community-help

4735 threads · Page 92 of 95

Status code 200 CORS 40 messages
errors
Issue using Mixtral on Sillytavern 3 messages
Creating api keys programmatically 49 messages
Change username 4 messages
Can't buy credits/ White screen of death from Stripe 9 messages
Account deletion 3 messages
claude2.0&2.1 failed response on playground and api 7 messages
Is logits_bias working with OpenHermes 2.5? 11 messages
Tokenister error? 2 messages
Which models are actually unfiltered? The label seems to be wrong for some of them. 3 messages
OpenRouter incompatible with new version of openai python library 2 messages
Function-calling (tool calls) not working with OpenHermes 2.5 12 messages
Native Tokens vs Tokens 11 messages
OpenChat 3.5 issues 101 messages
Instruction following not working properly on API? 7 messages
psy fighter isnt responding at all 4 messages
Perplexity modelds 27 messages
524 for Claude 2.0 with long prompt 2 messages
What's this? 6 messages
Stricter Moderation Than OpenAI? 2 messages
Are output token limits documented anywhere? 8 messages
Make.com Reference Conversation 4 messages
testing the fallbacks 11 messages
enterprise pricing 3 messages
Can I make users of my app insert their own tokens? 7 messages
Credit not being applied to key 3 messages
Unexpected end of JSON input 45 messages
Activity & Cost 6 messages
how-to
open source function calling & typing mind 2 messages
Questions for GDPR 24 messages
Failed to disable transforms: middle-out. 2 messages
Incorrect handling intel/neural-chat-7b when no max_tokens passed in non-stream mode, please fix 2 messages
Encountered this issue while using Claude-2.1 via OpenRouter API 12 messages
mythomax-l2-13b writes its own name multiple times in beginning of response 6 messages
Models endpoint does not work with rust async-openai library 2 messages
Capybara with prompt 5 messages
Is there a list/table of parameters each model supports? 2 messages
OpenAI Assistant through OpenRouter? 2 messages
Do you apply rate limits by IP? 36 messages
how do i make it work 5 messages
how-to errors
Tokens used? 10 messages
Topped M output issues 5 messages
help 2 messages
The response delay times out seriously 2 messages
Rate limit error 9 messages
Credits 2 messages
Very slow OpenAI responses via gpt-4-32k 3 messages
Getting very slow responses with lzlv-70b 3 messages
first token is too slow, 5s, can we make it fast? 17 messages
Getting incorrect instruct mode errors with weaver 8 messages
errors