Cerebras
Cerebras ultra-fast LLM inference
Cerebras is the AI inference company whose Wafer-Scale Engine custom hardware delivers among the fastest token generation in the industry — typically 5-10× faster than GPU-based inference for Llama and similar open-source models. Tiny Command exposes two actions, no triggers: Chat Completion (against Llama 3.1 8B, Llama 3.1 70B, Llama 3.3 70B, plus other open-weight models hosted on Cerebras inference, using OpenAI-compatible message-array shape), List Models. The connection uses a Cerebras API key from cloud.cerebras.ai. The speed advantage is the only reason to pick Cerebras — for workflows where you'd otherwise use Groq (also extreme inference speed) or where waiting for OpenAI's 50-100 tokens/sec slows your agent chains. For non-speed-sensitive workloads, OpenAI/Anthropic still win on model capability, and cheaper open-source providers (DeepInfra, Together) match Cerebras on price for non-speed-sensitive use cases.
Do anything Cerebras can do, from a workflow.
Every action accepts dynamic inputs from upstream nodes, whether that's an AI output, a form field, or a search result.
| Action | What it does |
|---|---|
| Cerebras Chat Completion | Runs chat completion against Cerebras's custom-hardware-served Llama models. Extreme speed (1000-2000+ tokens/sec) is the value — for multi-step agent workflows, the latency win stacks meaningfully across calls. |
| List Cerebras Models | Returns the current Cerebras-hosted model catalog — primarily Llama 3.1/3.3 variants. New models added as Cerebras expands their LPU-optimised lineup. |
Pre-built Cerebras workflows.
Clone any recipe and customize it in one click. Every recipe is fully editable.
Three things worth knowing.
Tiny Command counts a run the moment a trigger fires. Filtering early means only matching events spend your usage budget.
Connect Cerebras once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.
Every Cerebras field shows up in the visual picker for downstream nodes. The raw payload is there for power users, optional for everyone else.
Questions about the Cerebras integration.
If we missed yours, ping support. We usually reply within an hour.
How do I connect Cerebras to Tiny Command?
What Cerebras triggers does Tiny Command support?
What Cerebras actions can I run from a workflow?
Is the Cerebras integration real-time?
Do I need to write code to use Cerebras with Tiny Command?
How much does the Cerebras integration cost?
More communication apps people connect.
Same category as Cerebras, ordered by how often teams pair them. Hover the carousel to pause.
Do more with Cerebras.
Wire it to Slack, Notion, HubSpot, Stripe, or any of the other 438 apps in our catalog. Setup takes roughly two minutes. Free to try, no credit card.
