match value.chars().last()? {
-        'k' => (&value[..value.len() - 1], 1_000),
-        'm' => (&value[..value.len() - 1], 1_000_000),
-        _ => (value.as_str(), 1),
-    };
-    number.parse::<u64>().ok()?.checked_mul(multiplier)
-}
-
 #[cfg(test)]
 mod tests {
     use super::*;
diff --git a/server/src/model/mod.rs b/server/src/model/mod.rs
index 3ca7fe9..ae3637a 100644
--- a/server/src/model/mod.rs
+++ b/server/src/model/mod.rs
@@ -9,6 +9,7 @@ mod projection;
 mod provider;
 mod run;
 mod runtime_tag;
+mod token_count;
 mod tool;
 mod usage;
 
@@ -23,5 +24,6 @@ pub use projection::*;
 pub use provider::*;
 pub use run::*;
 pub use runtime_tag::*;
+pub(crate) use token_count::*;
 pub use tool::*;
 pub use usage::*;
diff --git a/server/src/model/token_count.rs b/server/src/model/token_count.rs
new file mode 100644
index 0000000..126b344
--- /dev/null
+++ b/server/src/model/token_count.rs
@@ -0,0 +1,39 @@
+pub(crate) fn parse_token_count(value: &str) -> Option<u64> {
+    let value = value.trim().to_ascii_lowercase();
+    let (number, multiplier) = match value.chars().last()? {
+        'k' => (&value[..value.len() - 1], 1_000),
+        'm' => (&value[..value.len() - 1], 1_000_000),
+        _ => (value.as_str(), 1),
+    };
+    number.parse::<u64>().ok()?.checked_mul(multiplier)
+}
+
+pub(crate) fn format_token_count(tokens: u64) -> String {
+    if tokens >= 1_000_000 && tokens.is_multiple_of(1_000_000) {
+        format!("{}M", tokens / 1_000_000)
+    } else if tokens >= 1_000 && tokens.is_multiple_of(1_000) {
+        format!("{}K", tokens / 1_000)
+    } else {
+        tokens.to_string()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn token_counts_parse_plain_and_abbreviated_values() {
+        assert_eq!(parse_token_count("272000"), Some(272_000));
+        assert_eq!(parse_token_count("272K"), Some(272_000));
+        assert_eq!(parse_token_count("1m"), Some(1_000_000));
+        assert_eq!(parse_token_count("invalid"), None);
+    }
+
+    #[test]
+    fn token_counts_format_exact_thousands_and_millions() {
+        assert_eq!(format_token_count(272_000), "272K");
+        assert_eq!(format_token_count(1_000_000), "1M");
+        assert_eq!(format_token_count(272_001), "272001");
+    }
+}