Text Embeddings Inference

Text Embeddings Inference endpoint info

get/info

Response

Served model info

auto_truncateboolean required

docker_labelstring nullable

max_batch_requestsinteger nullable

max_batch_tokensinteger required

max_client_batch_sizeinteger required

max_concurrent_requestsinteger required

Router Parameters

max_input_lengthinteger required

model_dtypestring required

model_idstring required

Model info

model_shastring nullable

served_model_namestring required

shastring nullable

tokenization_workersinteger required

versionstring required

Router Info

Example response

{
  "docker_label": "null",
  "model_dtype": "float16",
  "model_id": "thenlper/gte-base",
  "model_sha": "fca14538aa9956a46526bd1d0d11d69e19b5a101",
  "model_type": {
    "classifier": {
      "id2label": {
        "0": "LABEL"
      },
      "label2id": {
        "LABEL": 0
      }
    }
  },
  "served_model_name": "thenlper/gte-base",
  "sha": "null",
  "version": "0.5.0"
}

Changes

Changed in 6 of the 42 revisions of this API.54

Jan 21, 2026c29c7efc01821See the full diff
- ○
  added the required property served_model_name to the response with the 200 status
  response-required-property-added
Jun 28, 2024b923798e38681See the full diff
- ○
  added the required property auto_truncate to the response with the 200 status
  response-required-property-added
This revision also has 4 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
Jan 26, 202451015074a1261See the full diff
- ▲
  added subschema #3 to the model_type response property oneOf list for the response status 200
  response-property-one-of-added
Nov 15, 2023c4554b0fed8e11See the full diff
- ▲
  removed the required property model_pooling from the response with the 200 status
  response-required-property-removed
- ○
  added the required property model_type to the response with the 200 status
  response-required-property-added
Oct 16, 2023bd8a676e06821See the full diff
- ○
  added the required property model_pooling to the response with the 200 status
  response-required-property-added
Oct 13, 20238c00768ef7033See the full diff
- ▲
  removed the required property auto_truncate from the response with the 200 status
  response-required-property-removed
- ▲
  removed the required property model_type from the response with the 200 status
  response-required-property-removed
- ▲
  removed the required property served_model_name from the response with the 200 status
  response-required-property-removed
This revision also has 30 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

Full history