​
Create

Create a new dedicated inference endpoint.

​
Usage

Shell
together endpoints create [MODEL] [GPU] [OPTIONS]

​
Example

Shell
together endpoints create \
--model mistralai/Mixtral-8x7B-Instruct-v0.1 \
--gpu h100 \
--gpu-count 2 \
--display-name "My Endpoint" \
--wait

​
Options

OptionsDescription
--model- TEXT(required) The model to deploy
--gpu [ h100 | a100 | l40 | l40s | rtx-6000](required) GPU type to use for inference
--min-replicas- INTEGERMinimum number of replicas to deploy
--max-replicas- INTEGERMaximum number of replicas to deploy
--gpu-count - INTEGERNumber of GPUs to use per replica
--display-name- TEXTA human-readable name for the endpoint
--no-prompt-cacheDisable the prompt cache for this endpoint
--no-speculative-decodingDisable speculative decoding for this endpoint
--no-auto-startCreate the endpoint in STOPPED state instead of auto-starting it
--waitWait for the endpoint to be ready after creation

​
Hardware

List all the hardware options, optionally filtered by model.

​
Usage

Shell
together endpoints hardware [OPTIONS]

​
Example

Shell
together endpoints hardware --model mistralai/Mixtral-8x7B-Instruct-v0.1

​
Options

OptionsDescription
--model- TEXTFilter hardware options by model
--jsonPrint output in JSON format
--availablePrint only available hardware options (can only be used if model is passed in)

​
Get

Print details for a specific endpoint.

​
Usage

Shell
together endpoints get [OPTIONS]

​
Example

Shell
together endpoints get endpoint-c2a48674-9ec7-45b3-ac30-0f25f2ad9462

​
Options

OptionsDescription
--jsonPrint output in JSON format

​
Update

Update an existing endpoint by listing the changes followed by the endpoint ID. You can find the endpoint ID by listing your dedicated endpoints.

​
Usage

Shell
together endpoints update [OPTIONS] ENDPOINT_ID

​
Example

Shell
together endpoints update --min-replicas 2 --max-replicas 4 endpoint-c2a48674-9ec7-45b3-ac30-0f25f2ad9462

​
Options

Note: Both --min-replicas and --max-replicas must be specified together
OptionsDescription
--display-name - TEXTA new human-readable name for the endpoint
--min-replicas - INTEGERNew minimum number of replicas to maintain
--max-replicas - INTEGERNew maximum number of replicas to scale up to

​
Start

Start a dedicated inference endpoint.

​
Usage

Shell
together endpoints start [OPTIONS] ENDPOINT_ID

​
Example

Shell
together endpoints start endpoint-c2a48674-9ec7-45b3-ac30-0f25f2ad9462

​
Options

OptionsDescription
--waitWait for the endpoint to start

​
Stop

Stop a dedicated inference endpoint.

​
Usage

Shell
together endpoints stop [OPTIONS] ENDPOINT_ID

​
Example

Shell
together endpoints stop endpoint-c2a48674-9ec7-45b3-ac30-0f25f2ad9462

​
Options

OptionsDescription
--waitWait for the endpoint to stop

​
Update

​
Usage

Update an existing endpoint by listing the changes followed by the endpoint ID. You can find the endpoint ID by listing your dedicated endpoints
Shell
together endpoints update [OPTIONS] ENDPOINT_ID

​
Example

Shell
together endpoints update --min-replicas 2 --max-replicas 4 endpoint-c2a48674-9ec7-45b3-ac30-0f25f2ad9462

​
Options

Note: Both --min-replicas and --max-replicas must be specified together
OptionsDescription
--display-name - TEXTA new human-readable name for the endpoint
--min-replicas - INTEGERNew minimum number of replicas to maintain
--max-replicas - INTEGERNew maximum number of replicas to scale up to

​
Delete

Delete a dedicated inference endpoint.

​
Usage

Shell
together endpoints delete [OPTIONS] ENDPOINT_ID

​
Example

Shell
together endpoints delete endpoint-c2a48674-9ec7-45b3-ac30-0f25f2ad9462

​
List

​
Usage

Shell
together endpoints list [FLAGS]

​
Example

Shell
together endpoints list --type dedicated

​
Options

OptionsDescription
--jsonPrint output in JSON format
type [dedicated | serverless]Filter by endpoint type

​
Help

See all commands with
Shell
together endpoints --help