community-help
MythoMax 13B timeout
Latency: GPT-4o
Checking Remaining Credits via API
The payment attempt failed everytime every card
Unable to use google/gemini-flash-1.5
OpenRouter API privacy with Llama 3 70B
Batching multiple message in single API call
Payment failed but amount got deducted
Open-router with OpenAI client
paid credits via crypto (polygon) but no credits have been updated
Function calling claude
"total_cost" is gone
errors
Get usage data via API
how-to
Gemini 1.5 Flash quota exceeded (requests per minute)
change YOUR_SITE_NAME in oauth
Error message with more than 1 LLM's .
MythoMax output feels like extremely high temperature since recently
Strange Gemini 1.5 Flash Token counting
Garbled responses from PPLX 70B online
LZLV-70b repetition problems
I keep getting error 401 when I try clicking on "manage credentials"
include_usage not work while stream=True
Why does openrouter not consistently encapsulate the response to function calling?
oauth callback doesnt send state payload
Support Gpts
Context input in OpenRouter is less than given max context size
cohere/command-r outputs mixed languages
yo alex/lab question about gemini 1.5 for prod
Recommended Models for RP?
How to restrict a model to provide short responses
Credits not loading
PKCE auth not working
errors
Keep getting 429 error on Gemini 1.5
Can't load credit (Error 402)
RuntimeException: Connection ended before receiving response in C:\Apache24\htdocs\reportmines\vendo
Getting complete garbage response from mythomax very frequently
8x22B instruct continual error.
errors
HTTP-Referer Header
Rate-limiting despite being well within limits shown in keys endpoint
Can function calling be used with OpenAI's Python library in OpenRouter?
how-to
OctaAI (provider) returning empty responses all the time
mistralai/mixtral-8x7b-instruct:nitro
Error Message on Venus
I have a billing concern and can’t find contact
Question about model billing patterns
Moderation models like llama-guard-7b
how to choose a provider for a model
how-to
Error during generation, Authentication, Chub/Venus
errors
why does the LLM seem to output differently on playground than it does SillyTavern or Voxtra
API Rate limits question, LLAMA 3 8B
how-to