community-help
Base 405B is consistently giving 1015 errors
Window.ai?
Integrations is blank
Auto top up failed to work
OpenRouter charging 10x more
any way to get prompt caching usage tokens?
How do I find azure models supported?
HELP GETTING CHARGED REPEATEDLY!!!!
errors
Images not being processed by provider Hyperbolic
How can we become a provider?
Incorrect api key provided
OpenRouter charging approximately 5x what it should with Gemini 1.5 Flash
No credit added
Reuse a deleted account
Tool calling with Gemini pro 1.5
Possible glitch…
Try to pay credits
What is this strange reply
errors
Help please: Unicode characters garbled :(
Qwen 2 vl 72b :An error occurred: {"detail":"Insufficient funds, please see https://docs.hyperbolic}
When generating in playground, noromaid just keeps regenerating over and over again for no reason.
Docs issue: tool_calls in Message objects sent in requests?
Phantom API calls on my account
Provider Routing Latency
OpenRouter Credits
Are there any providers who do respect privacy?
how-to
/generation id not found
Prompt token limit exceeded
New Billing Method
make.com & Claude
o1 with api key or no api key ….. doesn’t put out. I’m desperate
base model completion question?
how-to
Seeking llama-3-70b (nitro) Model Files for Backup Purposes
"Not enough data for satisfy transfer length header." 405b Base
What are the terms for enabling logging for OpenRouter?
o1 limit?
i'm getting "Sorry, you have been blocked" on openai new models o1 and mini
Custom Routing in OpenAI python SDK
What domain(s) to whitelist
Chats/rooms text disappearing
errors
transaction
Assistance Required for API Access Issue
aider with bf16 versions.
200 qps: per key or org?
Openrouter Wizard 8x22b : Taking more than 60s to respond on the prompt specified
errors
Metamask (rabby) sign-in broken
errors
I'm stuck in the chat window.
errors
Chatroom sometimes "forgets" conversations or added models
OpenAI's new models only support temp of 1
errors
Uploading files