Use LLM API with
Sokko.
Connect LLM API and tell Sokko what to do. It runs the actions you ask for and reacts to what happens. No workflows, no code.
Works with 1,000+ tools · No code required
Actions
Everything Sokko can do in LLM API
Every LLM API action Sokko can run. Ask for one in a sentence and it's done.
Cancel Batch
Request best-effort cancellation of an in-progress batch. Return the provider's actual batch state without implying cancellation took effect; work may still finish and incur charges before the request is applied.
Count Anthropic Message Tokens
Count input tokens for an Anthropic-compatible message request without generating a model response.
Create Anthropic Message
Generate one complete, non-streaming Anthropic-compatible message with flexible content blocks, system prompts, and tool use.
Create Chat Completion
Generate a complete, non-streaming OpenAI-compatible chat response from role-based messages, optionally using tools, multimodal content, structured output, reasoning, or web search supported by the selected model.
Create Embeddings
Create vector embeddings for one text or a batch of texts with a selected embedding model.
Create Response
Generate one complete, non-streaming OpenAI Responses-compatible result from text or structured input, preserving reasoning and tool items.
Delete File
Permanently delete a caller-owned or explicitly authorized project file. This destructive operation cannot be undone; a missing file fails with not found rather than reporting a successful deletion.
Discover Models
Return one model's full live capabilities by ID, or browse a compact, bounded view of the live model catalog using local capability filters.
Get Account and Credits
Return the connected user, project, organization, purchased and bonus credit balances, funding mode, and balance gating in one account-status read.
List or Get Batches
Return one asynchronous batch and its latest lifecycle, token, and cost status by ID, or one provider-default page of project batches when no batch ID is supplied. List mode supports provider cursor pagination.
List or Get Files
Return metadata for one project file by ID, or one provider-default page of project file metadata when no file ID is supplied. List mode supports purpose filtering and provider cursor pagination.
Submit Batch
Create an asynchronous batch from an existing purpose=batch file ID, or upload a JSONL input file with purpose=batch and create the batch in one call.
Get connected
Live in your Slack in two minutes.
No workflows to wire up. Turn on the tools you already use, and your agent gets to work.
Add to Slack
1
Add Sokko to Slack
One click from the Slack marketplace. Your whole team gets Sokko at once.
2
Connect your tools
Sokko works with 1,000+ apps and any MCP server.
Martin
9:53 AM
@Sokko
What can you do with LLM API?
3
Put Sokko to work
@mention Sokko in any channel and it gets going. Minutes, not a weekend.
Questions, answered.
Sokko is an AI assistant that lives in your Slack. Connect your apps, ask for what you need in plain language, and Sokko takes the work off your plate.
Sign up to Sokko, ask Sokko to connect to LLM API, and approve the connection when prompted. From then on you can ask Sokko to do things in LLM API whenever you need.
No. There's nothing to build or configure. You ask Sokko in Slack the same way you'd ask a colleague, and Sokko handles the rest.
Yes. Ask once and tell Sokko when to repeat it, like every Monday at 9am, and it becomes a routine that runs without you.
Read and act on data in LLM API, and trigger workflows when something changes there. Tell Sokko the outcome you want and it handles the rest.
Yes. Sokko connects to 1,000+ apps and any MCP server, so you can ask for tasks that span LLM API and the rest of your stack in a single request.