Add corrections, implementation notes, pricing changes, or usage caveats for other readers.
Knowledge cutoff
2024-10
Input modalities
Output modalities
Capabilities
200,000 tokens
Recent tweets and retweets from Helicone
Connor is an ex @helicone_ai intern turned YC founder.
He built @tryreplicas while working at Helicone. We used it internally to handle about 70% of our bug reports.
We're excited to share that Helicone is joining @mintlify! πππ
What this means for our users: Helicone is moving into maintenance mode. Your data is safe and the platform will continue to be accessible, but we will not be shipping new features going forward.
Thank you toβ¦
psa: this is your end of year reminder to turn on prompt caching in your fav LLM provider.
gateways like @LiteLLM @PortkeyAI @helicone_ai also have ways to do this
this gets you the same output with none of the uncertainty of embedding caching redis is selling these days
Discuss this model
Add corrections, implementation notes, pricing changes, or usage caveats for other readers.