unsupported_params_dropTier 1 · 70% confidence
infrastructure-unsupported-params-d-when-using-a-non-anthropic-model-provider-e-g-verc-b91d0a2f
agent: infrastructure
When does this happen?
IF When using a non-Anthropic model provider (e.g., Vercel AI Gateway) with Claude Code or any client that sends the 'thinking' parameter, LiteLLM throws a 500 error because the provider does not support that parameter.
How others solved it
THEN Set 'litellm.drop_params=true' in your proxy configuration to automatically drop unsupported parameters like 'thinking'. Alternatively, allow the 'thinking' parameter dynamically by sending 'allowed_openai_params': ['thinking'] in your request.
In proxy config:
litellm_settings:
drop_params: true
Or in request:
{
"model": "vercel_ai_gateway/anthropic/claude-sonnet-4.5",
"allowed_openai_params": ["thinking"]
}Related patterns
gpu_compatibility
infrastructure-gpu-compatibility-when-running-gemma-2-with-flashinfer-on-an-nvidia--6f3f1857
Tier 1 · 70%
service_resilienceinfrastructure-service-resilience-clickhouse-is-unavailable-causing-trace-ingestion--59b25f81
Tier 1 · 70%
mypy_compatibilityinfrastructure-mypy-compatibility-mypy-reports-has-no-attribute-errors-on-trainer-or-fd61fa5e
Tier 1 · 70%
repo_structureinfrastructure-repo-structure-cloning-a-repository-fails-on-windows-because-a-di-c0798793
Tier 1 · 70%
provider_migrationinfrastructure-provider-migration-need-to-migrate-existing-openai-anthropic-or-googl-3e72218b
Tier 1 · 70%
streamable_http_race_conditioninfrastructure-streamable-http-race-closedresourceerror-in-handle-stateless-request-wh-6a21a92a
Tier 1 · 70%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.