Fireworks AI
Fireworks AI open-source model inference
Fireworks AI is the serverless inference platform optimised for open-source LLMs — competitive on price with Together and DeepInfra, with a focus on fine-tuning support and function calling. Tiny Command exposes three actions, no triggers: Chat Completion (against the Fireworks catalog — Llama 3.3, Mixtral, Qwen, DeepSeek V3, plus their own Firefunction V2 model optimised for function calling), Create Embeddings (sentence and document embeddings — BGE, gte-large, MTEB-strong models), List Models. The connection uses a Fireworks API key from fireworks.ai/account/api-keys. The API is OpenAI-compatible — same message-array shape, same function-calling shape (Firefunction V2 specifically advertises strong tool use). Fireworks's pricing is similar to DeepInfra (a few dollars per million input tokens for 70B+ models, much cheaper for smaller); the choice between them often comes down to which platform has the specific model you want at the latency you need.
Do anything Fireworks AI 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 |
|---|---|
| Fireworks Chat Completion | Runs chat completion against Fireworks-hosted open-source models. Notable for Firefunction V2 — Fireworks's fine-tuned Llama for reliable function calling. OpenAI-compatible shape. |
| Fireworks Embeddings | Generates embeddings from Fireworks-hosted models (BGE, GTE, sentence-transformers). For RAG-pipeline vector generation at competitive pricing. |
| List Fireworks Models | Returns the Fireworks model catalog with pricing. Useful for model-selection workflows and for per-model cost calculations. |
Pre-built Fireworks AI workflows.
Clone any recipe and customize it in one click. Every recipe is fully editable.
AI-triage every Fireworks AI event, ping the right channel only when it matters.
Every event matching a filter, appended to a running spreadsheet.
Turn Fireworks AI into a Notion-backed source of truth, auto-tagged.
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 Fireworks AI once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.
Every Fireworks AI 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 Fireworks AI integration.
If we missed yours, ping support. We usually reply within an hour.
How do I connect Fireworks AI to Tiny Command?
What Fireworks AI triggers does Tiny Command support?
What Fireworks AI actions can I run from a workflow?
Is the Fireworks AI integration real-time?
Do I need to write code to use Fireworks AI with Tiny Command?
How much does the Fireworks AI integration cost?
More communication apps people connect.
Same category as Fireworks AI, ordered by how often teams pair them. Hover the carousel to pause.
Do more with Fireworks AI.
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.
