community-help
How to get AI to play a Character part, please?
how-to
UI Now blocking more than three models.
Infermatic Error maximum context length on lumimaid 8b
errors
How to Ensure Reliable API Calls?
Llama 3.1 405b base model appears to be silently inserting 'user:' into messages
wizard 8x22 ignoring commands and being repetative
errors
Why can't I upload documents?
Claude 3.5 Sonnet Responses
bug with llama3.1 8b:free, sais limit exceeded
errors
_
How to use tool calling?
how to add my app to the showcase?
what happens if I set max_tokens to 0?
Why did it choose an expensive provider?
Can Open Router enable using plug-in for some Modeld
Personal domain email registration failed
How to get Beta use-your-own key?
"tool_choice": "none" broken on Anthropic Claude 3.5
How can I see my consumption per AI model?
how-to
Why i pay 4$, but credits only show 3.45$
how to use the voice
Is this warning from Openrouter or provider or from the character?
too much prose!
where are chat stored?
Euryale v2.1 70B provided by deepinfra is spewing incoherently.
Refund
Hello, could you please tell me how to check my account and find out the average cost per conversati
Random Method Not Allowed response
errors
How Does OpenRouter Handle Tool Choice Compatibility Between Different AI Models?
gemini-flash generating short responses
how-to
What happened to NVIDIA Nemotron-4 340B Instruct ?
Some Users Experiencing CORS Error ⚠
No endpoints found for the request — usual GPT-3.5 request
Card getting declined
errors
claude-3.5sonnet (not self moderated) suddenly starts rejecting requests like it was moderating.
errors
How to ger RAG working?
Weird 401 'Invalid Credentials' Error using LibreChat
Possibility of using fine tuned models with Integrations API
random timeout in production
OpenAI opted out model training. Is this going to be possible with Openrouter Open AI Models?
Help me using OpenRouter API with Typing Mind Plugins.
Access per-provider api keys
Bug notification...
HTTP 405 Error Code In Continue Dev VSCode Extension
errors
Does "moderated" or "self-moderated" produce higher quality responses?
Billing is not working
json response_format not respected for openai/gpt-o model
Usage graph by day?
Generation Details Endpoint not returning generation time for non-streamed requests
Card declined / couldn't authorize