All integrationsAI Models
LiteLLM
Manage your LiteLLM Proxy: send prompts to its models, create, limit, block and replace keys, manage teams and users, and read what each request cost.
- actions
- 20
- triggers
- 8
Triggers
Start a workflow when something happens in LiteLLM.
- New keyRuns when a key is created on your proxy. Keys already there when the workflow is turned on don't start it.
- Key nearing its budgetRuns when a key has spent a share of its budget, such as 80% or all of it, so someone can raise it or warn its owner. Runs again after the budget starts over and fills up again.
- Key about to expireRuns when a key will stop working soon, so it can be given a new end date or replaced before anything breaks.
- New teamRuns when a team is created on your proxy. Teams already there when the workflow is turned on don't start it.
- Team nearing its budgetRuns when a team has spent a share of its budget, such as 80% or all of it. Runs again after the budget starts over and fills up again.
- New userRuns when someone is added to your proxy as a user. Users already there when the workflow is turned on don't start it.
- New requestRuns for each request made through your proxy, with its model, cost, tokens and key. On a busy proxy, narrow it to one model or team.
- Request failedRuns when a request through your proxy fails, such as a provider error or a rate limit, with the error.
Actions
Steps a workflow can run in LiteLLM.
- Send a promptSend a prompt to one of your proxy's models and get its reply, with the tokens it used and what it cost. The proxy's budgets and limits apply as usual.
- List modelsList the models set up on your proxy, with who serves each, what it does, its token limits and prices.
- List keysList the proxy's keys with their spend, budget, models and expiry, optionally only one team's or user's.
- Get keyGet one key's details: what it has spent, its budget, limits, models, expiry and whether it is blocked.
- Create keyCreate a key for an app or person to call your proxy with, with an optional budget, limits, models and end date. The key is in the result once only, as 'api_key'.
- Update keyChange a key's name, models, budget, limits or end date. Fields left empty keep their value.
- Block or unblock keyBlock a key so every request with it is refused, such as when it has leaked, or unblock it again.
- Replace keyReplace a key with a new one that keeps its settings and spend; the old key stops working. Needs LiteLLM Enterprise. The new key is in the result once only, as 'api_key'.
- Delete keyDelete a key for good, so requests with it are refused.
- List teamsList the proxy's teams with their members, budget, spend and models.
- Get teamGet one team's details: its members, budget, spend, models and keys.
- Create teamCreate a team, with an optional budget, limits and models that every key of the team shares.
- Update teamChange a team's name, models, budget or limits, or block it so none of its keys work. Fields left empty keep their value.
- Add team memberAdd someone to a team, by user or by email address. LiteLLM adds them as a user if the email is new.
- Remove team memberTake someone off a team, by user or by email address.
- Delete teamDelete a team and its keys, for good.
- List usersList the proxy's users with their role, budget and spend, optionally only one role or team.
- Create userAdd a person to your proxy, with a role, an optional budget and team, and a key of their own if asked.
- Update userChange a user's email, name, role, models or budget. Fields left empty keep their value.
- List request logsList the requests made through your proxy in a time range, newest first, with each one's model, cost, tokens, key, team and any error.
No actions match that.
Automate LiteLLM with Lodol.
Connect LiteLLM, then hand Lodol the job in Slack, Claude or ChatGPT.
Free plan, no credit card