cicada
Start free
AI & automation · Connects with an API key

An AI teammate for LLM API.

Connect LLM API and your Cicada agent works in it for you: 12 LLM API actions, from looking things up to making changes. Ask from iMessage, WhatsApp, Slack or the app, and keep it read-only if you only want it to look.

Start free

300 free credits. No card. Read-only if you want.

Things to ask about LLM API
  • Run these files through LLM API and send me the results.
  • Use LLM API on this list and put the output in a sheet.
  • Check LLM API every morning and tell me what's new.
  • Compare this week's LLM API output with last week's.
Text it, Slack it, or type it in the app. Swap in your own details.
What Cicada can do in LLM API

12 LLM API actions, picked for what you ask.

About LLM API: LLM API provides a unified inference API for text, embeddings, images, audio, video, files, and batch workloads across multiple AI providers.

Reads

5 in all · always allowed
  • Discover Models
    Return one model's full live capabilities by ID, or browse a compact, bounded view of the live…
  • List or Get Files
    Return metadata for one project file by ID, or one provider-default page of project file metadata…
  • List or Get Batches
    Return one asynchronous batch and its latest lifecycle, token, and cost status by ID, or one…
  • Get Account and Credits
    Return the connected user, project, organization, purchased and bonus credit balances, funding…
  • Count Anthropic Message Tokens
    Count input tokens for an Anthropic-compatible message request without generating a model response.

Changes

7 in all · off when LLM API is read-only
  • Delete File
    Permanently delete a caller-owned or explicitly authorized project file.
  • Create Response
    Generate one complete, non-streaming OpenAI Responses-compatible result from text or structured…
  • Create Embeddings
    Create vector embeddings for one text or a batch of texts with a selected embedding model.
  • Create Chat Completion
    Generate a complete, non-streaming OpenAI-compatible chat response from role-based messages,…
  • Create Anthropic Message
    Generate one complete, non-streaming Anthropic-compatible message with flexible content blocks,…
  • Cancel Batch
    Request best-effort cancellation of an in-progress batch.
  • Submit Batch
    Create an asynchronous batch from an existing purpose=batch file ID, or upload a JSONL input file…

Showing 12 of 12. Your agent can use every one of them; you don't pick them, you ask for the outcome.

How it works

Connected in a minute. In your control after that.

  1. Connect LLM API

    Open Connections, find LLM API and paste an API key from your LLM API account settings. Cicada checks it works before saving it.

  2. Choose what it may do

    Full, Ask first or Read-only, for the whole workspace. Share LLM API with the team, or keep it under each person's own login.

  3. Ask from anywhere

    Text your agent on iMessage or WhatsApp, message it in Slack or the app, or put a LLM API job on a schedule: every morning, every Friday.

Works with your other tools

LLM API, together with the rest of your stack.

Ask for an outcome that spans apps and your agent pulls from each one, cross-checks them and sends back one answer.

More ai & automation integrations

Faraday integrationMem0 integrationScale ai integrationGoogle Cloud Vision integrationCohere integrationLyzr integrationHoncho integrationBolna integration

Often used alongside

Gmail integrationSlack integrationGoogle Sheets integrationGoogle Calendar integration

See all 888 integrations

Questions

LLM API and Cicada, answered.

Does Cicada integrate with LLM API?

Yes. LLM API is one of the 888 apps with a page here, and it connects with an API key. Once it's connected, every agent in your workspace can use it from any channel you talk to them on.

How do I connect LLM API?

Open Connections, find LLM API and paste an API key from your LLM API account settings. Cicada checks it works before saving it.

What can Cicada do in LLM API?

12 actions: 5 that read from LLM API and 7 that change things in it, for example discover models, list or get files, list or get batches. It picks the right ones for what you ask and chains them with your other apps.

Can I stop Cicada changing things in LLM API?

Yes. In Connections, set LLM API to Read-only and no agent in your workspace can create, change or delete anything in it; it can still read. Ask first lets it act but makes it check with you before each change.

Can I ask about LLM API from my phone?

Yes. Text your agent on iMessage or WhatsApp, or message it in Slack or the app. It answers in the same thread, and it can run LLM API jobs on a schedule, like every morning at 8.

Is my LLM API data safe?

Your LLM API login or key is stored on the server and never appears in a conversation. Disconnecting removes it. Every action an agent takes is in your activity log, and your data isn't used to train models.

One teammate. The output of a team.

Works nights, remembers every decision, answers in the thread. Start free with 300 credits.

Start free