FFlow
RUStart free

All nodes/AI/RAG

Embedding Model

Embedding model configuration (analogous to the LLM node). Links to Embed Text. Does not perform computations itself.

Embedding Model
Embedding

Type in the graph: embedding

Try it

The model behind a vector

This node names the model; Embed Text computes the vector with it.

Entry
Embedding Model
Embed Text▶
Exit▶
  • Execute + Data
  • Embedding
Press “Copy nodes”, open the editor and hit Ctrl+V on the canvas.

Runs as pasted Before running, set: an embedding model available in the workspace.

When to use it

This node computes nothing — it names the model that Embed Text will use. It has no other consumer: the link_embedding wire is accepted by that node alone.

If a vector is computed once in the graph, pick the model directly in the Embedding Model field of Embed Text — a separate node is not needed then. It pays off when several Embed Text nodes must share one model: you change one value instead of three.

How it works

The node has no inputs and no run port, so it never becomes a step of its own. Its value is computed when a consumer asks for it, and it carries exactly one field — the model id.

The value from the port overrides the Embedding Model field on Embed Text, and that field goes inactive in the form. If the model here is empty anyway, the consumer falls back to its own field rather than to nothing.

The model list is the platform catalog plus the models of your workspace: a model of an OpenAI-compatible connection whose purpose is Embeddings shows up in the same dropdown. Tokens spent on your own key are not billed by the platform.

Common mistakes

  • Expecting it to pick the model for a knowledge base. A base fixes its model when it is created and never changes it. This node only affects what Embed Text computes with.
  • Wiring it into RAG Query or KB Write. The Embedding port of RAG Query expects a ready vector from Embed Text, not a model config, and a link_embedding wire will not connect there.
  • Expecting the node to run. It is configuration, not an action: no step of its own appears in the run log.
  • Leaving the model field empty. A graph with no model selected does not pass the check before a run or a deploy.

Inputs

—

Outputs

PortWirePayloadNotes
EmbeddingoutputEmbeddinglink_embedding—

Configuration

FieldTypeDefaultDescription
Embedding Modelmodelstringsentence_transformers/all-MiniLM-L6-v2

Options: sentence_transformers/all-MiniLM-L6-v2 — Sentence Transformers (Local) / all-MiniLM-L6-v2 (fast, 384-dim), lm_studio_embeddings/text-embedding-embeddinggemma-300m-qat — LM Studio Embeddings / text-embedding-embeddinggemma-300m-qat, sentence_transformers/all-mpnet-base-v2 — Sentence Transformers (Local) / all-mpnet-base-v2 (better quality, 768-dim), openai/text-embedding-3-small — OpenAI Embeddings / text-embedding-3-small (recommended), openai/text-embedding-3-large — OpenAI Embeddings / text-embedding-3-large, openai/text-embedding-ada-002 — OpenAI Embeddings / text-embedding-ada-002, openrouter/openai/text-embedding-3-small — OpenRouter Embeddings / text-embedding-3-small, openrouter/openai/text-embedding-3-large — OpenRouter Embeddings / text-embedding-3-large, openrouter/openai/text-embedding-ada-002 — OpenRouter Embeddings / text-embedding-ada-002, openrouter/google/gemini-embedding-001 — OpenRouter Embeddings / gemini-embedding-001, openrouter/mistralai/mistral-embed-2312 — OpenRouter Embeddings / mistral-embed, openrouter/baai/bge-m3 — OpenRouter Embeddings / bge-m3, openrouter/baai/bge-large-en-v1.5 — OpenRouter Embeddings / bge-large-en-v1.5, openrouter/baai/bge-base-en-v1.5 — OpenRouter Embeddings / bge-base-en-v1.5, openrouter/intfloat/multilingual-e5-large — OpenRouter Embeddings / multilingual-e5-large, openrouter/intfloat/e5-large-v2 — OpenRouter Embeddings / e5-large-v2, openrouter/intfloat/e5-base-v2 — OpenRouter Embeddings / e5-base-v2, openrouter/thenlper/gte-large — OpenRouter Embeddings / gte-large, openrouter/thenlper/gte-base — OpenRouter Embeddings / gte-base, openrouter/sentence-transformers/all-minilm-l6-v2 — OpenRouter Embeddings / all-MiniLM-L6-v2, openrouter/sentence-transformers/all-minilm-l12-v2 — OpenRouter Embeddings / all-MiniLM-L12-v2, openrouter/sentence-transformers/all-mpnet-base-v2 — OpenRouter Embeddings / all-mpnet-base-v2, openrouter/qwen/qwen3-embedding-8b — OpenRouter Embeddings / qwen3-embedding-8b, openrouter/qwen/qwen3-embedding-4b — OpenRouter Embeddings / qwen3-embedding-4b, openrouter/google/gemini-embedding-2 — OpenRouter Embeddings / gemini-embedding-2, openrouter/perplexity/pplx-embed-v1-4b — OpenRouter Embeddings / pplx-embed-v1-4b, openrouter/perplexity/pplx-embed-v1-0.6b — OpenRouter Embeddings / pplx-embed-v1-0.6b, openrouter/mistralai/codestral-embed-2505 — OpenRouter Embeddings / codestral-embed, openrouter/nvidia/nemotron-3-embed-1b:free — OpenRouter Embeddings / Nemotron 3 Embed 1B (free), openrouter/nvidia/llama-nemotron-embed-vl-1b-v2:free — OpenRouter Embeddings / Llama Nemotron Embed VL 1B V2 (free)