Skip to main content
PATCH
Update a serverless endpoint

Authorizations

Authorization
string
header
required

Runpod API key authentication. Generate an API key in the Runpod console and send it in the Authorization header as Bearer <api_key>. Keys are scoped to the permissions granted when created; requests may return 403 when a valid key lacks access to the requested resource or action.

Path Parameters

id
string
required

Serverless endpoint identifier

Body

application/json

Only provided fields are changed.

image
string

Docker image reference

Example:

"runpod/pytorch:2.8.0-py3.11-cuda12.8.1"

args
string

Arguments passed to the container entrypoint

Example:

""

disk
integer

Container disk in GB (ephemeral, wiped on restart)

Required range: x >= 1
Example:

50

ports
string[]

Exposed ports, formatted as port/protocol

Example:
env
object

Environment variables as key-value pairs

Example:
registry
string | null

Container registry credential ID (for private images)

Example:

null

name
string
Minimum string length: 1
gpu
object
workers
object
scaling
object
dataCenterIds
string[]

Preferred data centers for placement. Omit or pass an empty array to let the scheduler choose.

networkVolumes
string[]
timeout
integer
flashboot
enum<string>

FlashBoot cold-start acceleration mode.

  • OFF — disabled
  • FLASHBOOT — enabled
  • PRIORITY_FLASHBOOT — enabled with priority capacity
Available options:
OFF,
FLASHBOOT,
PRIORITY_FLASHBOOT

Response

OK

Reusable container configuration shared across templates, pods, and serverless endpoints. Adding a field here automatically propagates to all three resources.

id
string
required
Example:

"ep_abc123"

name
string
required
Example:

"my-inference"

workers
object
required
scaling
object
required
dataCenterIds
string[]
required
Example:
networkVolumes
string[]
required
Example:
timeout
integer
required

Per-request execution timeout in milliseconds

Example:

300000

flashboot
enum<string>
required

FlashBoot cold-start acceleration mode.

  • OFF — disabled
  • FLASHBOOT — enabled
  • PRIORITY_FLASHBOOT — enabled with priority capacity
Available options:
OFF,
FLASHBOOT,
PRIORITY_FLASHBOOT
createdAt
string<date-time>
required
Example:

"2026-03-13T20:00:00Z"

image
string

Docker image reference

Example:

"runpod/pytorch:2.8.0-py3.11-cuda12.8.1"

args
string

Arguments passed to the container entrypoint

Example:

""

disk
integer

Container disk in GB (ephemeral, wiped on restart)

Required range: x >= 1
Example:

50

ports
string[]

Exposed ports, formatted as port/protocol

Example:
env
object

Environment variables as key-value pairs

Example:
registry
string | null

Container registry credential ID (for private images)

Example:

null

type
enum<string>

Request-routing semantics for a modern serverless endpoint.

  • QUEUE_BASED — submit asynchronous or synchronous jobs through the managed queue.
  • LOAD_BALANCING — send requests directly to worker-defined HTTP paths.
Available options:
QUEUE_BASED,
LOAD_BALANCING
requestUrls
object

Request submission URLs appropriate to the endpoint's top-level type. Queue-based endpoints provide run and runSync; load-balancing endpoints provide base because their paths are worker-defined.

gpu
object | null
cpu
object | null

Read-only. Present for CPU serverless endpoints; CPU create/update is not yet supported.