diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index a77b3b7a..18d2af8a 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -2646,18 +2646,9 @@ struct server_context {
 
         // populate res.probs_output
         if (slot.sparams.n_probs > 0) {
-            if (!slot.params.stream && slot.stopped_word) {
-                const std::vector<llama_token> stop_word_toks = llama_tokenize(ctx, slot.stopping_word, false);
-
-                size_t safe_offset = std::min(slot.generated_token_probs.size(), stop_word_toks.size());
-                res.probs_output = std::vector<completion_token_output>(
-                        slot.generated_token_probs.begin(),
-                        slot.generated_token_probs.end() - safe_offset);
-            } else {
-                res.probs_output = std::vector<completion_token_output>(
-                        slot.generated_token_probs.begin(),
-                        slot.generated_token_probs.end());
-            }
+            res.probs_output = std::vector<completion_token_output>(
+                    slot.generated_token_probs.begin(),
+                    slot.generated_token_probs.end());
             res.data["completion_probabilities"] = probs_vector_to_json(ctx, res.probs_output);
         }
 
diff --git a/examples/server/utils.hpp b/examples/server/utils.hpp
index 24dcb044..3c4b6dd1 100644
--- a/examples/server/utils.hpp
+++ b/examples/server/utils.hpp
@@ -466,6 +466,12 @@ static json oaicompat_chat_params_parse(const json& body) {
         throw std::runtime_error("Only no echo is supported");
     }
 
+    // Handle "logprobs" field
+    int n_probs = json_value(body, "logprobs", 0);
+    if (n_probs > 0) {
+        llama_params["n_probs"] = n_probs;
+    }
+
     // Params supported by OAI but unsupported by llama.cpp
     static const std::vector<std::string> unsupported_params{ "best_of", "suffix" };
     for (const auto& param : unsupported_params) {