Together AI open-source model inference
Together AI is the inference platform for open-source ML models — one of the largest catalogs covering text (Llama, Mixtral, Qwen, DeepSeek), image (Flux, SDXL), code (CodeLlama, DeepSeek-Coder), embeddings, and audio models. Tiny Command exposes three actions, no triggers: Chat Completion (against text-generation models with the OpenAI-compatible message-array shape), Create Embeddings (embedding models in the catalog — BGE, GTE, M2-BERT), List Models. The connection uses a Together API key from api.together.xyz. Together's pricing is competitive across the board; the differentiation is catalog breadth — if you want to run a specific niche open-source model (a vision-language fine-tune, a particular embedding variant), Together often has it where Fireworks or DeepInfra might not. Plus Together offers dedicated endpoints (paid) for guaranteed throughput on a specific model — useful for production workflows that need predictable latency.
No credit card required · Set up in under 2 minutes
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 | Open action |
|---|---|---|
| Chat Completion | Runs an open-weight chat model (Llama 4, DeepSeek-V3, Qwen, Mixtral, etc.) on Together AI's fast inference platform. OpenAI-compatible request shape so existing chat-completion code mostly works as is. | |
| Create Embeddings | Generates vector embeddings using one of Together's open-weight embedding models (e.g. BGE, M2-BERT, UAE). Use for RAG, semantic search, or clustering pipelines. | |
| List Models | Lists models available on Together AI with their type (chat, language, embeddings, image) and pricing tier. Useful for surfacing a dynamic model picker. |
Clone any recipe and customize it in one click. Every recipe is fully editable.
Tiny Command counts a run the moment a trigger fires. Filtering early means only matching events spend your usage budget.
Connect Together AI once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.
Every Together AI field shows up in the visual picker for downstream nodes. The raw payload is there for power users, optional for everyone else.
If we missed yours, ping support. We usually reply within an hour.
Same category as Together AI, ordered by how often teams pair them. Hover the carousel to pause.
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.