---
title: "Text Generation Inference endpoint info"
method: GET
path: "/info"
tags: ["Text Generation Inference"]
---

# Text Generation Inference endpoint info

`GET /info`

Text Generation Inference endpoint info

## Response `200`

Served model info

- Info
  - `docker_label` string, nullable
  - `max_batch_total_tokens` integer, required
  - `max_best_of` integer, required
  - `max_concurrent_requests` integer, required — Router Parameters
  - `max_input_length` integer, required
  - `max_stop_sequences` integer, required
  - `max_total_tokens` integer, required
  - `max_waiting_tokens` integer, required
  - `model_device_type` string, required
  - `model_dtype` string, required
  - `model_id` string, required — Model info
  - `model_pipeline_tag` string, nullable
  - `model_sha` string, nullable
  - `sha` string, nullable
  - `validation_workers` integer, required
  - `version` string, required — Router Info
  - `waiting_served_ratio` number, float, required

## Changes

- **2023-05-09** `36489c7b42f0` — 12 info
  - added the optional property `docker_label` to the response with the `200` status
  - added the required property `max_batch_total_tokens` to the response with the `200` status
  - added the required property `max_best_of` to the response with the `200` status
  - added the required property `max_concurrent_requests` to the response with the `200` status
  - …8 more
- **2023-04-18** `de34bec00da8` — 1 info
  - endpoint added
- **2023-02-03** `a9059df72b92` — 1 breaking
  - api path removed without deprecation

[Change history](https://skmtc.dev/preemo-inc/apis/text-generation-inference/changes/info/get.md)

---

[API](https://skmtc.dev/preemo-inc/apis/text-generation-inference.md) · [All operations](https://skmtc.dev/preemo-inc/apis/text-generation-inference/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/preemo-inc/text-generation-inference/revisions/12de8108e4dd/schema)