baseten model-api

List and inspect Baseten Model APIs. Authenticate with baseten auth login or the BASETEN_API_KEY environment variable.

describe

baseten model-api describe [OPTIONS]

Describe a single Model API by name.

Options

TEXT

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

TEXT

required

Name of the Model API to describe.

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

Enable verbose logging

Examples

Describe a Model API by name

baseten model-api describe --model <name>

Filter output with `--jq`

Print the Model API’s invoke URL

baseten model-api describe --model <name> --jq '.invoke_url'

Output

Text mode (--output text): Field-per-line summary of the Model API. JSON mode (--output json): payload type managementapi.ModelAPI.

list

baseten model-api list [OPTIONS]

List the Model APIs in the full visible catalog. Pass --added-only to restrict to just the Model APIs the workspace has added.

CLI v0.3.0 removed --all and changed the default: baseten model-api list now returns the full catalog instead of just added Model APIs. Scripts that relied on the old default should pass --added-only.

Options

BOOL

Restrict to the Model APIs the workspace has added instead of the full visible catalog.

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

Enable verbose logging

Examples

List the full visible catalog of Model APIs

baseten model-api list

List only the Model APIs the workspace has added

baseten model-api list --added-only

Filter output with `--jq`

Print just the Model API names

baseten model-api list --jq '.items[].name'

Output

Text mode (--output text): Table with columns: NAME, CONTEXT,

/1M IN,

/1M OUT, ADDED. When no Model APIs match, prints “No Model APIs found.” to stderr. JSON mode (--output json): payload type cmd.ModelAPIList.

predict

baseten model-api predict [OPTIONS]

POST an inference request to a Model API and write the response to stdout. The request is sent to --url, which defaults to the OpenAI chat-completions endpoint on the shared inference host. Override it for other shapes (e.g. /v1/messages, /v1/embeddings) or different hosts. --content is the simple path: it builds an OpenAI chat-completions body with a single user message and --model as the model, and prints just the assistant’s reply. It is only valid for OpenAI chat URLs and requires --model. --data and --file send a request body verbatim, so any format the endpoint accepts works (OpenAI, Anthropic, embeddings, custom). The response is written as-is: JSON is pretty-printed, streams and binary bodies are passed through.

Options

TEXT

Single user message; builds an OpenAI chat-completions request and prints the assistant’s reply. Only valid for OpenAI chat URLs and requires —model.Mutually exclusive with other flags in group predict-input.

TEXT

Inline request body, sent verbatim.Mutually exclusive with other flags in group predict-input.

TEXT

Path to a file containing the request body, sent verbatim. 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

Name of the Model API. Required with —content, where it sets the request’s model.

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

Endpoint to POST the request to. Defaults to https://inference.baseten.co/v1/chat/completions.

BOOL

Enable verbose logging

Examples

Send a single user message

baseten model-api predict --model <name> --content "hello"

Send a full OpenAI-shaped body and stream it as JSONL

baseten model-api predict --model <name> --data '{"model":"<name>","messages":[{"role":"user","content":"hi"}],"stream":true}' --output jsonl

Filter output with `--jq`

Extract the assistant’s message content

baseten model-api predict --model <name> --content "hi" --jq '.choices[0].message.content'

Output

Text mode (--output text): With --content, the assistant message text. With --data/--file, the response body as-is (pretty-printed JSON, or a raw stream/binary body). JSON mode (--output json): payload type cmd.JSONUndefined. Under --output json, --content emits the full chat-completions response. For --data/--file, a streamed response becomes one JSON record per chunk under --output jsonl, and a binary body is base64-encoded under a ‘body’ key.

usage

baseten model-api usage [OPTIONS]

Show the workspace’s Model APIs token usage as contiguous time buckets, oldest first, broken down by the dimensions passed to --group-by. Buckets with no usage are included, so the series has no gaps. Usage is retained for 92 days; buckets older than that come back empty. Every bucket in the window is fetched, paging as needed, until --limit buckets are collected. Usage is attributed to a user when the request was authenticated with a personal API key or an OAuth credential. Usage from workspace or other non-user-scoped credentials has no user. For machine-readable streaming, prefer --output jsonl over --output json.

Options

TEXT (repeatable)

Only return usage for these API key prefixes. May be repeated.

TEXT

default:"1d"

Width of each time bucket. Also sets the default window: 7d for 1d, 24h for 1h, 60m for 1m.One of: 1m, 1h, 1d

TEXT

End of the range, exclusive. ISO 8601, local when no timezone is given. Defaults to now.

TEXT (repeatable)

Dimension to break usage down by. May be repeated. One of: api-key, user, model. Defaults to model.

TEXT

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

INTEGER

Maximum number of time buckets, paging as needed. Rows per bucket depend on —group-by. 0 for no limit.

TEXT (repeatable)

Only return usage for these models. May be repeated.

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

Window from a relative time ago until now (e.g. ‘30m’, ‘3d’). Mutually exclusive with —start and —end.

TEXT

Start of the range, inclusive, snapped down to its bucket start. ISO 8601, local when no timezone is given.

TEXT (repeatable)

Only return usage attributed to these user IDs. May be repeated.

BOOL

Enable verbose logging

Examples

Show daily usage per model over the last 7 days

baseten model-api usage

Show which users drove usage over the last 3 days

baseten model-api usage --since 3d --group-by user

Break hourly usage down by user and model for one model

baseten model-api usage --since 12h --bucket-width 1h --group-by user --group-by model --model <name>

Filter output with `--jq`

Stream each bucket’s per-user output tokens as a JSONL stream

baseten model-api usage --group-by user --output jsonl --jq '.results[] | {user_id, output_tokens}'

Output

Text mode (--output text): Table with a time column, one column per --group-by dimension, then REQUESTS, INPUT, CACHED, and OUTPUT token counts, followed by an ALL totals row. A bucket with no usage renders as a single “(no usage)” row. When no bucket in the window has any usage, prints “No usage in the selected window.” to stderr instead of a table. JSON mode (--output json): payload type managementapi.ModelApisUsageBucket. One record per time bucket: its start_time, end_time, and the per-dimension usage totals in results.

Reference

Inference API

Management API

CLI reference

SDK reference

Training API

Frontier Gateway API

CI/CD

baseten model-api

describe

Options

Examples

Filter output with `--jq`

Output

list

Options

Examples

Filter output with `--jq`

Output

predict

Options

Examples

Filter output with `--jq`

Output

usage

Options

Examples

Filter output with `--jq`

Output

​describe

​Options

​Examples

​Filter output with --jq

​Output

​list

​Options

​Examples

​Filter output with --jq

​Output

​predict

​Options

​Examples

​Filter output with --jq

​Output

​usage

​Options

​Examples

​Filter output with --jq

​Output

describe

Options

Examples

Filter output with `--jq`

Output

list

Options

Examples

Filter output with `--jq`

Output

predict

Options

Examples

Filter output with `--jq`

Output

usage

Options

Examples

Filter output with `--jq`

Output