diff --git a/agent/usage_pricing.py b/agent/usage_pricing.py
index 5cacdb04a9..1b4a5e2fb7 100644
--- a/agent/usage_pricing.py
+++ b/agent/usage_pricing.py
@@ -1283,8 +1283,16 @@ def normalize_usage(
         )
         input_tokens = max(0, input_total - cache_read_tokens - cache_write_tokens)
     else:
-        prompt_total = _to_int(getattr(response_usage, "prompt_tokens", 0))
-        output_tokens = _to_int(getattr(response_usage, "completion_tokens", 0))
+        # OpenAI-style names first; fall back to Anthropic-style
+        # (input_tokens/output_tokens). Local OpenAI-compatible servers like
+        # mlx_vlm.server emit the Anthropic names in chat_completions responses,
+        # and the OpenAI Python client preserves them as extra attributes.
+        prompt_total = _to_int(getattr(response_usage, "prompt_tokens", 0)) or _to_int(
+            getattr(response_usage, "input_tokens", 0)
+        )
+        output_tokens = _to_int(getattr(response_usage, "completion_tokens", 0)) or _to_int(
+            getattr(response_usage, "output_tokens", 0)
+        )
         details = getattr(response_usage, "prompt_tokens_details", None)
         # Primary: OpenAI-style prompt_tokens_details. Fallback: Anthropic-style
         # top-level fields that some OpenAI-compatible proxies (OpenRouter, Vercel