LFM2.5-Embedding-350M is a text embedding model from Liquid AI. It produces 1,024-dimensional embeddings for retrieval and semantic search.
Successful OpenRouter requests and embeddings may be retained and used to train Liquid models.
Modalities
Context
512
Released
Aug 18, 2026
LFM2.5-Embedding-350M is a text embedding model from Liquid AI. It produces 1,024-dimensional embeddings for retrieval and semantic search. Successful OpenRouter requests and embeddings may be retained and used to train Liquid models.
LFM2.5-Embedding-350M accepts up to 512 tokens per input. Longer text has to be split into multiple inputs.
LFM2.5-Embedding-350M accepts text as input and returns embedding vectors.
LFM2.5-Embedding-350M was released on August 18, 2026.
Token volume and request traffic to this model over time.