diff --git a/evalharness/model/adapter.py b/evalharness/model/adapter.py
index feebd20..44cbc75 100644
--- a/evalharness/model/adapter.py
+++ b/evalharness/model/adapter.py
@@ -205,7 +205,8 @@ class OpenAICompatible(ModelAdapter):
                 if stream:
                     out = await self._post_stream_perf(
                         f'{self.api_base}/chat/completions', payload, headers, t0)
-                elif int(payload.get('max_tokens') or 0) > 8192:
+                elif int(payload.get('max_tokens') or 0) > 100000 \
+                        and not os.environ.get('EVALHARNESS_NO_AUTOSTREAM'):
                     # long generation: stream and aggregate (gateway-safe).
                     # Some gateways drop chat_template_kwargs on the STREAM
                     # path only (non-stream honors it) -- append the /no_think