/
HU
huggingface
/
Text Embeddings Inference
Search skmtc…
⌘K
Sign in
Sign in
APIs
Generators
Stacks
Projects
Docs
History
Schema
Sources
Subscribe
v1
latest
OpenAPI 3.0.3
Apache 2.0
2026-07-17
12
41
50.8 KB
Text Embeddings Inference
Decode input ids
post
/decode
Request body
DecodeRequest
required
ids
union
required
skip_special_tokens
boolean
Response
Decoded ids
string[]
required
Example response
[ "test" ]
All 12 operations
post
Decode input ids
post
Get Embeddings. Returns a 424 status code if the model is not an embedding model.
post
Get all Embeddings without Pooling.
post
Get Sparse Embeddings. Returns a 424 status code if the model is not an embedding model with SPLADE pooling.
get
Health check method
get
Text Embeddings Inference endpoint info
get
Prometheus metrics scrape endpoint
post
Get Predictions. Returns a 424 status code if the model is not a Sequence Classification model
post
Get Ranks. Returns a 424 status code if the model is not a Sequence Classification model with
post
Get Sentence Similarity. Returns a 424 status code if the model is not an embedding model.
post
Tokenize inputs
post
OpenAI compatible route. Returns a 424 status code if the model is not an embedding model.