Models
Agents
Infrastructure
Pricing
Docs
Security
Contact us
Log in
Open app
Models
Agents
Infrastructure
Pricing
Docs
Security
Show navigation
Docs
/
LitAI
/
Features
Features
Async LLM generation
Fallback and retry
Manage models
Multi-turn conversation memory
Streaming
Async LLM generation
In applications that handle multiple users, API calls, or agents, blocking LLM requests can become a bottleneck. Python’…
Fallback and retry
In production environments, LLM APIs can fail due to rate limits, timeouts, or provider outages. Manually handling retri…
Manage models
In most LLM applications, switching between models or providers involves setting up separate APIs, handling varied param…
Multi-turn conversation
LLMs are stateless by default. Every API call is treated independently so they forget previous questions, answers, or fo…
Streaming
Most LLM APIs return full responses only after the entire output is generated, which can slow down UX and delay response…
Tools
AI models (LLMs) today can only respond with text - they can’t look up live information or take actions - so apps built …
Granular billing
Organize billing for API calls at organization, teamspace and user level. Your API key decides where the cost of API cal…
Was this page helpful?
Yes
No
Thanks for the feedback.
What went wrong?
Inaccurate or out of date
Hard to understand
Missing information
Hard to find things / poorly organized
Code sample didn't work
Something is broken (link, image, layout)
Cancel
Send
Share with AI
Copy link for LLM
Copy page for LLM
Open with AI
Open in ChatGPT
Open in Claude
Was this helpful?
Thanks for the feedback.
What went wrong?
Inaccurate or out of date
Hard to understand
Missing information
Hard to find things / poorly organized
Code sample didn't work
Something is broken (link, image, layout)
Cancel
Send
↑
↓
Navigate
↵
Open
⌘
↵
New tab
esc
Close