Update a pod
Update selected settings on an existing Runpod Pod while preserving omitted fields, with guidance on mutable fields and restart behavior.
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.
Console sessions (Clerk JWTs) act for the signed-in user. To act for a team instead, also send X-Team-Id: <team_id>; it applies only when the user owns or belongs to that team, otherwise the request runs against the user's own account. API keys created inside a team already act for that team and do not need the header.
Body
Reusable container configuration shared across templates, pods, and serverless endpoints. Adding a field here automatically propagates to all three resources.
The container's command, as a single raw string. This is the field entrypoint and cmd encode into, exposed in its stored form.
Two shapes are accepted. A bare shell string is treated as CMD and split into arguments, which is what the console's "Container start command" field writes. A JSON object of the form {"entrypoint":[...],"cmd":[...]} sets either or both explicitly.
Responses always return both representations: args exactly as stored, plus the deconstructed entrypoint and cmd. Supplying args together with entrypoint or cmd is allowed only when they describe the same command, so a read-modify-write client can send back everything it received. Send "" to clear, omit to leave unchanged.
"--model meta-llama/Llama-3-8B --max-model-len 8192"
"{\"entrypoint\":[\"/bin/bash\",\"-c\"],\"cmd\":[\"python -u main.py\"]}"
""
Changes to a pod's mounts. Each entry names one volume by volumeId
and changes only that volume; volumes that are not listed, and kinds
that are omitted, are left as they are. Omitting mounts or sending
{} changes nothing.
- A listed volume the pod does not have is mounted at
path. - A listed volume the pod already has moves to
path(or stays put whenpathis omitted). remove: trueunmounts the volume. It cannot be combined withpath, and the volume must be mounted on the pod.- To swap a volume, remove the old one and add the new one in the same request.
Limits are checked against the pod as it would be after the request and rejected with 400: at most 4 network volumes and 1 global volume, and a volume disk cannot share a pod with network or global volumes. A volume disk can be added to a pod that has no volumes mounted (or unmounts them all in the same request), and it can only grow. Removing a volume disk is not supported yet.
ID of a pod template whose container settings are applied as
if they were provided in this PATCH body (image, args, disk,
ports, env, registry — mounts are not applied on update).
Explicit body fields override the template's; env merges
template and body per key (body wins) and, per PATCH
semantics, replaces the pod's env. One-time application —
no link to the template is retained. Must be one of your
templates or a public template (unknown or inaccessible ID
→ 404); must not be a serverless template (→ 422).
"30zmvf89kd"
Response
OK
Reusable container configuration shared across templates, pods, and serverless endpoints. Adding a field here automatically propagates to all three resources.
The container's command, as a single raw string. This is the field entrypoint and cmd encode into, exposed in its stored form.
Two shapes are accepted. A bare shell string is treated as CMD and split into arguments, which is what the console's "Container start command" field writes. A JSON object of the form {"entrypoint":[...],"cmd":[...]} sets either or both explicitly.
Responses always return both representations: args exactly as stored, plus the deconstructed entrypoint and cmd. Supplying args together with entrypoint or cmd is allowed only when they describe the same command, so a read-modify-write client can send back everything it received. Send "" to clear, omit to leave unchanged.
"--model meta-llama/Llama-3-8B --max-model-len 8192"
"{\"entrypoint\":[\"/bin/bash\",\"-c\"],\"cmd\":[\"python -u main.py\"]}"
""
Lifecycle status of a pod.
PROVISIONING— pod is being allocatedSTARTING— container is startingRUNNING— container is healthyEXITED— container exited (stopped)ERROR— container is in an unrecoverable error stateTERMINATED— pod has been permanently deleted
PROVISIONING, STARTING, RUNNING, EXITED, ERROR, TERMINATED Storage mounts attached to a pod. persistent (the volume disk) is
mutually exclusive with both network and global (enforced at the
handler with 400 if combined). A pod takes up to 4 network volumes
and 1 global volume. Every network volume must be in the pod's data
center, each volume may be listed once, and mount paths must not
overlap; a request that breaks one of these is rejected. To change a
pod's mounts after creation, see UpdatePodMounts.
CUDA version reported by the host machine. Retained while the pod is stopped — a stopped pod keeps its machine assignment and resumes onto the same host. Null means unknown or not applicable (CPU pods, or a host that has not reported one), not that CUDA is absent.
"12.8"
The tags on this resource that are visible to the caller. Keys and values are returned exactly as stored. Tags under the reserved runpod: prefix, such as the cost center, are never listed here. Absent when the resource's tags are unavailable to the caller; an empty array means none are visible.