Model deployment
A model deployment, called a serving in the API and the CLI, is a model running behind an endpoint on one of your devices. The platform starts it, keeps it up, and proxies calls to it, so a client never has to reach the device directly.
It is a service whose command the platform supplies rather than you: the model runs through the CLIKA runtime on the device, and the endpoints a client calls are derived from the model's type rather than configured by hand.
The commands sit under the v1 group, which is the runtime-facing part of the API.
Managing a serving
| Command | Purpose |
|---|---|
v1 servings | List servings. |
v1 servings-id <id> | Get one, with its state and its endpoint. |
v1 servings-create --body '<json>' | Create one. |
v1 servings-update-id <id> --body '<json>' | Change one. |
v1 servings-start <id> | Start it. |
v1 servings-stop <id> | Stop it without removing it. |
v1 servings-restart <id> | Restart it. |
v1 servings-delete-id <id> | Delete it. |
v1 projects-servings <id> | List one project's servings. |
clika-rt v1 servings
clika-rt v1 servings-id 4b7e0c1a-2d3e-4f50-6172-8394a5b6c7d8
Starting and stopping are separate from creating and deleting for the same reason they are on a service: stopping frees the device's accelerator while keeping the deployment and its configuration, so you can bring the same endpoint back without redefining it.
Calling a serving through the platform
clika-rt v1 servings-devices-proxy <id> <device_id> <upstream>
The proxy is how a client reaches a deployed model without a route to the device. You address the platform, name the serving, the device and the upstream path, and the platform forwards the call to the model and the response back.
<upstream> is the path on the model's own endpoint. Which paths exist depends on the model's type, because the runtime exposes the endpoints that type implies rather than a fixed set.
Four variants cover the HTTP methods, since a proxied call has to carry the caller's own verb:
| Command | Method it proxies |
|---|---|
v1 servings-devices-proxy | GET |
v1 servings-devices-proxy-create | POST |
v1 servings-devices-proxy-update | PUT |
v1 servings-devices-proxy-update-patch | PATCH |
v1 servings-devices-proxy-delete | DELETE |
For anything beyond a check that the endpoint answers, call the proxy endpoint from your own client rather than through the CLI. The CLI's value here is discovery: v1 servings-id tells you the serving is up and what its endpoint is.
What it needs
A model deployment consumes a licensed inference engine on the device, so the same entitlement gate that applies to a job definition applies here. A device without the engine package cannot host one, and the refusal is not forceable. Provision the engine with devices engine-package <name-or-id>, and see runtime licenses for the entitlement that permits it.
Full command reference
Every command below is generated from the deployment's own API description, so
one subcommand is exactly one platform operation. Each entry names the method,
the endpoint and the MCP tool name, so the same operation is
identifiable whichever surface you drive it from. Path parameters are positional
arguments, query parameters are flags, and a request body is --body or
--body-file. The hand-written commands, the ones that stream, propagate an
exit code, or hand your terminal to ssh, carry no operation line.
The prose above covers the commands most people reach for. This section is the complete surface, for when you need the flag you have not used before.
clika-rt v1
v1 has 13 subcommands on this page.
clika-rt v1 servings
List model servings
clika-rt v1 servings [flags]
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: GET /api/v1/servings. MCP tool name: get_v1_servings.
clika-rt v1 servings-create
Create model serving
clika-rt v1 servings-create [flags]
| Flag | Type | Default | Meaning |
|---|---|---|---|
--body | string | none | request body (inline JSON) |
--body-file | string | none | request body (path to a JSON file) |
--raw | bool | false | print raw response without pretty-printing |
Endpoint: POST /api/v1/servings. MCP tool name: post_v1_servings.
clika-rt v1 servings-delete-id
Delete model serving
clika-rt v1 servings-delete-id <id> [flags]
Positional arguments: required <id>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: DELETE /api/v1/servings/{id}. MCP tool name: delete_v1_servings_id.
clika-rt v1 servings-devices-proxy
Call a model serving on one device through the platform
clika-rt v1 servings-devices-proxy <id> <device_id> <upstream> [flags]
Positional arguments: required <id>, <device_id>, <upstream>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: GET /api/v1/servings/{id}/devices/{device_id}/proxy/{upstream}. MCP tool name: get_v1_servings_id_devices_device_id_proxy_upstream.
clika-rt v1 servings-devices-proxy-create
Call a model serving on one device through the platform
clika-rt v1 servings-devices-proxy-create <id> <device_id> <upstream> [flags]
Positional arguments: required <id>, <device_id>, <upstream>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: POST /api/v1/servings/{id}/devices/{device_id}/proxy/{upstream}. MCP tool name: post_v1_servings_id_devices_device_id_proxy_upstream.
clika-rt v1 servings-devices-proxy-delete
Call a model serving on one device through the platform
clika-rt v1 servings-devices-proxy-delete <id> <device_id> <upstream> [flags]
Positional arguments: required <id>, <device_id>, <upstream>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: DELETE /api/v1/servings/{id}/devices/{device_id}/proxy/{upstream}. MCP tool name: delete_v1_servings_id_devices_device_id_proxy_upstream.
clika-rt v1 servings-devices-proxy-update
Call a model serving on one device through the platform
clika-rt v1 servings-devices-proxy-update <id> <device_id> <upstream> [flags]
Positional arguments: required <id>, <device_id>, <upstream>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: PUT /api/v1/servings/{id}/devices/{device_id}/proxy/{upstream}. MCP tool name: put_v1_servings_id_devices_device_id_proxy_upstream.
clika-rt v1 servings-devices-proxy-update-patch
Call a model serving on one device through the platform
clika-rt v1 servings-devices-proxy-update-patch <id> <device_id> <upstream> [flags]
Positional arguments: required <id>, <device_id>, <upstream>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: PATCH /api/v1/servings/{id}/devices/{device_id}/proxy/{upstream}. MCP tool name: patch_v1_servings_id_devices_device_id_proxy_upstream.
clika-rt v1 servings-id
Get model serving
clika-rt v1 servings-id <id> [flags]
Positional arguments: required <id>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: GET /api/v1/servings/{id}. MCP tool name: get_v1_servings_id.
clika-rt v1 servings-restart
Restart model serving
clika-rt v1 servings-restart <id> [flags]
Positional arguments: required <id>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: POST /api/v1/servings/{id}/restart. MCP tool name: post_v1_servings_id_restart.
clika-rt v1 servings-start
Start model serving
clika-rt v1 servings-start <id> [flags]
Positional arguments: required <id>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: POST /api/v1/servings/{id}/start. MCP tool name: post_v1_servings_id_start.
clika-rt v1 servings-stop
Stop model serving
clika-rt v1 servings-stop <id> [flags]
Positional arguments: required <id>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: POST /api/v1/servings/{id}/stop. MCP tool name: post_v1_servings_id_stop.
clika-rt v1 servings-update-id
Update model serving
clika-rt v1 servings-update-id <id> [flags]
Positional arguments: required <id>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--body | string | none | request body (inline JSON) |
--body-file | string | none | request body (path to a JSON file) |
--raw | bool | false | print raw response without pretty-printing |
Endpoint: PATCH /api/v1/servings/{id}. MCP tool name: patch_v1_servings_id.
clika-rt v1
v1 has 1 subcommands on this page.
clika-rt v1 projects-servings
List a project's model servings
clika-rt v1 projects-servings <id> [flags]
Positional arguments: required <id>.
| Flag | Type | Default | Meaning |
|---|---|---|---|
--raw | bool | false | print raw response without pretty-printing |
Endpoint: GET /api/v1/projects/{id}/servings. MCP tool name: get_v1_projects_id_servings.
Related
- Services: the free-form counterpart, where you supply the command.
- Runtime licenses: the entitlement a deployed model runs under.
- Devices: the device that hosts the deployment.
- Artifacts and models: registering the model to deploy.
- Model deployment concept: what a deployment is, in prose.