community-help
Questions about email contacts and credit monitoring
A query about credits.
Bug: OpenRouter + GPT-5 + AI SDK + Vite**
Langchain Typescript OpenRouter select Provider
I keep on getting an error
Error to validate my address to purchase credits.
json.decoder.JSONDecodeError
errors
Error 429 without reaching the limit.
Syntax highlighting incorrect
deepseek-chat-v3.1 Is not being routed?
Is OpenRouter feasible for Production
"Empty response from API" error message
Just asking Again
Repeated Unexpected Deletion of Openroot Key Disrupting Our Translation Website's API Operations
How do I mock a fail on the primary to test fallback?
Rate limit exceeded 429 Too many requests
Critical issue: the /api/v1/generation endpoint seems to be down
Stuck on “Auto Router” ?
deepseek/deepseek-chat-v3.1:thinking - the model worked and now it is gone
Openrouter Key exposed
Clarification on Native PDF Processing Support for Anthropic Claude Sonnet 4 via OpenRouter API
Response format for OpenAI models not working
errors
OpenRouter support OpenAI Responses API?
how do i turn on thinking for GLM 4.5 ? I am Roleplaying On Janitor AI
Chat On Mobile Stored Differently from on PC.
Cerebras Qwen3 235B Thinking always cut off thinking since 4096 tokens
selected model is gpt5 but ai response gpt 4..
Is ChatGoogleGenerativeAI Langchain compatible with OpenRouter?
model not found: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
The model "account/usage" is not available
how to get the slug for openrouter's providers for a specific model
High costs in input tokens
is openrouter LLM models able to work like RAG system where LLM first refers to vectorized data?
Become Openrouter provider
Annotations Not Streaming in SSE on OpenRouter
Web search options not supported with this model 'openai/gpt-4o'
BYOK Billing
Rate limited help!
Rate still Limited after 10 credits purchase (API Error 429)
errors
Billing Issue - Charged for Free Model Usage
Error while Creating API key via `keys` endpoint
errors
Credits lost
errors
Set service_tier=priority for openai
An empty response with no error makes it hard to implement retries
Does OpenRouter have Token Per Minute (TPM) and Request per minute (RPM) limits?
I'm switching from the Open AI API. How do I upload files and create batches?
Can't export table with requests information from the Activity tab
I put $10 in, and it won’t pop up.
Bug Report: openrouter/auto => File + Structured Output w/ Require Parameters not routing correctly
Full usage including tool calls via AI SDK