LiteLLM Bedrock serviceTier Parameter Error - Malformed Input Request
Fix LiteLLM Bedrock serviceTier parameter causing Malformed input request error Includes evidence for LiteLLM troubleshooting demand.
Malformed input request Topic hub pagination
LiteLLM errors - page 8
Continue browsing this topic cluster with SEO-safe static pagination.
LiteLLM Chat Completions to Responses API Bridge tool_choice 400 Error
Fix LiteLLM 400 error when using tool_choice named function format with GPT-5.4/5.5 models Includes evidence for LiteLLM troubleshooting demand.
400 Bad Request - tool_choice named function format LiteLLM count_tokens Silently Falls Back to Local Tokenizer for Bedrock Anthropic Models
Fix LiteLLM /v1/messages/count_tokens returning wrong token count for Bedrock-backed Anthropic models Includes evidence for LiteLLM troubleshooting demand.
Provider token counting failed (400): messages.N.content: Field required. Falling back to local tokenizer LiteLLM gpt-4o-transcribe-diarize chunking_strategy Required Error
Fix LiteLLM 400 error requiring chunking_strategy for gpt-4o-transcribe-diarize model Includes evidence for LiteLLM troubleshooting demand.
400 litellm.BadRequestError: OpenAIException - chunking_strategy is required for diarization models LiteLLM max_budget Ignored After Monthly Budget Reset
Fix LiteLLM max_budget being ignored after ResetBudgetJob resets key spending to zero Includes evidence for LiteLLM troubleshooting demand.
max_budget is ignored after reset LiteLLM phantom BudgetExceededError — Redis spend counter leak
Fix random LiteLLM BudgetExceededError (429) when actual spend is near zero Includes evidence for LiteLLM troubleshooting demand.
BudgetExceededError (HTTP 429) LiteLLM Proxy Cost Override Ignored in Upstream Proxy Chaining
Fix LiteLLM model_info cost_per_token override being ignored when calling upstream LiteLLM proxy Includes evidence for LiteLLM troubleshooting demand.
model_info cost override (input_cost_per_token/output_cost_per_token) ignored when using litellm_proxy/ prefix LiteLLM Proxy Phantom BudgetExceededError After Redis Spend Counter Leak
Fix LiteLLM proxy randomly returning BudgetExceededError 429 despite zero actual spend after upgrade Includes evidence for LiteLLM troubleshooting demand.
BudgetExceededError (HTTP 429) — phantom budget exceeded despite actual spend near $0 LiteLLM Streaming Crash with Reasoning Field — async for NoneType Error Fix
Fix LiteLLM TypeError crash when streaming models that return reasoning field in delta Includes evidence for LiteLLM troubleshooting demand.
TypeError: 'async for' requires an object with __aiter__ method, got NoneType when streaming models with reasoning field in delta LiteLLM Supply Chain Attack — Malicious .pth File Steals Credentials
Fix or investigate malicious code execution from litellm package on Python startup Includes evidence for LiteLLM troubleshooting demand.
malicious litellm_init.pth in litellm 1.82.8 — credential stealer LiteLLM Virtual Key MCP Access Bypasses Team Access Group Controls
Fix LiteLLM virtual key MCP endpoints ignoring team access group restrictions Includes evidence for LiteLLM troubleshooting demand.
Virtual key MCP access ignores team access groups — discovery and enforcement failure Popular links in this topic hub
- LiteLLM Proxy Rate Limit Error — "RateLimitError" when routing through LiteLLM proxy
- Fixing LiteLLM APIConnectionError: Connection timed out
- OpenRouter Free Models Keep Going 404 — Model Unavailable After Rate Limit
- LiteLLM 429 Errors Bypass Cooldown When Using OpenAI-like Providers (Wrapped as APIConnectionError)
- LiteLLM Azure OpenAI Authentication Error 401 with DefaultAzureCredential