Choosing LLM models for AI tasks
planned
Log In
r
rhtdutt
Taskade typically implements changes rapidly, but this one has been pending since August 5, 2024. Can you provide an update on when multiple models will be available?
g
gabriel.ross
Own API integration. When selecting the LLM model... It would be amazing to have the option to use/add our own OpenAI / DeepSeek / Gemini APIs...
So we could leverage the speed of Requests per minute using our own APIs and not rely on Taskade's GTP-4o only.
Im in a point that I need to have agents to work on 4k, 100K, 700K tasks in projects and I cant get it moving for the RPM limits or whatever reason I was get errors... I end up using my owns API within Excel Labs to do it. Not ideal.... Copilot can't handle the task, nor web gpt-o1. Only API is able to do it.
I do believe this will be a great tool and will withdraw a lot of Taskade's API requests, for those seeking API RPM tier speed.... Please consider this.
I'm opened to a conversation/call if needed. Im starting to use taskade as the core AI operations, along with N8N and Power Automate.
Narek Zograbian
Merged in a post:
more models
scoobysneck
r1 just came out, its open source, let's go, 4o is behind the times I have better success with llama most of the time I wouldn't even dare to use 4o mini for what asking a yes or no question? its not very smart
caitlinrway
Would love to see an update on the timeline for this when possible! Really looking forward to it.
Narek Zograbian
caitlinrway: Would you be okay with this option if it was BYOK?
caitlinrway
Narek Zograbian Yes I think so!
Narek Zograbian
caitlinrway Noted. Thanks for confirming!
d5v6r2ytb2
Narek Zograbian Just wanted to add that I would be as well! Hope to see it soon! I dont like to having to switch out of taskade to use other models - Happy holidays :)
Narek Zograbian
d5v6r2ytb2 Thank you for confirming that too!
azedgetech
Great request. Let's not forget Grok.
rossstokes
azedgetech agree Grok is important to add
Narek Zograbian
planned
brucerfleck
If we are able to BYOK, I would like to suggest the following priority of models:
GPT 4o
Sonnet 3.5
Perplexity
Gemini 1.5
Open source (Llama, Mistral)
I rank Perplexity at 3 because there is no better engine for gathering research with sources.
If Taskade is able to work with multiple models internally and push an output via webhook or API, we will not need to use tools like Zapier or Make. This would make Taskade even more valuable!
Narek Zograbian
brucerfleck We're looking into this!
artewebnet
brucerfleck If you would consider a free alternative to perplexity, tavily.com. it's not as fancy and pretty looking but it gets the research job done efficiently. I'm pretty sure you will have a new item on the list.
rossstokes
brucerfleck GROK as it has the broadest and most current perspective on whats available to draw from.
Heidi Briones
API keys would be the best way, I think
Narek Zograbian
under review
r
ryantaskade
Merged in a post:
choose your llm (gpt4o, sonnet 3.5, opus, and others)
floriane.c
like in Merlin or Perplexity
Load More
→