Update a serverless endpoint
Partially updates a serverless endpoint. This is a PATCH: only the
fields present in the body are changed; omitted fields are left
untouched. See UpdateEndpointRequest for the full body.
Mutable fields: name, gpu, workers (min/max), scaling
(type/value/idleTimeout), dataCenterIds, networkVolumes,
timeout, flashboot, and the container settings (image, args,
disk, ports, env, registry).
Returns 200 with the full updated endpoint. Effect timing differs
by field: scaling and worker-bound settings (workers, scaling,
timeout) are applied to the autoscaler promptly, while
container-affecting changes (e.g. image, env) create a new
endpoint release that rolls out as workers cycle — in-flight workers
keep the previous version until they are replaced. Track rollout via
listEndpointReleases.
Authorizations
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
Serverless endpoint identifier
Body
Only provided fields are changed.
Docker image reference
"runpod/pytorch:2.8.0-py3.11-cuda12.8.1"
Arguments passed to the container entrypoint
""
Container disk in GB (ephemeral, wiped on restart)
x >= 150
Exposed ports, formatted as port/protocol
Environment variables as key-value pairs
Container registry credential ID (for private images)
null
1Preferred data centers for placement. Omit or pass an empty array to let the scheduler choose.
FlashBoot cold-start acceleration mode.
OFF— disabledFLASHBOOT— enabledPRIORITY_FLASHBOOT— enabled with priority capacity
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.
"ep_abc123"
"my-inference"
Per-request execution timeout in milliseconds
300000
FlashBoot cold-start acceleration mode.
OFF— disabledFLASHBOOT— enabledPRIORITY_FLASHBOOT— enabled with priority capacity
OFF, FLASHBOOT, PRIORITY_FLASHBOOT "2026-03-13T20:00:00Z"
Docker image reference
"runpod/pytorch:2.8.0-py3.11-cuda12.8.1"
Arguments passed to the container entrypoint
""
Container disk in GB (ephemeral, wiped on restart)
x >= 150
Exposed ports, formatted as port/protocol
Environment variables as key-value pairs
Container registry credential ID (for private images)
null
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.
QUEUE_BASED, LOAD_BALANCING 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.
- Option 1
- Option 2
Read-only. Present for CPU serverless endpoints; CPU create/update is not yet supported.