BerriAI/litellm · error · ValueError
QualityRouter: no model available for quality tier {tier} an
Error message
QualityRouter: no model available for quality tier {tier} and no default_model configured What it means
Routing failure in QualityRouter: no indexed model exists for the requested quality tier, and no higher/lower tier could round into it, and no default_model is configured, so there is no model to route to.
Source
Thrown at litellm/router_strategy/quality_router/quality_router.py:303
if tier in tier_index and tier_index[tier]:
return tier_index[tier][0]
# Round up.
higher_tiers: Final = sorted(t for t in tier_index if t > tier)
for t in higher_tiers:
if tier_index[t]:
return tier_index[t][0]
# Round down — closest lower tier first.
lower_tiers: Final = sorted((t for t in tier_index if t < tier), reverse=True)
for t in lower_tiers:
if tier_index[t]:
return tier_index[t][0]
if self.config.default_model:
return self.config.default_model
raise ValueError(f"QualityRouter: no model available for quality tier {tier} and no default_model configured")
def _stash_decision(
self,
request_kwargs: dict[str, Any] | None,
decision: dict[str, Any],
) -> None:
"""
Stash the routing decision in request_kwargs.metadata so the Router can
lift it into response headers (`x-litellm-quality-router-*`). The same
dict object flows from here through to `make_call.set_response_headers`.
"""
if request_kwargs is None:
return
metadata: Final = request_kwargs.setdefault("metadata", {})
if isinstance(metadata, dict):
metadata["quality_router_decision"] = decision
async def async_pre_routing_hook(View on GitHub (pinned to 77b7c6c40c)
Solutions
- Configure a model for the quality tier or set default_model in the QualityRouter config.
Defensive patterns
Strategy: fallback
When it happens
Trigger: Thrown at litellm/router_strategy/quality_router/quality_router.py:303 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18).
Data as JSON: /api/errors/ffe80f2e8d94232d.
Report an issue: GitHub.