---
title: "Changes to Create a deployment"
method: POST
path: "/projects/{projectId}/endpoints/{endpointId}/deployments"
---

# Changes to Create a deployment

`POST /projects/{projectId}/endpoints/{endpointId}/deployments`

> Every recorded change to this endpoint, newest first.

## Timeline

Changed in 2 of 15 revisions.

- **2026-08-31** `f4885bc38424` — 1 breaking, 8 warning, 8 info
- **2026-07-26** `0c4fdad77435` — 1 info

## Changes

- **2026-08-31** `f4885bc38424` — 1 breaking, 8 warning, 8 info
  - request property `autoscaling/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name` was restricted to a list of enum values
  - added the new `cache_hit_rate` enum value to the `autoscaling/allOf[#/components/schemas/DE.AutoscalingResponse]/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name` response property for the response status `200`
  - added the new `decoding_speed` enum value to the `autoscaling/allOf[#/components/schemas/DE.AutoscalingResponse]/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name` response property for the response status `200`
  - added the new `e2e_latency` enum value to the `autoscaling/allOf[#/components/schemas/DE.AutoscalingResponse]/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name` response property for the response status `200`
  - added the new `gpu_utilization` enum value to the `autoscaling/allOf[#/components/schemas/DE.AutoscalingResponse]/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name` response property for the response status `200`
  - added the new `inflight_requests` enum value to the `autoscaling/allOf[#/components/schemas/DE.AutoscalingResponse]/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name` response property for the response status `200`
  - added the new `throughput_per_replica` enum value to the `autoscaling/allOf[#/components/schemas/DE.AutoscalingResponse]/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name` response property for the response status `200`
  - added the new `token_utilization` enum value to the `autoscaling/allOf[#/components/schemas/DE.AutoscalingResponse]/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name` response property for the response status `200`
  - added the new `ttft` enum value to the `autoscaling/allOf[#/components/schemas/DE.AutoscalingResponse]/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name` response property for the response status `200`
  - added the new `cache_hit_rate` enum value to the request property `autoscaling/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name`
  - added the new `decoding_speed` enum value to the request property `autoscaling/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name`
  - added the new `e2e_latency` enum value to the request property `autoscaling/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name`
  - added the new `gpu_utilization` enum value to the request property `autoscaling/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name`
  - added the new `inflight_requests` enum value to the request property `autoscaling/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name`
  - added the new `throughput_per_replica` enum value to the request property `autoscaling/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name`
  - added the new `token_utilization` enum value to the request property `autoscaling/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name`
  - added the new `ttft` enum value to the request property `autoscaling/allOf[#/components/schemas/DE.Autoscaling]/scalingMetrics/items/name`
- **2026-07-26** `0c4fdad77435` — 1 info
  - endpoint added

---

[Operation](https://skmtc.dev/together/apis/together-apis/docs/projects/:projectId/endpoints/:endpointId/deployments/post.md) · [API](https://skmtc.dev/together/apis/together-apis.md) · [Page](https://skmtc.dev/together/apis/together-apis/changes/projects/:projectId/endpoints/:endpointId/deployments/post)