baseten model - Baseten

Create, list, and push Baseten models. Authentication is through baseten auth login or the BASETEN_API_KEY environment variable.

push

baseten model push [OPTIONS] [--dir DIR]

Build a model archive, upload it to Baseten, and create either a new model or a new deployment of an existing model. By default, the command pushes the current directory. Pass --dir to push a model directory at another path. If your model only needs a configuration file, pass --file to push that file directly without creating a model directory. The CLI uploads the file as config.yaml. You can’t combine --file and --dir. Baseten identifies the model by the model_name field in config.yaml. Use --override-name to change the name for this push without editing the file. A push can set the new deployment’s instance type (--instance-type), autoscaling (--min-replica, --max-replica, and the other autoscaling flags), and request backpressure (--request-backpressure-policy) without editing config.yaml. With --environment, the environment keeps those settings after the promotion. The promotion-only flags --autoscaling-schedule-update-json and --override-* apply only with --environment. --instance-type can’t be combined with --preserve-env-instance-type.

Options

TEXT

Autoscaling schedule changes for the environment, applied when the promotion completes, as a JSON object with schedules, delete_schedules, and timezone. Same shape and values as autoscaling_schedule_settings on the environment update API, for example cadence DAILY. Requires --environment.

INTEGER

Timeframe of traffic considered for autoscaling decisions, in seconds.

INTEGER

Number of requests per replica before scaling up.

BOOL

Create the environment named by --environment when the model does not have it yet. Without this, pushing to an environment that does not exist fails. Only meaningful for an environment other than production, which every model has.

TEXT

Deployment timeout as a duration (e.g. 30m, 1h); allowed range 10m to 24h.

TEXT

Human-readable name for the new deployment.

BOOL

Push as a development deployment: the model’s single mutable dev slot, created if absent and overwritten in place otherwise. Incompatible with --environment and --deployment-name.

TEXT

Model directory to push. Defaults to the current directory when --file is not set.

BOOL

Disable archive download for the new model. Only valid for new models.

BOOL

Validate the push and request upload credentials without uploading or creating anything.

TEXT

Stable environment to push to. Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Config file to push on its own, for models defined entirely by their config. Use - for stdin. Only this file is uploaded, as the model’s config.yaml. Mutually exclusive with --dir.

BOOL

Attach the git commit, latest tag, commits since that tag, and whether there are uncommitted changes, when the model directory is in a git repository.

TEXT

Instance type for the new deployment, for example A10Gx4x16, instead of the one in config.yaml. With --environment, the environment keeps it once the promotion completes. See https://docs.baseten.co/deployment/resources for the available types. Cannot be combined with --preserve-env-instance-type.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

User-provided labels for the deployment as a JSON object, e.g. ’{“team”:“ml”,“priority”:1}’.

INTEGER

Maximum number of replicas.

INTEGER

Maximum percentage of replicas that can be removed per autoscaling window (1-50). For example, 20 means at most 20% of replicas are removed per window.

BOOL

Force a full rebuild without using cached layers.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

INTEGER

For this promotion only, the maximum surge percentage for rolling deploys.

INTEGER

For this promotion only, the maximum unavailable percentage for rolling deploys.

TEXT

Override the model_name from config.yaml for this push only. The on-disk config.yaml is not modified.

TEXT

For this promotion only, the cleanup strategy to use after it completes.One of: keep, scale-to-zero, deactivate

INTEGER

For this promotion only, the replica overhead percentage for rolling deploys.

BOOL

For this promotion only, whether to use rolling deploy orchestration.

TEXT

For this promotion only, the rolling deploy strategy.One of: replica

INTEGER

For this promotion only, the stabilization time for rolling deploys, in seconds.

BOOL

Keep the target environment’s current instance type instead of applying the one from config.yaml. Only meaningful when an environment is targeted.

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Slug of the region to deploy the model in. Defaults to a region Baseten selects. Run ‘baseten org regions’ to see the slugs available.

TEXT | null

Backpressure policy for the new deployment. With --environment, the environment keeps it once the promotion completes. Pass null to clear the policy.One of: queue-on-full, reject-on-full, null

INTEGER

Waiting period before scaling down any active replica, in seconds.

BOOL

Stream build and runtime logs to stderr after pushing. Logs are always text-formatted; use ‘baseten model deployment logs --tail’ for structured log streaming.

INTEGER

Target number of in-flight tokens for autoscaling decisions. Early access only.

INTEGER

Target utilization percentage for scaling up and down.

TEXT

Team the model belongs to. Only valid for new models.

BOOL

Block until the deployment is active. Exits non-zero on a terminal-failure status.

BOOL

After pushing, watch the model directory and live-patch the development deployment on change. Implies --develop.

BOOL

With --watch, hot-reload the running container when every change is to model code; mixed changes fall back to a cold patch.

BOOL

With --watch, let the development deployment scale to zero while watching. By default it is kept warm by periodic pings.

INTEGER

Minimum number of replicas.

BOOL

For this promotion only, whether to create a new deployment with a copy of the image.

BOOL

Enable verbose logging

Examples

Push the current directory as a new deployment

baseten model push

Push and stream build/runtime logs until the deployment is active

baseten model push --tail --wait

Push a single configuration file directly:

baseten model push --file config.yaml --wait

Read the configuration from standard input:

cat config.yaml | baseten model push --file - --wait

Push with an instance type and autoscaling settings for the new deployment

baseten model push --instance-type <instance-type> --min-replica 1 --max-replica 4 --concurrency-target 8

Filter output with `--jq`

Print the new deployment’s predict URL

baseten model push --jq '.predict_url'

Output

Text mode (--output text): Narrative summary on stdout: success banner, deployment facts, then grouped next-step hints for viewing logs, invoking the model, and (when the pushed config enables it) SSH access; hints scoped to an environment are tagged “(once deployed)”. Under --output json the narrative is redirected to stderr so stdout stays a clean JSON document. JSON mode (--output json): payload type cmd.ModelPushResult. Under --dry-run no upload or deployment happens; the push is validated, upload credentials are requested, and stdout is the empty JSON object \{\}. Otherwise stdout is the full model+deployment result.

watch

baseten model watch [OPTIONS] [--dir DIR]

Watch a model directory and patch the model’s development deployment in place on every change, skipping a full rebuild. The current directory is used by default; pass --dir to watch a model directory at another path. The model is identified by the model_name field in that directory’s config.yaml, like baseten model push. The model must already have a development deployment; if it does not, run baseten model push --develop (or baseten model push --watch) first. Runs until interrupted. Some changes cannot be expressed as a patch (removing config.yaml, or any change under the data directory); the watcher reports these and you must re-push.

Options

TEXT

default:"."

Model directory to watch. Defaults to the current directory.

BOOL

Hot-reload the running container when every change is to model code; mixed changes fall back to a cold patch.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

BOOL

Let the development deployment scale to zero while watching. By default it is kept warm by periodic pings.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team the model belongs to. Use to disambiguate when the same model_name exists in multiple teams.

BOOL

Enable verbose logging

Examples

Watch the current directory against its model’s development deployment

baseten model watch

Watch another directory and hot-reload on model-code changes

baseten model watch --dir ./my-model --hot-reload

Output

Text mode (--output text): Streams patch and sync status to stderr as changes are applied. Runs until interrupted and produces no stdout output. JSON mode (--output json): payload type cmd.JSONUndefined.

list

baseten model list [OPTIONS]

List Baseten models.

Options

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID to scope the listing to. Defaults to all teams the caller can see.

BOOL

Enable verbose logging

Examples

List all models accessible to the caller

baseten model list

List only models in a specific team

baseten model list --team my-team

Filter output with `--jq`

Print just the model IDs

baseten model list --jq '.models[].id'

Output

Text mode (--output text): Table with columns: ID, NAME, TEAM, DEPLOYMENTS, CREATED. When no models exist, prints “No models found.” to stderr. JSON mode (--output json): payload type managementapi.Models.

describe

baseten model describe [OPTIONS]

Describe a Baseten model.

Options

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Describe a model by ID

baseten model describe --model-id <model-id>

Describe a model by name

baseten model describe --model-name <name>

Filter output with `--jq`

Print the production deployment ID

baseten model describe --model-id <model-id> --jq '.production_deployment_id'

Output

Text mode (--output text): Field-per-line summary: ID, Name, Team, Deployments, Instance, Production, Development, Created. Optional fields are omitted when unset. JSON mode (--output json): payload type managementapi.Model.

predict

baseten model predict [OPTIONS]

POST a JSON request to a model and write the response to stdout. Targets the production environment by default. Use --environment, --deployment-id, --deployment-name, or --regional to target something else. Streaming responses (Transfer-Encoding: chunked) are passed through as they arrive. For machine-readable streaming JSON from OpenAI-compatible models, use --output jsonl. Pass --verbose to log the request URL, the response status, and the response headers to stderr.

Options

TEXT

Inline JSON request body. The shape is the deployed model’s own input schema; see https://docs.baseten.co/inference/calling-your-model.Mutually exclusive with other flags in group predict-input.

TEXT

Specific deployment to target. Mutually exclusive with --environment, --deployment-name, and --regional.

TEXT

Name of the deployment to target. Mutually exclusive with --environment, --deployment-id, and --regional.

TEXT

Environment to target (e.g. production, development). Defaults to production. Mutually exclusive with --deployment-id, --deployment-name, and --regional. Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Path to a JSON file containing the request body. Use ’-’ for stdin.Mutually exclusive with other flags in group predict-input.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Regional environment name; routes through the regional hostname. Mutually exclusive with —environment, —deployment-id, and —deployment-name.

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Use the WebSocket predict endpoint. Sends the body as one frame, reads one frame back, then closes. Not for multi-message or back-and-forth sessions.

BOOL

Enable verbose logging

Examples

Send an inline JSON body

baseten model predict --model-id <model-id> --data '{"prompt":"hello"}'

Send a request body from a file

baseten model predict --model-id <model-id> --file request.json

Filter output with `--jq`

Extract a field when the model returns JSON

baseten model predict --model-id <model-id> --data '{"x":1}' --jq '.result'

Output

Text mode (--output text): The model’s response body, passed through verbatim. May be JSON, plain text, or binary, and may stream when the model uses chunked transfer encoding or SSE. JSON mode (--output json): payload type cmd.JSONUndefined. Under --output json, binary frames are base64-encoded under a ‘body’ key. Under --output jsonl, each SSE or binary chunk is emitted as its own record, one per line.

delete

baseten model delete [OPTIONS]

Delete a Baseten model and all of its deployments. Prompts for the model name to confirm the deletion. Pass --yes to skip the prompt. When stdin is not a terminal, --yes is required.

Options

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Skip the interactive confirmation prompt. Required when stdin is not a terminal.

BOOL

Enable verbose logging

Examples

Delete by ID without confirmation

baseten model delete --model-id <model-id> --yes

Delete by name with interactive confirmation

baseten model delete --model-name <name>

Filter output with `--jq`

Print the deleted model’s ID

baseten model delete --model-id <model-id> --yes --jq '.id'

Output

Text mode (--output text): On success, prints “Deleted model name (id)” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.ModelTombstone.

rename

baseten model rename [OPTIONS]

Change a model’s name. The new name must be unique within the model’s team. Renaming does not change the model ID, endpoints, or deployments. Pushes that still use the old model_name create another model or target a model that now uses that name, so update config.yaml after renaming. Run baseten model describe to see the current values.

Options

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

required

New name for the model, unique within its team.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Rename by ID

baseten model rename --model-id <model-id> --new-name my-model-v2

Rename by name, scoped to a team

baseten model rename --model-name <name> --team <team> --new-name my-model-v2

Filter output with `--jq`

Print the model’s new name

baseten model rename --model-id <model-id> --new-name my-model-v2 --jq '.name'

Output

Text mode (--output text): On success, prints “Renamed model id to name” and a reminder to update model_name in config.yaml to stderr (also under --output json); no stdout output. JSON mode (--output json): payload type managementapi.Model.

audit-logs

baseten model audit-logs [OPTIONS]

List audit-log entries scoped to a single model, newest first. Returns up to --limit entries (default 20) across the full history by default. Use --start/--end or --since to scope the time window, and the filter flags (--event-type-group, --source, --user-id, --deployment-id, --environment, --search) to narrow results within the model. For machine-readable streaming, prefer --output jsonl over --output json.

Options

TEXT (repeatable)

Only return entries referencing one of these model deployment IDs. May be repeated.

TEXT

default:"desc"

Sort order by the time the action occurred: ‘desc’ (newest first) or ‘asc’ (oldest first).One of: asc, desc

TEXT

End of the time window. Accepts ISO 8601; values without a timezone designator are interpreted in the local timezone. Defaults to now.

TEXT (repeatable)

Only return entries for one of these environments. May be repeated.

TEXT (repeatable)

Only return entries whose event type falls in one of these groups. May be repeated. One of: activated-deactivated, api-keys, autoscaling-settings, deleted, deployed, directory-group-management, environment-settings, gateway, instance-type-changed, promoted, replica-terminated, secrets, ssh, user-management, webhook-signing-secrets.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

INTEGER

default:"20"

Maximum number of entries to return, paging as needed. Use 0 for no limit (every entry in the window).

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Case-insensitive substring matched against resource names and IDs in the entry.

TEXT

Shortcut for a window from a relative time ago until now. Accepts a duration (e.g. ‘30m’, ‘1h30m’) or ‘Nd’ (e.g. ‘3d’). Mutually exclusive with --start and --end.

TEXT (repeatable)

Only return entries issued from one of these surfaces. May be repeated. One of: ui, api, mcp, other.

TEXT

Start of the time window. Accepts ISO 8601 (e.g. ‘2026-05-14’, ‘2026-05-14T12:00:00’, ‘2026-05-14T12:00:00Z’). Values without a timezone designator are interpreted in the local timezone. Defaults to the beginning of the audit-log history.

TEXT

Team name or ID. Only valid with --model-name.

TEXT (repeatable)

Only return entries whose acting user is one of these IDs. May be repeated.

BOOL

Enable verbose logging

Examples

List the 20 most recent audit-log entries for a model

baseten model audit-logs --model-id <model-id>

List promote events for a model over the last 30 days

baseten model audit-logs --model-name <name> --since 30d --event-type-group promoted

Filter output with `--jq`

Stream each entry’s event type as a JSONL stream

baseten model audit-logs --model-id <model-id> --output jsonl --jq '.event_type'

Output

Text mode (--output text): Table with columns: TIME, ACTOR, EVENT, SOURCE. When no entries match, prints “No audit-log entries found.” to stderr. JSON mode (--output json): payload type managementapi.AuditLogEntry.

deployment

Deployments are the instances of a model that serve traffic. Activate and deactivate them, read their config, logs, and metrics, and change their autoscaling and request backpressure settings.

activate

baseten model deployment activate [OPTIONS]

Activate a model deployment.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Activate a deployment

baseten model deployment activate --model-id <model-id> --deployment-id <deployment-id>

Filter output with `--jq`

Print just the success flag

baseten model deployment activate --model-id <model-id> --deployment-id <deployment-id> --jq '.success'

Output

Text mode (--output text): On success, prints “Activated deployment id” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.ActivateResponse.

config

baseten model deployment config [OPTIONS]

Fetch the config of a deployed model. By default prints the original config.yaml. Use --output json to emit the full response {config, raw_config} as JSON.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Print the deployment’s config.yaml

baseten model deployment config --model-id <model-id> --deployment-id <deployment-id>

Filter output with `--jq`

Extract the parsed model_name field

baseten model deployment config --model-id <model-id> --deployment-id <deployment-id> --jq '.config.model_name'

Output

Text mode (--output text): The original config.yaml text (preserving comments and ordering) when available, otherwise the parsed config marshaled as YAML. JSON mode (--output json): payload type managementapi.DeploymentConfigResponse. The full {config, raw_config} envelope. raw_config is the original config.yaml text; config is the parsed shape.

deactivate

baseten model deployment deactivate [OPTIONS]

Deactivate a model deployment. Prompts for yes/no confirmation. Pass --yes to skip the prompt. When stdin is not a terminal, --yes is required.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Skip the interactive confirmation prompt. Required when stdin is not a terminal.

BOOL

Enable verbose logging

Examples

Deactivate a deployment without the confirmation prompt

baseten model deployment deactivate --model-id <model-id> --deployment-id <deployment-id> --yes

Filter output with `--jq`

Print just the success flag

baseten model deployment deactivate --model-id <model-id> --deployment-id <deployment-id> --yes --jq '.success'

Output

Text mode (--output text): On success, prints “Deactivated deployment id” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.DeactivateResponse.

download

baseten model deployment download [OPTIONS]

Download the model source for a model deployment as an uncompressed tar. Exactly one of --out-file or --out-dir is required. --out-file writes the raw tar bytes; --out-dir extracts the tar into the directory. Use --overwrite to replace an existing file or write into a non-empty directory.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

Extract the model source tar into this directory.Mutually exclusive with other flags in group download-out.

TEXT

Save the model source as an uncompressed tar file at this path.Mutually exclusive with other flags in group download-out.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

BOOL

Allow overwriting an existing file or non-empty directory.

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Save the model source as a tar file

baseten model deployment download --model-id <model-id> --deployment-id <deployment-id> --out-file model.tar

Extract the model source into a directory

baseten model deployment download --model-id <model-id> --deployment-id <deployment-id> --out-dir ./model

Filter output with `--jq`

Print just the destination path

baseten model deployment download --model-id <model-id> --deployment-id <deployment-id> --out-file truss.tar --jq '.out_file'

Output

Text mode (--output text): Writes the model source to disk; prints progress and the final destination path to stderr; no stdout output. JSON mode (--output json): payload type cmd.ModelDeploymentDownloadResult. On success, stdout is a JSON object with either out_file or out_dir set to the path written.

promote

baseten model deployment promote [OPTIONS]

Promote a model deployment to an environment. Defaults to the production environment. Cleanup of the previous deployment is controlled by the target environment’s promotion cleanup strategy. Promotions use the target environment’s rolling deployment settings, including mixed mode (beta) when enabled for your organization. Configure those settings with model environment update-promotion before promoting the deployment. A promotion can also change the target environment’s settings: --region, --instance-type, --request-backpressure-policy, the autoscaling flags, and --autoscaling-schedule-update-json for autoscaling schedules as raw API JSON. The --override-* flags change the promotion’s settings for this promotion only. The confirmation prompt names the settings the promotion changes. Prompts for yes/no confirmation. Pass --yes to skip the prompt. When stdin is not a terminal, --yes is required.

Options

TEXT

INTEGER

Timeframe of traffic considered for autoscaling decisions, in seconds.

INTEGER

Number of requests per replica before scaling up.

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

default:"production"

Target environment name. Defaults to production.

TEXT

Instance type to set on the environment, for example A10Gx4x16. See https://docs.baseten.co/deployment/resources for the available types. Cannot be combined with --preserve-env-instance-type.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

INTEGER

Maximum number of replicas.

INTEGER

Maximum percentage of replicas that can be removed per autoscaling window (1-50). For example, 20 means at most 20% of replicas are removed per window.

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

INTEGER

For this promotion only, the maximum surge percentage for rolling deploys.

INTEGER

For this promotion only, the maximum unavailable percentage for rolling deploys.

TEXT

For this promotion only, the cleanup strategy to use after it completes.One of: keep, scale-to-zero, deactivate

INTEGER

For this promotion only, the replica overhead percentage for rolling deploys.

BOOL

For this promotion only, whether to use rolling deploy orchestration.

TEXT

For this promotion only, the rolling deploy strategy.One of: replica

INTEGER

For this promotion only, the stabilization time for rolling deploys, in seconds.

BOOL

Keep the target environment’s current instance type instead of applying the promoted deployment’s.

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Region slug to set on the environment. Pass an empty string for Global. Run ‘baseten org regions’ to see the slugs available.

TEXT | null

Backpressure policy to set on the environment. Pass null to clear the environment’s policy.One of: queue-on-full, reject-on-full, null

INTEGER

Waiting period before scaling down any active replica, in seconds.

INTEGER

Target number of in-flight tokens for autoscaling decisions. Early access only.

INTEGER

Target utilization percentage for scaling up and down.

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Skip the interactive confirmation prompt. Required when stdin is not a terminal.

INTEGER

Minimum number of replicas.

BOOL

For this promotion only, whether to create a new deployment with a copy of the image.

BOOL

Enable verbose logging

Examples

Promote a deployment to production without the confirmation prompt

baseten model deployment promote --model-id <model-id> --deployment-id <deployment-id> --yes

Promote to a non-production environment using the deployment’s own instance type

baseten model deployment promote --model-id <model-id> --deployment-id <deployment-id> --environment staging --preserve-env-instance-type --yes

Promote to production and switch the environment to a different instance type

baseten model deployment promote --model-id <model-id> --deployment-id <deployment-id> --environment production --instance-type <instance-type> --yes

Filter output with `--jq`

Print the promoted deployment’s status

baseten model deployment promote --model-id <model-id> --deployment-id <deployment-id> --yes --jq '.status'

Output

Text mode (--output text): On success, prints “Promoted deployment id to environment env” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.Deployment. Under --output json, the promoted deployment object.

delete

baseten model deployment delete [OPTIONS]

Delete a single model deployment. Deployments associated with an environment (e.g. production, development) and the only deployment of a model cannot be deleted server-side. Prompts for yes/no confirmation. Pass --yes to skip the prompt. When stdin is not a terminal, --yes is required.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Skip the interactive confirmation prompt. Required when stdin is not a terminal.

BOOL

Enable verbose logging

Examples

Delete a deployment without the confirmation prompt

baseten model deployment delete --model-id <model-id> --deployment-id <deployment-id> --yes

Filter output with `--jq`

Print the deleted deployment’s ID

baseten model deployment delete --model-id <model-id> --deployment-id <deployment-id> --yes --jq '.id'

Output

Text mode (--output text): On success, prints “Deleted deployment id” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.DeploymentTombstone.

describe

baseten model deployment describe [OPTIONS]

Describe a model deployment by ID.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Describe a deployment by ID

baseten model deployment describe --model-id <model-id> --deployment-id <deployment-id>

Filter output with `--jq`

Print just the deployment status

baseten model deployment describe --model-id <model-id> --deployment-id <deployment-id> --jq '.status'

Output

Text mode (--output text): Field-per-line summary: ID, Name, Model, Environment (optional), Status, Instance (optional), Replicas, Created. JSON mode (--output json): payload type managementapi.Deployment.

list

baseten model deployment list [OPTIONS]

List all deployments of a model.

Options

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

List all deployments of a model

baseten model deployment list --model-id <model-id>

Filter output with `--jq`

Print just the deployment IDs

baseten model deployment list --model-id <model-id> --jq '.deployments[].id'

Output

Text mode (--output text): Table with columns: ID, NAME, ENVIRONMENT, STATUS, INSTANCE, REPLICAS, CREATED. When no deployments exist, prints “No deployments found.” to stderr. JSON mode (--output json): payload type managementapi.Deployments.

logs

baseten model deployment logs [OPTIONS]

Fetch logs for a model deployment. By default returns up to --limit lines from the last 30 minutes, newest first, and prints a note to stderr when --limit trims older lines. Use --start/--end or --since to scope the window (max 7 days). Use --tail to stream live logs until the deployment leaves a runnable state or you interrupt with Ctrl-C. For machine-readable streaming, prefer --output jsonl over --output json. For request-ID tracing, scope, and log export, see Logs.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

End of the log time range. Accepts ISO 8601; values without a timezone designator are interpreted in the local timezone. Default is now. Window must be at most 7 days.

TEXT (repeatable)

Case-sensitive substring; lines containing it are dropped. May be repeated.

TEXT (repeatable)

Case-sensitive substring that must appear in the log message. May be repeated; all must match.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

INTEGER

default:"5000"

Maximum number of log lines to return, paging backward from the end of the window. Use 0 for no limit (every log line in the window). Not applicable with --tail.

TEXT

Only return logs at or above this severity level.One of: debug, info, warning, error

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Only return logs emitted by this replica (5-char short ID).

TEXT

Only return logs tagged with this inference request ID.

TEXT

RE2 regular expression matched against the log message. Prefer --includes and --excludes for plain substring matches.

TEXT

Shortcut for fetching logs from a relative time ago until now. Accepts a duration (e.g. ‘30m’, ‘1h30m’) or ‘Nd’ (e.g. ‘3d’). Maximum ‘7d’. Mutually exclusive with --start and --end.

TEXT

Start of the log time range. Accepts ISO 8601 (e.g. ‘2026-05-14’, ‘2026-05-14T12:00:00’, ‘2026-05-14T12:00:00Z’). Values without a timezone designator are interpreted in the local timezone. Default is 30 minutes before the end. Window must be at most 7 days.

BOOL

Stream new logs as they arrive until the deployment leaves a runnable state or you interrupt with Ctrl-C. Cannot be combined with the time-range or filter flags. For machine-readable streaming, prefer --output jsonl over --output json.

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Print logs for a deployment over the last hour

baseten model deployment logs --model-id <model-id> --deployment-id <deployment-id> --since 1h

Print logs for a fixed time range

baseten model deployment logs --model-id <model-id> --deployment-id <deployment-id> --start 2026-05-14T00:00:00Z --end 2026-05-15T00:00:00Z

Tail live logs until the deployment leaves a runnable state

baseten model deployment logs --model-id <model-id> --deployment-id <deployment-id> --tail

Filter to warnings and above that contain a term

baseten model deployment logs --model-id <model-id> --deployment-id <deployment-id> --min-level warning --includes timeout

Filter output with `--jq`

Stream just the log messages as a JSONL stream

baseten model deployment logs --model-id <model-id> --deployment-id <deployment-id> --output jsonl --jq '.message'

Output

Text mode (--output text): One line per log record: “[YYYY-MM-DD HH:MM:SS]: (replica) message”. JSON mode (--output json): payload type managementapi.Log.

metrics

baseten model deployment metrics [OPTIONS]

Fetch metrics for a model deployment. Use --mode current for a snapshot, --mode summary to aggregate a window, or --mode series to plot values over time. Scope the window with --since or --start/--end (max 7 days; only applies to summary and series), and select metrics with one or more --metric flags.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

End of the metrics time range. Accepts ISO 8601; values without a timezone designator are interpreted in the local timezone. If omitted, the server defaults the end to now. Window must be at most 7 days.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT (repeatable)

Name of a metric to return; see https://docs.baseten.co/observability/export-metrics/supported-metrics for the available names. May be repeated. When omitted, a default set is returned.

TEXT

default:"current"

Aggregation mode. ‘current’ returns an instantaneous snapshot at now; ‘summary’ aggregates the whole window into one value per metric; ‘series’ returns evenly-spaced points across the window. --start/--end/--since are only meaningful for summary and series.One of: current, summary, series

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

BOOL

For --mode series, emit a per-step table instead of sparklines.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Shortcut for a window from a relative time ago until now. Accepts a duration (e.g. ‘30m’, ‘1h30m’) or ‘Nd’ (e.g. ‘3d’). Maximum ‘7d’. Mutually exclusive with --start and --end.

TEXT

Start of the metrics time range. Accepts ISO 8601 (e.g. ‘2026-05-14’, ‘2026-05-14T12:00:00’, ‘2026-05-14T12:00:00Z’). Values without a timezone designator are interpreted in the local timezone. If omitted, the server defaults the start to one hour before the end. Window must be at most 7 days.

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Show a current snapshot of the default metrics

baseten model deployment metrics --model-name <model-name> --deployment-id <deployment-id>

Summarize request volume and latency over the last hour

baseten model deployment metrics --model-id <model-id> --deployment-id <deployment-id> --mode summary --since 1h --metric baseten_inference_requests_total --metric baseten_end_to_end_response_time_seconds

Plot a series over the last 6 hours

baseten model deployment metrics --model-id <model-id> --deployment-id <deployment-id> --mode series --since 6h

Filter output with `--jq`

Print the metric names returned

baseten model deployment metrics --model-id <model-id> --deployment-id <deployment-id> --jq '.metric_descriptors[].name'

Output

Text mode (--output text): For current and summary, a table with columns METRIC, one column per label dimension (for example QUANTILE, STAT), and VALUE; summary counter values show “total (rate/s)”. For series, a sparkline per metric label set with its min-max range and end value, or a per-step table under --no-chart. JSON mode (--output json): payload type managementapi.GetModelMetricsResponse. The metrics response: metric_descriptors, index-mapped metric_values, the resolved mode, and the returned window.

rename

baseten model deployment rename [OPTIONS]

Change a deployment’s name. The new name must be unique among the model’s deployments and may contain only alphanumeric characters, hyphens, underscores, and periods. Run baseten model deployment describe to see the current values.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

required

New name for the deployment, unique among the model’s deployments. Only alphanumeric characters, hyphens, underscores, and periods are allowed.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Rename a deployment

baseten model deployment rename --model-id <model-id> --deployment-id <deployment-id> --new-name canary

Filter output with `--jq`

Print the deployment’s new name

baseten model deployment rename --model-id <model-id> --deployment-id <deployment-id> --new-name canary --jq '.name'

Output

Text mode (--output text): On success, prints “Renamed deployment id to name” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.Deployment.

update-autoscaling

baseten model deployment update-autoscaling [OPTIONS]

Update a deployment’s autoscaling settings. Only the flags you pass are changed; every other setting is left alone. Changes are applied asynchronously, so the response reports whether the request was accepted rather than the settled state. Run baseten model deployment describe to see the current values.

Options

INTEGER

Timeframe of traffic considered for autoscaling decisions, in seconds.

INTEGER

Number of requests per replica before scaling up.

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

INTEGER

Maximum number of replicas.

INTEGER

Maximum percentage of replicas that can be removed per autoscaling window (1-50). For example, 20 means at most 20% of replicas are removed per window.

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

INTEGER

Waiting period before scaling down any active replica, in seconds.

INTEGER

Target number of in-flight tokens for autoscaling decisions. Early access only.

INTEGER

Target utilization percentage for scaling up and down.

TEXT

Team name or ID. Only valid with --model-name.

INTEGER

Minimum number of replicas.

BOOL

Enable verbose logging

Examples

Raise a deployment’s replica bounds

baseten model deployment update-autoscaling --model-id <model-id> --deployment-id <deployment-id> --min-replica 2 --max-replica 10

Shorten the scale-down delay, leaving every other setting unchanged

baseten model deployment update-autoscaling --model-id <model-id> --deployment-id <deployment-id> --scale-down-delay 60

Filter output with `--jq`

Print just the status

baseten model deployment update-autoscaling --model-id <model-id> --deployment-id <deployment-id> --min-replica 2 --jq '.status'

Output

Text mode (--output text): The status of the request followed by the server’s message. JSON mode (--output json): payload type managementapi.UpdateAutoscalingSettingsResponse.

update-request-backpressure

baseten model deployment update-request-backpressure [OPTIONS]

Set the policy applied when a deployment’s request queue is full. Pass --policy null to clear an existing policy and fall back to the default. Run baseten model deployment describe to see the current values.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT | null

required

Backpressure policy to apply. Pass null to clear an existing policy.One of: queue-on-full, reject-on-full, null

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Reject requests once the queue is full

baseten model deployment update-request-backpressure --model-id <model-id> --deployment-id <deployment-id> --policy reject-on-full

Clear the policy

baseten model deployment update-request-backpressure --model-id <model-id> --deployment-id <deployment-id> --policy null

Filter output with `--jq`

Print the resulting policy

baseten model deployment update-request-backpressure --model-id <model-id> --deployment-id <deployment-id> --policy reject-on-full --jq '.policy'

Output

Text mode (--output text): The resulting policy, or “none” when no policy is set. JSON mode (--output json): payload type managementapi.RequestBackpressureSettings.

deployment replica

Inspect and terminate individual replicas of a deployment.

terminate

baseten model deployment replica terminate [OPTIONS]

Terminate a single replica of a model deployment. Prompts for yes/no confirmation. Pass --yes to skip the prompt. When stdin is not a terminal, --yes is required.

Options

TEXT

ID of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Name of the deployment.Mutually exclusive with other flags in group deployment-ref.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

required

ID of the replica.

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Skip the interactive confirmation prompt. Required when stdin is not a terminal.

BOOL

Enable verbose logging

Examples

Terminate a replica without the confirmation prompt

baseten model deployment replica terminate --model-id <model-id> --deployment-id <deployment-id> --replica-id <replica-id> --yes

Filter output with `--jq`

Print just the success flag

baseten model deployment replica terminate --model-id <model-id> --deployment-id <deployment-id> --replica-id <replica-id> --yes --jq '.success'

Output

Text mode (--output text): On success, prints “Terminated replica id of deployment id” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.TerminateReplicaResponse.

environment

An environment such as production or development points at the deployment currently serving it. Activate it, read its logs and metrics, and configure promotion, autoscaling, and request backpressure.

activate

baseten model environment activate [OPTIONS]

Activate the deployment associated with an environment.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Activate the deployment associated with an environment

baseten model environment activate --model-id <model-id> --environment production

Filter output with `--jq`

Print just the success flag

baseten model environment activate --model-id <model-id> --environment production --jq '.success'

Output

Text mode (--output text): On success, prints “Activated environment name” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.ActivateResponse.

deactivate

baseten model environment deactivate [OPTIONS]

Deactivate the deployment associated with an environment. Prompts for yes/no confirmation. Pass --yes to skip the prompt. When stdin is not a terminal, --yes is required.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Skip the interactive confirmation prompt. Required when stdin is not a terminal.

BOOL

Enable verbose logging

Examples

Deactivate an environment without the confirmation prompt

baseten model environment deactivate --model-id <model-id> --environment production --yes

Filter output with `--jq`

Print just the success flag

baseten model environment deactivate --model-id <model-id> --environment production --yes --jq '.success'

Output

Text mode (--output text): On success, prints “Deactivated environment name” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.DeactivateResponse.

describe

baseten model environment describe [OPTIONS]

Describe a model environment by name.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Describe the production environment of a model

baseten model environment describe --model-id <model-id> --environment production

Filter output with `--jq`

Print the current deployment ID

baseten model environment describe --model-id <model-id> --environment production --jq '.current_deployment.id'

Output

Text mode (--output text): Field-per-line summary: Name, Model, Current Deployment, Status, Candidate Deployment (optional), Created. JSON mode (--output json): payload type managementapi.Environment.

list

baseten model environment list [OPTIONS]

List all environments of a model.

Options

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

List all environments of a model

baseten model environment list --model-id <model-id>

Filter output with `--jq`

Print just the environment names

baseten model environment list --model-id <model-id> --jq '.environments[].name'

Output

Text mode (--output text): Table with columns: NAME, CURRENT DEPLOYMENT, STATUS. When no environments exist, prints “No environments found.” to stderr. JSON mode (--output json): payload type managementapi.Environments.

logs

baseten model environment logs [OPTIONS]

Fetch logs for a model environment, spanning every deployment that was active on the environment across the time range. By default returns up to --limit lines from the last 30 minutes, newest first, and prints a note to stderr when --limit trims older lines. Use --start/--end or --since to scope the window (max 7 days). Use --tail to stream live logs until the environment’s current deployment leaves a runnable state or you interrupt with Ctrl-C. For machine-readable streaming, prefer --output jsonl over --output json. For request-ID tracing, scope, and log export, see Logs.

Options

TEXT

End of the log time range. Accepts ISO 8601; values without a timezone designator are interpreted in the local timezone. Default is now. Window must be at most 7 days.

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT (repeatable)

Case-sensitive substring; lines containing it are dropped. May be repeated.

TEXT (repeatable)

Case-sensitive substring that must appear in the log message. May be repeated; all must match.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

INTEGER

default:"5000"

Maximum number of log lines to return, paging backward from the end of the window. Use 0 for no limit (every log line in the window). Not applicable with --tail.

TEXT

Only return logs at or above this severity level.One of: debug, info, warning, error

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Only return logs emitted by this replica (5-char short ID).

TEXT

Only return logs tagged with this inference request ID.

TEXT

RE2 regular expression matched against the log message. Prefer --includes and --excludes for plain substring matches.

TEXT

BOOL

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Print logs for the production environment over the last hour

baseten model environment logs --model-id <model-id> --environment production --since 1h

Tail live logs until the environment’s current deployment leaves a runnable state

baseten model environment logs --model-id <model-id> --environment production --tail

Filter output with `--jq`

Stream just the log messages as a JSONL stream

baseten model environment logs --model-id <model-id> --environment production --output jsonl --jq '.message'

Output

Text mode (--output text): One line per log record: “[YYYY-MM-DD HH:MM:SS]: (replica) message”. JSON mode (--output json): payload type managementapi.Log.

metrics

baseten model environment metrics [OPTIONS]

Fetch metrics aggregated across every deployment that was active on the environment over the time range. Use --mode current for a snapshot, --mode summary to aggregate a window, or --mode series to plot values over time. Scope the window with --since or --start/--end (max 7 days; only applies to summary and series), and select metrics with one or more --metric flags. In series mode the window is split at each promotion so every point reflects the deployment(s) serving the environment at that time.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT (repeatable)

Name of a metric to return; see https://docs.baseten.co/observability/export-metrics/supported-metrics for the available names. May be repeated. When omitted, a default set is returned.

TEXT

default:"current"

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

BOOL

For --mode series, emit a per-step table instead of sparklines.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Show a current snapshot of the default metrics for the production environment

baseten model environment metrics --model-id <model-id> --environment production

Summarize request volume and latency over the last hour

baseten model environment metrics --model-id <model-id> --environment production --mode summary --since 1h --metric baseten_inference_requests_total --metric baseten_end_to_end_response_time_seconds

Plot a series over the last 6 hours

baseten model environment metrics --model-id <model-id> --environment production --mode series --since 6h

Filter output with `--jq`

Print the metric names returned

baseten model environment metrics --model-id <model-id> --environment production --jq '.metric_descriptors[].name'

Output

update-autoscaling

baseten model environment update-autoscaling [OPTIONS]

Update an environment’s autoscaling settings, which apply to whichever deployment currently serves it. Only the flags you pass are changed; every other setting is left alone. Run baseten model environment describe to see the current values.

Options

INTEGER

Timeframe of traffic considered for autoscaling decisions, in seconds.

INTEGER

Number of requests per replica before scaling up.

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

INTEGER

Maximum number of replicas.

INTEGER

Maximum percentage of replicas that can be removed per autoscaling window (1-50). For example, 20 means at most 20% of replicas are removed per window.

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

INTEGER

Waiting period before scaling down any active replica, in seconds.

INTEGER

Target number of in-flight tokens for autoscaling decisions. Early access only.

INTEGER

Target utilization percentage for scaling up and down.

TEXT

Team name or ID. Only valid with --model-name.

INTEGER

Minimum number of replicas.

BOOL

Enable verbose logging

Examples

Raise the production environment’s replica bounds

baseten model environment update-autoscaling --model-id <model-id> --environment production --min-replica 2 --max-replica 10

Filter output with `--jq`

Print the environment’s resulting minimum replica count

baseten model environment update-autoscaling --model-id <model-id> --environment production --min-replica 2 --jq '.environment.autoscaling_settings.min_replica'

Output

Text mode (--output text): On success, prints “Updated autoscaling settings for environment name” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.UpdateEnvironmentResponse.

update-promotion

baseten model environment update-promotion [OPTIONS]

Update how deployments are promoted into an environment: whether to redeploy, whether to roll out gradually and with what rolling deploy config, what to do with the outgoing deployment, and whether to ramp up traffic. Only the flags you pass are changed; every other setting is left alone. For organizations with mixed mode (beta) enabled, set both --max-surge-percent and --max-unavailable-percent to positive values. Set the budget you want to disable to 0. These settings apply to future promotions into the environment. Inspect promotion_settings in the JSON output from model environment describe.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

INTEGER

Maximum percentage of the baseline replica count to provision as extra replicas across both deployments, including replicas still starting. Accepts integers from 0 to 100. Pass 0 to disable this budget; omit the flag to keep its current value. Both budgets can be positive when mixed mode (beta) is enabled for your organization. Configure rolling deployments.

INTEGER

Maximum percentage of the baseline replica count that can be unavailable through planned replica replacement. Accepts integers from 0 to 50. Pass 0 to disable this budget; omit the flag to keep its current value. Both budgets can be positive when mixed mode (beta) is enabled for your organization. Configure rolling deployments.

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

The cleanup strategy to use after a promotion completes.One of: keep, scale-to-zero, deactivate

BOOL

Whether to deploy on all promotions. Enabling this allows model code to safely handle environment-specific logic: when a deployment is promoted, a new deployment is created with a copy of the image. Pass true or false explicitly; omit the flag to leave this setting unchanged.

INTEGER

The replica overhead percentage for rolling deploys.

BOOL

Whether the environment should rely on rolling deploy orchestration. Pass true or false explicitly; omit the flag to leave this setting unchanged.

TEXT

The rolling deploy strategy to use for promotions.One of: replica

INTEGER

The stabilization time for rolling deploys, in seconds.

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Turn on rolling deploys and scale the outgoing deployment to zero

baseten model environment update-promotion --model-id <model-id> --environment production --rolling-deploy true --promotion-cleanup-strategy scale-to-zero

Slow the rollout by lowering the surge percentage

baseten model environment update-promotion --model-id <model-id> --environment production --max-surge-percent 10

To configure mixed mode (beta): If mixed mode is enabled for your organization, replace <MODEL_ID> with your model’s ID and run the following command:

baseten model environment update-promotion --model-id "<MODEL_ID>" \
  --environment production \
  --rolling-deploy true \
  --max-surge-percent 25 \
  --max-unavailable-percent 10 \
  --jq '.environment.promotion_settings.rolling_deploy_config | {max_surge_percent, max_unavailable_percent}'

{
  "max_surge_percent": 25,
  "max_unavailable_percent": 10
}

Filter output with `--jq`

Print the resulting cleanup strategy

baseten model environment update-promotion --model-id <model-id> --environment production --rolling-deploy true --jq '.environment.promotion_settings.promotion_cleanup_strategy'

Output

Text mode (--output text): On success, prints “Updated promotion settings for environment name” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.UpdateEnvironmentResponse.

update-request-backpressure

baseten model environment update-request-backpressure [OPTIONS]

Set the policy applied when the environment’s request queue is full. Pass --policy null to clear an existing policy and fall back to the default. Run baseten model environment describe to see the current values.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT | null

required

Backpressure policy to apply. Pass null to clear an existing policy.One of: queue-on-full, reject-on-full, null

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Reject requests once the queue is full

baseten model environment update-request-backpressure --model-id <model-id> --environment production --policy reject-on-full

Clear the policy

baseten model environment update-request-backpressure --model-id <model-id> --environment production --policy null

Filter output with `--jq`

Print the resulting policy

baseten model environment update-request-backpressure --model-id <model-id> --environment production --policy reject-on-full --jq '.environment.request_backpressure_settings.policy'

Output

Text mode (--output text): The resulting policy, or “none” when no policy is set. JSON mode (--output json): payload type managementapi.UpdateEnvironmentResponse.

environment autoscaling-schedule

A schedule scales an environment to a target replica count over a recurring or one-time window. Manage the schedules themselves and the timezone they share.

create

baseten model environment autoscaling-schedule create [OPTIONS]

Add one autoscaling schedule to an environment. --cadence selects the schedule’s shape. ‘daily’ and ‘hourly’ are recurring and need --weekdays and a minute window; ‘one-time’ runs once and needs --start-at and --end-at instead. --min-replica and --max-replica are required. Any other autoscaling flag you omit is inherited from the environment while the schedule is active. --timezone is required for the first schedule on an environment, since the timezone is shared by the whole collection and has no default. Afterwards it is optional and must match the existing one; use ‘update-settings’ to change it for every schedule at once. Run ‘baseten model environment describe’ to see the current values.

Options

INTEGER

Timeframe of traffic considered for autoscaling decisions, in seconds.

TEXT

required

Shape of the schedule. Recurring schedules use --weekdays and a minute window; one-time schedules use --start-at and --end-at.One of: daily, hourly, one-time

INTEGER

Number of requests per replica before scaling up.

BOOL

Whether the schedule is enabled. Defaults to true on create.

TEXT

Exclusive end of the window, ISO 8601. One-time schedules only.

INTEGER

Hour the window closes, in the collection timezone. Omit for an hourly schedule that runs every hour. Recurring schedules only.

INTEGER

Minute the window closes. Recurring schedules only.

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

INTEGER

Maximum number of replicas.

INTEGER

Maximum percentage of replicas that can be removed per autoscaling window (1-50). For example, 20 means at most 20% of replicas are removed per window.

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

required

Name of the schedule, unique among the environment’s schedules.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

INTEGER

Waiting period before scaling down any active replica, in seconds.

TEXT

Inclusive start of the window, ISO 8601 (for example 2026-09-01T08:00). Values without a timezone designator are read in the local timezone. Must be in the future. One-time schedules only.

INTEGER

Hour the window opens, in the collection timezone. Omit for an hourly schedule that runs every hour. Recurring schedules only.

INTEGER

Minute the window opens. Recurring schedules only.

INTEGER

Target number of in-flight tokens for autoscaling decisions. Early access only.

INTEGER

Target utilization percentage for scaling up and down.

TEXT

Team name or ID. Only valid with --model-name.

TEXT

IANA timezone shared by every schedule on the environment, for example America/New_York. Required for the first schedule; afterwards it must match the existing one.

TEXT (repeatable)

Weekdays the schedule runs, comma-separated. Recurring schedules only.One of: monday, tuesday, wednesday, thursday, friday, saturday, sunday

INTEGER

Minimum number of replicas.

BOOL

Enable verbose logging

Examples

Scale up on weekday mornings

baseten model environment autoscaling-schedule create --model-id <model-id> --environment production --name weekday-peak --cadence daily --weekdays monday,tuesday,wednesday,thursday,friday --start-hour 8 --start-minute 0 --end-hour 18 --end-minute 0 --timezone America/New_York --min-replica 4 --max-replica 20

Scale up for a one-off launch window

baseten model environment autoscaling-schedule create --model-id <model-id> --environment production --name launch --cadence one-time --start-at 2026-09-01T08:00 --end-at 2026-09-01T20:00 --timezone America/New_York --min-replica 10 --max-replica 50

Filter output with `--jq`

Print the ids of every schedule after the create

baseten model environment autoscaling-schedule create --model-id <model-id> --environment production --name weekday-peak --cadence daily --weekdays monday --start-minute 0 --end-minute 0 --timezone UTC --min-replica 1 --max-replica 2 --jq '.environment.autoscaling_schedules.schedules[].id'

Output

Text mode (--output text): On success, prints “Created autoscaling schedule name” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.UpdateEnvironmentResponse.

delete

baseten model environment autoscaling-schedule delete [OPTIONS]

Remove one autoscaling schedule from an environment, identified by id or by name. Run ‘baseten model environment autoscaling-schedule list’ to see both.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Stable identifier of the schedule, from ‘autoscaling-schedule list’.Mutually exclusive with other flags in group schedule-ref.

TEXT

Name of the schedule, unique among the environment’s schedules.Mutually exclusive with other flags in group schedule-ref.

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Delete a schedule by id

baseten model environment autoscaling-schedule delete --model-id <model-id> --environment production --schedule-id <schedule-id>

Delete a schedule by name

baseten model environment autoscaling-schedule delete --model-id <model-id> --environment production --schedule-name weekday-peak

Filter output with `--jq`

Print the ids that remain

baseten model environment autoscaling-schedule delete --model-id <model-id> --environment production --schedule-id <schedule-id> --jq '.environment.autoscaling_schedules.schedules[].id'

Output

Text mode (--output text): On success, prints “Deleted autoscaling schedule id” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.UpdateEnvironmentResponse.

list

baseten model environment autoscaling-schedule list [OPTIONS]

List every autoscaling schedule on an environment with its id, which the update and delete commands take.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

List an environment’s schedules

baseten model environment autoscaling-schedule list --model-id <model-id> --environment production

Filter output with `--jq`

Print each schedule’s id and name

baseten model environment autoscaling-schedule list --model-id <model-id> --environment production --jq '.schedules[] | "\(.id) \(.name)"'

Output

Text mode (--output text): Table with columns: ID, NAME, CADENCE, ENABLED, WINDOW, REPLICAS. When no schedules exist, prints “No autoscaling schedules found.” to stderr. JSON mode (--output json): payload type managementapi.EnvironmentAutoscalingSchedules.

update

baseten model environment autoscaling-schedule update [OPTIONS]

Change one autoscaling schedule, identified by id or by name. Only the flags you pass are changed; the rest of the schedule is preserved. Because the API replaces a schedule wholesale, the command reads the environment first and merges your changes into the existing schedule. Pass --cadence to change a schedule’s shape. The new shape’s timing flags are then required, since a recurring window and a one-time interval have nothing in common to carry over; the name, enabled state, and autoscaling overrides carry over either way. --timezone is not accepted here, because it belongs to the whole collection; use ‘update-settings’.

Options

INTEGER

Timeframe of traffic considered for autoscaling decisions, in seconds.

TEXT

New shape for the schedule. Changing it requires the new shape’s timing flags, since there is nothing to carry over.One of: daily, hourly, one-time

INTEGER

Number of requests per replica before scaling up.

BOOL

Whether the schedule is enabled. Pass true or false explicitly; omit the flag to leave this setting unchanged.

TEXT

Exclusive end of the window, ISO 8601. One-time schedules only.

INTEGER

Hour the window closes, in the collection timezone. Omit for an hourly schedule that runs every hour. Recurring schedules only.

INTEGER

Minute the window closes. Recurring schedules only.

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

INTEGER

Maximum number of replicas.

INTEGER

Maximum percentage of replicas that can be removed per autoscaling window (1-50). For example, 20 means at most 20% of replicas are removed per window.

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

New name for the schedule, unique among the environment’s schedules.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

INTEGER

Waiting period before scaling down any active replica, in seconds.

TEXT

Stable identifier of the schedule, from ‘autoscaling-schedule list’.Mutually exclusive with other flags in group schedule-ref.

TEXT

Name of the schedule, unique among the environment’s schedules.Mutually exclusive with other flags in group schedule-ref.

TEXT

Inclusive start of the window, ISO 8601 (for example 2026-09-01T08:00). Values without a timezone designator are read in the local timezone. Must be in the future. One-time schedules only.

INTEGER

Hour the window opens, in the collection timezone. Omit for an hourly schedule that runs every hour. Recurring schedules only.

INTEGER

Minute the window opens. Recurring schedules only.

INTEGER

Target number of in-flight tokens for autoscaling decisions. Early access only.

INTEGER

Target utilization percentage for scaling up and down.

TEXT

Team name or ID. Only valid with --model-name.

TEXT (repeatable)

Weekdays the schedule runs, comma-separated. Recurring schedules only.One of: monday, tuesday, wednesday, thursday, friday, saturday, sunday

INTEGER

Minimum number of replicas.

BOOL

Enable verbose logging

Examples

Raise a schedule’s replica floor

baseten model environment autoscaling-schedule update --model-id <model-id> --environment production --schedule-id <schedule-id> --min-replica 6

Turn a schedule off without deleting it, naming it instead of using its id

baseten model environment autoscaling-schedule update --model-id <model-id> --environment production --schedule-name weekday-peak --enabled false

Convert a recurring schedule into a one-time one

baseten model environment autoscaling-schedule update --model-id <model-id> --environment production --schedule-name weekday-peak --cadence one-time --start-at 2026-09-01T08:00 --end-at 2026-09-01T20:00

Filter output with `--jq`

Print the resulting schedule names

baseten model environment autoscaling-schedule update --model-id <model-id> --environment production --schedule-id <schedule-id> --min-replica 6 --jq '.environment.autoscaling_schedules.schedules[].name'

Output

Text mode (--output text): On success, prints “Updated autoscaling schedule id” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.UpdateEnvironmentResponse.

update-settings

baseten model environment autoscaling-schedule update-settings [OPTIONS]

Change the settings shared by all of an environment’s autoscaling schedules. Today that is only the timezone. Setting the timezone rewrites every existing schedule, which is why it lives here rather than on ‘update’. The environment must already have at least one schedule, since the timezone is stored per schedule. Run ‘baseten model environment autoscaling-schedule list’ to see the schedules this affects.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

TEXT

required

IANA timezone to apply to every schedule on the environment, for example America/New_York.

BOOL

Enable verbose logging

Examples

Move every schedule to a new timezone

baseten model environment autoscaling-schedule update-settings --model-id <model-id> --environment production --timezone Europe/Berlin

Filter output with `--jq`

Print the resulting timezone

baseten model environment autoscaling-schedule update-settings --model-id <model-id> --environment production --timezone Europe/Berlin --jq '.environment.autoscaling_schedules.timezone'

Output

Text mode (--output text): On success, prints “Updated autoscaling schedule settings” to stderr; no stdout output. JSON mode (--output json): payload type managementapi.UpdateEnvironmentResponse.

environment traffic-rule

PRE-RELEASE: Traffic routing rules are not GA yet. Their arguments, flags, and output may change.

A traffic routing rule changes what happens to requests that reach an environment. A shadow rule sends a copy of a percentage of the environment’s traffic to another environment or a specific deployment and discards the responses, so you can test a candidate there against live traffic. A rule names its target once. Send traffic somewhere else by deleting the rule and creating a new one. Every rule carries an expiry, at most 7 days out. model environment describe shows an environment’s active rules.

list

baseten model environment traffic-rule list [OPTIONS]

Lists every active rule on an environment with the ID that update and delete take.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

List an environment’s rules

baseten model environment traffic-rule list --model-id <model-id> --environment production

Filter output with `--jq`

Print each rule’s ID and percentage

baseten model environment traffic-rule list --model-id <model-id> --environment production --jq '.rules[] | "\(.id) \(.percent_traffic)"'

Output

Text mode (--output text): Table with columns: ID, TYPE, TARGET, PERCENT, SAMPLING MODE, PROPAGATE CANCELLATION, EXPIRES. When no rules exist, prints “No traffic rules found.” to stderr. JSON mode (--output json): Go output type managementapi.EnvironmentTrafficRouting.

create

baseten model environment traffic-rule create [OPTIONS]

Adds a rule to an environment. Set one target with --target-environment or --target-deployment-id. A target environment sends the shadow traffic to whichever deployment that environment is serving. --sampling-mode random picks each request independently. --sampling-mode user-session keeps a whole session together, so every request in a sampled session is shadowed. --expires-at takes an ISO 8601 time such as 2026-11-02T18:00, at most 7 days out. --propagate-client-cancellation decides whether a shadow request is cancelled when the original client disconnects, and it needs an explicit true or false.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

required

When the rule stops, ISO 8601 (for example 2026-10-08T18:00), at most 7 days out. Values without a timezone designator are read in the local timezone.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

INTEGER

required

Percentage of the environment’s traffic to shadow.

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

BOOL

required

Whether a shadow request is cancelled when the original client disconnects.

TEXT

required

How requests are picked for shadowing. random picks each request independently. user-session keeps a whole session together.One of: random, user-session

TEXT

ID of the target deployment.Mutually exclusive with other flags in group target.

TEXT

Name of the target environment. Traffic goes to whichever deployment the environment is serving.Mutually exclusive with other flags in group target.

TEXT

Team name or ID. Only valid with --model-name.

TEXT

required

Rule type. A shadow rule sends a copy of the environment’s traffic to its target.One of: shadow

BOOL

Enable verbose logging

Examples

Shadow 25% of production’s traffic to staging

baseten model environment traffic-rule create --model-id <model-id> --environment production --type shadow --target-environment staging --percent-traffic 25 --expires-at <iso-time-within-7-days> --sampling-mode user-session --propagate-client-cancellation true

Shadow 10% of production’s traffic to a specific deployment

baseten model environment traffic-rule create --model-id <model-id> --environment production --type shadow --target-deployment-id <deployment-id> --percent-traffic 10 --expires-at <iso-time-within-7-days> --sampling-mode random --propagate-client-cancellation false

Filter output with `--jq`

Print the IDs of the environment’s active rules after the create

baseten model environment traffic-rule create --model-id <model-id> --environment production --type shadow --target-environment staging --percent-traffic 25 --expires-at <iso-time-within-7-days> --sampling-mode random --propagate-client-cancellation false --jq '.environment.traffic_routing.rules[].id'

Output

Text mode (--output text): Prints “Created traffic rule” to stderr; nothing on stdout. JSON mode (--output json): Go output type managementapi.UpdateEnvironmentResponse.

update

baseten model environment traffic-rule update [OPTIONS]

Changes one rule, identified by --rule-id. Only the flags you pass change; the command reads the environment, merges your flags into the existing rule, and writes it back, because the API replaces a rule wholesale.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

New time the rule stops, ISO 8601 (for example 2026-10-08T18:00), at most 7 days out. Values without a timezone designator are read in the local timezone.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

INTEGER

New percentage of the environment’s traffic to shadow.

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

BOOL

Whether a shadow request is cancelled when the original client disconnects.

TEXT

required

ID of the rule. Run ‘baseten model environment traffic-rule list’ to see the environment’s rules.

TEXT

New way requests are picked for shadowing.One of: random, user-session

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Enable verbose logging

Examples

Raise the percentage of traffic a rule shadows

baseten model environment traffic-rule update --model-id <model-id> --environment production --rule-id <rule-id> --percent-traffic 50

Filter output with `--jq`

Print each active rule’s percentage after the update

baseten model environment traffic-rule update --model-id <model-id> --environment production --rule-id <rule-id> --percent-traffic 50 --jq '.environment.traffic_routing.rules[].percent_traffic'

Output

Text mode (--output text): Prints “Updated traffic rule id” to stderr; nothing on stdout. JSON mode (--output json): Go output type managementapi.UpdateEnvironmentResponse.

delete

baseten model environment traffic-rule delete [OPTIONS]

Removes one rule from an environment, identified by --rule-id. Prompts for yes/no confirmation. Pass --yes to skip the prompt. When stdin is not a terminal, --yes is required.

Options

TEXT

required

Name of the environment (e.g. production). Run ‘baseten model environment list’ to see a model’s environments.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

ID of the model.Mutually exclusive with other flags in group model-ref.

TEXT

Name of the model. Use --team to disambiguate when the same name exists in multiple teams.Mutually exclusive with other flags in group model-ref.

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

TEXT

required

ID of the rule. Run ‘baseten model environment traffic-rule list’ to see the environment’s rules.

TEXT

Team name or ID. Only valid with --model-name.

BOOL

Skip the interactive confirmation prompt. Required when stdin is not a terminal.

BOOL

Enable verbose logging

Examples

Delete a rule

baseten model environment traffic-rule delete --model-id <model-id> --environment production --rule-id <rule-id> --yes

Filter output with `--jq`

Print the IDs of the rules that remain

baseten model environment traffic-rule delete --model-id <model-id> --environment production --rule-id <rule-id> --yes --jq '.environment.traffic_routing.rules[].id'

Output

Text mode (--output text): Prints “Deleted traffic rule id” to stderr; nothing on stdout. JSON mode (--output json): Go output type managementapi.UpdateEnvironmentResponse.

image

Build a local Docker image, or just its Docker build context, from a model directory. These commands run entirely locally: they shell out to the truss CLI (via ‘uv’) to generate the build context and to ‘docker’ to build the image. They need no authentication and make no Baseten API calls. ‘uv’ must be on PATH; ‘build’ also requires ‘docker’.

build

baseten model image build [OPTIONS] [-- DOCKER_BUILD_ARGS...]

Generate the Docker build context for a model directory and build it into a local Docker image. The current directory is used by default; pass --dir to point at a model directory elsewhere. The build context is written to a temporary directory that is removed afterward unless --build-dir is given. Any arguments after ’—’ are passed through verbatim to ‘docker build’. If you supply your own --iidfile there, it is honored and used to report the image ID; otherwise one is injected internally.

Options

TEXT

Directory for the Docker build context. Defaults to a temp dir removed after the build.

TEXT

Enable a persistent apt/pip/uv build cache keyed by this id.

TEXT

default:"."

Model directory.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

BOOL

Run the image’s container as root instead of the default non-root user.

TEXT

Image tag. Defaults to ‘model_name:latest’ from config.yaml.

TEXT

Run this truss executable instead of fetching one with uv, e.g. a virtualenv’s bin/truss. A value with no path separator is looked up on PATH, so ‘--truss-executable truss’ runs the truss you installed. Defaults to BASETEN_TRUSS_EXECUTABLE.

TEXT

Version of truss to fetch and run with ‘uv tool run’, e.g. 0.18.26. Defaults to BASETEN_TRUSS_VERSION, or the latest release. Mutually exclusive with --truss-executable.

BOOL

Enable verbose logging

Examples

Build the current directory into a local Docker image

baseten model image build

Build another directory with a custom tag

baseten model image build --dir ./my-model --tag my-model:dev

Pass extra flags through to docker build

baseten model image build -- --no-cache --build-arg FOO=bar

Filter output with `--jq`

Print the built image ID

baseten model image build --jq '.image_id'

Output

Text mode (--output text): Build progress from truss and docker is streamed to stderr. On success a one-line summary is printed to stdout. JSON mode (--output json): payload type cmd.ModelImageBuildResult. Under --output json, stdout is the {image_id, tag} result. image_id is empty when it cannot be resolved (e.g. a custom buildx builder that does not write the iidfile).

prepare

baseten model image prepare [OPTIONS] --build-dir DIR

Generate the Docker build context (Dockerfile and supporting files) for a model directory into --build-dir, without building an image. The current directory is used by default; pass --dir to point at a model directory elsewhere. The resulting directory is self-contained and can be built with ‘docker build build-dir’.

Options

TEXT

required

Directory for the Docker build context. Created if absent and kept.

TEXT

Enable a persistent apt/pip/uv build cache keyed by this id.

TEXT

default:"."

Model directory.

TEXT

Filter JSON output with a jq expression; implies --output json (or jsonl for streamed commands)

TEXT

default:"text"

Output formatOne of: text, json, jsonl, none

TEXT

Use a specific stored profile for this command, overriding BASETEN_PROFILE and the current profile

BOOL

Run the image’s container as root instead of the default non-root user.

TEXT

Version of truss to fetch and run with ‘uv tool run’, e.g. 0.18.26. Defaults to BASETEN_TRUSS_VERSION, or the latest release. Mutually exclusive with --truss-executable.

BOOL

Enable verbose logging

Examples

Write the current directory’s build context to ./ctx

baseten model image prepare --build-dir ./ctx

Filter output with `--jq`

Print the generated Dockerfile path

baseten model image prepare --build-dir ./ctx --jq '.dockerfile'

Output

Text mode (--output text): Progress from truss is streamed to stderr. On success a one-line summary is printed to stdout. JSON mode (--output json): payload type cmd.ModelImagePrepareResult. Under --output json, stdout is the {build_dir, dockerfile} result with absolute paths.

⌘I

​push

​Options

​Examples

​Filter output with --jq

​Output

​watch

​Options

​Examples

​Output

​list

​Options

​Examples

​Filter output with --jq

​Output

​describe

​Options

​Examples

​Filter output with --jq

​Output

​predict

​Options

​Examples

​Filter output with --jq

​Output

​delete

​Options

​Examples

​Filter output with --jq

​Output

​rename

​Options

​Examples

​Filter output with --jq

​Output

​audit-logs

​Options

​Examples

​Filter output with --jq

​Output

​deployment

​activate

​Options

​Examples

​Filter output with --jq

​Output

​config

​Options

​Examples

​Filter output with --jq

​Output

​deactivate

​Options

​Examples

​Filter output with --jq

​Output

​download

​Options

​Examples

​Filter output with --jq

​Output

​promote

​Options

​Examples

​Filter output with --jq

​Output

​delete

​Options

​Examples

​Filter output with --jq

​Output

​describe

​Options

​Examples

​Filter output with --jq

​Output

​list

​Options

​Examples

​Filter output with --jq

​Output

push

Options

Examples

Filter output with `--jq`

Output

watch

Options

Examples

Output

list

Options

Examples

Filter output with `--jq`

Output

describe

Options

Examples

Filter output with `--jq`

Output

predict

Options

Examples

Filter output with `--jq`

Output

delete

Options

Examples

Filter output with `--jq`

Output

rename

Options

Examples

Filter output with `--jq`

Output

audit-logs

Options

Examples

Filter output with `--jq`

Output

deployment

activate

Options

Examples

Filter output with `--jq`

Output

config

Options

Examples

Filter output with `--jq`

Output

deactivate

Options

Examples

Filter output with `--jq`

Output

download

Options

Examples

Filter output with `--jq`

Output

promote

Options

Examples

Filter output with `--jq`

Output

delete

Options

Examples

Filter output with `--jq`

Output

describe

Options

Examples

Filter output with `--jq`

Output

list

Options

Examples

Filter output with `--jq`

Output