Skip to content

fix: increase health check max_tokens default to 16 (#23836) #26610

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Sameerlite merged 2 commits into from
Jun 18, 2026
+3 −4
Merged

fix: increase health check max_tokens default to 16 (#23836) #26610

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
fd3eadb
fix: increase health check max_tokens from 5 to 16 (#23836)
hannahmadison Apr 27, 2026
3ae8ca3
Merge branch 'litellm_oss_staging' into fix/health-check-max-tokens-2…
Sameerlite Jun 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions litellm/proxy/health_check.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -401,7 +401,7 @@ def _resolve_health_check_max_tokens(
3. For non-wildcard reasoning routes: BACKGROUND_HEALTH_CHECK_MAX_TOKENS_REASONING
from env (if set)
4. BACKGROUND_HEALTH_CHECK_MAX_TOKENS (global, any route including wildcards)
5. Non-wildcard default: 5
5. Non-wildcard default: 16
6. Wildcard and nothing from (1)(4): leave unset (caller omits max_tokens)
"""
explicit = model_info.get("health_check_max_tokens", None)
Expand Down Expand Up @@ -432,7 +432,7 @@ def _resolve_health_check_max_tokens(
return int(BACKGROUND_HEALTH_CHECK_MAX_TOKENS)

if not is_wildcard:
return 16 # OpenAI GPT-5 models require max_output_tokens >= 16
return 16

return None

Expand Down
3 changes: 1 addition & 2 deletions tests/test_litellm/proxy/test_health_check_max_tokens.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,8 +49,7 @@ async def test_update_litellm_params_max_tokens_wildcard():

updated_params = _update_litellm_params_for_health_check(model_info, litellm_params)

# Should not be set to 1
assert "max_tokens" not in updated_params or updated_params["max_tokens"] != 1
assert "max_tokens" not in updated_params


@pytest.mark.asyncio
Expand Down
Loading