BerriAI/litellm · error · HTTPException
Model '{m}' not in organization's allowed models. Organizati
Error message
Model '{m}' not in organization's allowed models. Organization allowed models={org_table.models}. Organization: {org_table.organization_id} What it means
Org model allowlist enforcement: unless the org grants all-proxy-models, every model in data.models must appear in org_table.models; an unlisted model is rejected with 400 listing the org's allowed set.
Source
Thrown at litellm/proxy/management_endpoints/team_endpoints.py:959
and org_table.litellm_budget_table.max_budget is not None
and data.max_budget > org_table.litellm_budget_table.max_budget
):
raise HTTPException(
status_code=400,
detail={
"error": f"Team max_budget ({data.max_budget}) exceeds organization's max_budget ({org_table.litellm_budget_table.max_budget}). Organization: {org_table.organization_id}"
},
)
# Validate team models against organization's allowed models
if data.models is not None and len(org_table.models) > 0:
# If organization has 'all-proxy-models', skip validation as it allows all models
if SpecialModelNames.all_proxy_models.value in org_table.models:
pass
else:
for m in data.models:
if m not in org_table.models:
raise HTTPException(
status_code=400,
detail={
"error": f"Model '{m}' not in organization's allowed models. Organization allowed models={org_table.models}. Organization: {org_table.organization_id}"
},
)
# Validate team TPM/RPM against organization's TPM/RPM limits (direct comparison)
if (
data.tpm_limit is not None
and org_table.litellm_budget_table is not None
and org_table.litellm_budget_table.tpm_limit is not None
and data.tpm_limit > org_table.litellm_budget_table.tpm_limit
):
raise HTTPException(
status_code=400,
detail={
"error": f"Team tpm_limit ({data.tpm_limit}) exceeds organization's tpm_limit ({org_table.litellm_budget_table.tpm_limit}). Organization: {org_table.organization_id}"
},View on GitHub (pinned to 77b7c6c40c)
Solutions
- Remove the model from the team request, or add it to the organization's allowed models first.
Defensive patterns
Strategy: validation
When it happens
Trigger: Thrown at litellm/proxy/management_endpoints/team_endpoints.py:959 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/01f3bd7a4f3e0aee.
Report an issue: GitHub.