Get a serverless endpoint
Returns a single serverless endpoint by ID.
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
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"
Autoscaling signal — a discriminated union on type: QUEUE_DELAY
(queue-based endpoints only) or REQUEST_COUNT. The scaler is chosen
independently of the endpoint's routing type and can be switched on
update.
- Option 1
- Option 2
Per-request execution timeout in milliseconds
300000
FlashBoot cold-start acceleration mode.
OFF— disabledFLASHBOOT— enabledPRIORITY_FLASHBOOT— enabled with priority capacity
OFF, FLASHBOOT, PRIORITY_FLASHBOOT Acceptable CUDA versions for worker placement, as major.minor. Empty means any version.
"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— submit asynchronous or synchronous jobs through the managed queue.LOAD_BALANCER— send requests directly to worker-defined HTTP paths. Configure viaenv:PORT(server port, default 80),PORT_HEALTH(health-check port, default 80), andHEALTH_CHECK_PATH(path the load balancer polls for worker health, default/ping).
QUEUE, LOAD_BALANCER Request URLs appropriate to the endpoint's top-level type.
Queue-based endpoints provide job submission and management URLs;
load-balancing endpoints provide base and health because their
remaining paths are worker-defined.
- Option 1
- Option 2
Read-only. Present for CPU serverless endpoints; CPU create/update is not yet supported.