{"id":"text-embeddings-inference","name":"Text Embeddings Inference","maker":"Hugging Face","url":"https://huggingface.co/docs/text-embeddings-inference","repo":"huggingface/text-embeddings-inference","summary":"A server from Hugging Face for serving embedding, reranking and sequence classification models.","details":"Text Embeddings Inference is a Rust server shipped as a Docker image, with an HTTP API that includes an OpenAI-compatible embeddings route. It loads models from the Hub and runs on CPU or GPU. It is the engine behind some hosted embedding endpoints.","open_source":true,"hosted":false,"speaks":["openai-api"],"also":["runtimes"],"verified":"2026-11-15","category":"retrieval","category_name":"Vector databases and retrieval","page":"https://modelmoot.com/tools/text-embeddings-inference","reviewed":"2026-11-15","checked":{"at":"2026-11-15T16:10:15.342Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}