LiteLLM

App · 20 actions

Manage your LiteLLM Proxy: send prompts to its models, create, limit, block and replace keys, manage teams and users, and read what each request cost. Start a workflow when a key nears its budget or is about to expire, or a request fails.

Actions

ActionWhat it does
Add team memberAdd someone to a team, by user or by email address.
Block or unblock keyBlock a key so every request with it is refused, such as when it has leaked, or unblock it again.
Create keyCreate a key for an app or person to call your proxy with, with an optional budget, limits, models and end date.
Create teamCreate a team, with an optional budget, limits and models that every key of the team shares.
Create userAdd a person to your proxy, with a role, an optional budget and team, and a key of their own if asked.
Delete keyDelete a key for good, so requests with it are refused.
Delete teamDelete a team and its keys, for good.
Get keyGet one key's details: what it has spent, its budget, limits, models, expiry and whether it is blocked.
Get teamGet one team's details: its members, budget, spend, models and keys.
List keysList the proxy's keys with their spend, budget, models and expiry, optionally only one team's or user's.
List modelsList the models set up on your proxy, with who serves each, what it does, its token limits and prices.
List request logsList the requests made through your proxy in a time range, newest first, with each one's model, cost, tokens, key, team and any error.
List teamsList the proxy's teams with their members, budget, spend and models.
List usersList the proxy's users with their role, budget and spend, optionally only one role or team.
Remove team memberTake someone off a team, by user or by email address.
Replace keyReplace a key with a new one that keeps its settings and spend; the old key stops working.
Send a promptSend a prompt to one of your proxy's models and get its reply, with the tokens it used and what it cost.
Update keyChange a key's name, models, budget, limits or end date.
Update teamChange a team's name, models, budget or limits, or block it so none of its keys work.
Update userChange a user's email, name, role, models or budget.

Add team member

Add someone to a team, by user or by email address. LiteLLM adds them as a user if the email is new.

Inputs

Teamlitellm_team_idtextRequired
The team. Pick one, or give its ID from an earlier step.
Userlitellm_user_idtext
The user to add. Give this or an email address.
Emailemailtext
The email address of who to add, if they aren't a user yet.
Role on the teamroletext
Team admins can manage the team. Defaults to Member.One of: user (Member), admin (Team admin). Default: user.
Their budget (US dollars)max_budget_in_teamnumber
The most they may spend through the team.At least 0.

Outputs

teamobject
The team, as it is now
userobject
The member
Example output
{
  "team": {
    "blocked": false,
    "budget_duration": "1mo",
    "budget_reset_at": "2026-12-01T00:00:00Z",
    "created_at": "2026-10-01T09:00:00Z",
    "max_budget": 200.0,
    "members_with_roles": [
      {
        "role": "admin",
        "user_email": "amelie@example.com",
        "user_id": "amelie@example.com"
      }
    ],
    "metadata": {},
    "models": [
      "gpt-4o-mini",
      "claude-sonnet"
    ],
    "rpm_limit": 120,
    "spend": 31.2,
    "team_alias": "Support",
    "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
    "tpm_limit": 200000
  },
  "user": {
    "budget_duration": "30d",
    "created_at": "2026-10-01T09:00:00Z",
    "max_budget": 20.0,
    "metadata": {},
    "models": [],
    "spend": 4.1,
    "teams": [
      "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab"
    ],
    "user_alias": "Amelie",
    "user_email": "amelie@example.com",
    "user_id": "amelie@example.com",
    "user_role": "internal_user"
  }
}

Block or unblock key

Block a key so every request with it is refused, such as when it has leaked, or unblock it again.

Inputs

Keykey_idtextRequired
The key. Pick one, or give its ID (token) from an earlier step.
Block or unblockdecisiontextRequired
Block stops the key working; unblock lets it work again.One of: block (Block (the key stops working)), unblock (Unblock (the key works again)).

Outputs

keyobject
The key, as it is now
Example output
{
  "key": {
    "blocked": true,
    "budget_duration": "30d",
    "budget_reset_at": "2026-12-01T00:00:00Z",
    "created_at": "2026-11-06T12:00:00Z",
    "expires": "2027-11-06T12:00:00Z",
    "key_alias": "support-bot",
    "key_name": "sk-...Xy9Q",
    "max_budget": 50.0,
    "metadata": {
      "owner": "support"
    },
    "models": [
      "gpt-4o-mini"
    ],
    "rpm_limit": 60,
    "spend": 12.48,
    "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
    "token": "8a9b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f6789",
    "tpm_limit": 100000,
    "user_id": "amelie@example.com"
  }
}

Create key

Create a key for an app or person to call your proxy with, with an optional budget, limits, models and end date. The key is in the result once only, as 'api_key'.

Inputs

Key namekey_aliastext
A name to know the key by, such as support-bot.
Modelsmodelslist
The models the key may call. Leave empty for every model.
Budget (US dollars)max_budgetnumber
The most the key may spend; requests are refused once it is used up.At least 0.
Budget starts againbudget_periodtext
How often the spend goes back to zero. Leave empty for never.One of: 1h (Every hour), 1d (Every day), 7d (Every 7 days), 30d (Every 30 days), 1mo (Every calendar month).
Works forlifetimetext
How long the key works from now. Leave empty for no end date.One of: 1h (1 hour), 1d (1 day), 7d (7 days), 30d (30 days), 90d (90 days), 365d (1 year).
Teamlitellm_team_idtext
The team the key belongs to; the team's limits apply.
Userlitellm_user_idtext
The user the key belongs to.
Tokens a minutetpm_limitnumber
The most tokens the key may use a minute.At least 0.
Requests a minuterpm_limitnumber
The most requests the key may make a minute.At least 0.
Metadatametadataobject
Names and values to keep with the key, such as who it is for. Added to any it already has.

Outputs

api_keytext
The key itself (sk-...), shown only this once
detailsobject
Everything else LiteLLM returned
expirestext
When it stops working (ISO 8601)
key_aliastext
The key's name
key_idtext
The key's ID, for the other key steps
Example output
{
  "api_key": "sk-RV-l2BJEZ_LYNChSx2EueQ",
  "details": {
    "max_budget": 50.0,
    "models": [
      "gpt-4o-mini"
    ],
    "team_id": null
  },
  "expires": "2027-11-06T12:00:00Z",
  "key_alias": "support-bot",
  "key_id": "8a9b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f6789"
}

Create team

Create a team, with an optional budget, limits and models that every key of the team shares.

Inputs

Team nameteam_aliastextRequired
The team's name, such as Support.
Modelsmodelslist
The models the team may call. Leave empty for every model.
Budget (US dollars)max_budgetnumber
The most the team may spend; requests are refused once it is used up.At least 0.
Budget starts againbudget_periodtext
How often the spend goes back to zero. Leave empty for never.One of: 1h (Every hour), 1d (Every day), 7d (Every 7 days), 30d (Every 30 days), 1mo (Every calendar month).
Tokens a minutetpm_limitnumber
The most tokens the team may use a minute.At least 0.
Requests a minuterpm_limitnumber
The most requests the team may make a minute.At least 0.
Metadatametadataobject
Names and values to keep with the team, such as who it is for. Added to any it already has.

Outputs

teamobject
The new team
Example output
{
  "team": {
    "blocked": false,
    "budget_duration": "1mo",
    "budget_reset_at": "2026-12-01T00:00:00Z",
    "created_at": "2026-10-01T09:00:00Z",
    "max_budget": 200.0,
    "members_with_roles": [
      {
        "role": "admin",
        "user_email": "amelie@example.com",
        "user_id": "amelie@example.com"
      }
    ],
    "metadata": {},
    "models": [
      "gpt-4o-mini",
      "claude-sonnet"
    ],
    "rpm_limit": 120,
    "spend": 31.2,
    "team_alias": "Support",
    "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
    "tpm_limit": 200000
  }
}

Create user

Add a person to your proxy, with a role, an optional budget and team, and a key of their own if asked.

Inputs

Emailuser_emailtextRequired
Their email address.
Nameuser_aliastext
Their name, as the admin page shows it.
Roleuser_roletext
What they may do on the proxy.One of: internal_user (Internal user (can create and use their own keys)), internal_user_viewer (Internal user, view only), proxy_admin (Admin (can do everything)), proxy_admin_viewer (Admin, view only).
Teamlitellm_team_idtext
A team to put them on.
Modelsmodelslist
The models they may call. Leave empty for every model.
Budget (US dollars)max_budgetnumber
The most they may spend; requests are refused once it is used up.At least 0.
Budget starts againbudget_periodtext
How often the spend goes back to zero. Leave empty for never.One of: 1h (Every hour), 1d (Every day), 7d (Every 7 days), 30d (Every 30 days), 1mo (Every calendar month).
Create a key for themcreate_keytrue/false
Also make them a key, returned once as 'api_key'.
Email them an invitesend_invite_emailtrue/false
Send them LiteLLM's invite email (needs email set up on the proxy).

Outputs

api_keytext
Their key, if one was asked for, shown only once
userobject
The new user
user_idtext
The new user's ID
Example output
{
  "api_key": "",
  "user": {
    "budget_duration": "30d",
    "created_at": "2026-10-01T09:00:00Z",
    "max_budget": 20.0,
    "metadata": {},
    "models": [],
    "spend": 4.1,
    "teams": [
      "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab"
    ],
    "user_alias": "Amelie",
    "user_email": "amelie@example.com",
    "user_id": "amelie@example.com",
    "user_role": "internal_user"
  },
  "user_id": "amelie@example.com"
}

Delete key

Delete a key for good, so requests with it are refused.

Inputs

Keykey_idtextRequired
The key. Pick one, or give its ID (token) from an earlier step.

Outputs

deletedtrue/false
Always true once done
key_idtext
The key deleted
Example output
{
  "deleted": true,
  "key_id": "8a9b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f6789"
}

Delete team

Delete a team and its keys, for good.

Inputs

Teamlitellm_team_idtextRequired
The team. Pick one, or give its ID from an earlier step.

Outputs

deletedtrue/false
Always true once done
team_idtext
The team deleted
Example output
{
  "deleted": true,
  "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab"
}

Get key

Get one key's details: what it has spent, its budget, limits, models, expiry and whether it is blocked.

Inputs

Keykey_idtextRequired
The key. Pick one, or give its ID (token) from an earlier step.

Outputs

keyobject
The key, as it is now
Example output
{
  "key": {
    "blocked": false,
    "budget_duration": "30d",
    "budget_reset_at": "2026-12-01T00:00:00Z",
    "created_at": "2026-11-06T12:00:00Z",
    "expires": "2027-11-06T12:00:00Z",
    "key_alias": "support-bot",
    "key_name": "sk-...Xy9Q",
    "max_budget": 50.0,
    "metadata": {
      "owner": "support"
    },
    "models": [
      "gpt-4o-mini"
    ],
    "rpm_limit": 60,
    "spend": 12.48,
    "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
    "token": "8a9b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f6789",
    "tpm_limit": 100000,
    "user_id": "amelie@example.com"
  }
}

Get team

Get one team's details: its members, budget, spend, models and keys.

Inputs

Teamlitellm_team_idtextRequired
The team. Pick one, or give its ID from an earlier step.

Outputs

keyslist
The team's keys
teamobject
The team
Example output
{
  "keys": [
    {
      "blocked": false,
      "budget_duration": "30d",
      "budget_reset_at": "2026-12-01T00:00:00Z",
      "created_at": "2026-11-06T12:00:00Z",
      "expires": "2027-11-06T12:00:00Z",
      "key_alias": "support-bot",
      "key_name": "sk-...Xy9Q",
      "max_budget": 50.0,
      "metadata": {
        "owner": "support"
      },
      "models": [
        "gpt-4o-mini"
      ],
      "rpm_limit": 60,
      "spend": 12.48,
      "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
      "token": "8a9b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f6789",
      "tpm_limit": 100000,
      "user_id": "amelie@example.com"
    }
  ],
  "team": {
    "blocked": false,
    "budget_duration": "1mo",
    "budget_reset_at": "2026-12-01T00:00:00Z",
    "created_at": "2026-10-01T09:00:00Z",
    "max_budget": 200.0,
    "members_with_roles": [
      {
        "role": "admin",
        "user_email": "amelie@example.com",
        "user_id": "amelie@example.com"
      }
    ],
    "metadata": {},
    "models": [
      "gpt-4o-mini",
      "claude-sonnet"
    ],
    "rpm_limit": 120,
    "spend": 31.2,
    "team_alias": "Support",
    "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
    "tpm_limit": 200000
  }
}

List keys

List the proxy's keys with their spend, budget, models and expiry, optionally only one team's or user's.

Inputs

Teamlitellm_team_idtext
Only this team's keys.
Userlitellm_user_idtext
Only this user's keys.
Key namekey_aliastext
Only keys with exactly this name.
Most to returnlimitnumber
How many to return at most, newest first. Defaults to 100.From 1 to 1000.

Outputs

countnumber
How many
keyslist
The keys
Example output
{
  "count": 1,
  "keys": [
    {
      "blocked": false,
      "budget_duration": "30d",
      "budget_reset_at": "2026-12-01T00:00:00Z",
      "created_at": "2026-11-06T12:00:00Z",
      "expires": "2027-11-06T12:00:00Z",
      "key_alias": "support-bot",
      "key_name": "sk-...Xy9Q",
      "max_budget": 50.0,
      "metadata": {
        "owner": "support"
      },
      "models": [
        "gpt-4o-mini"
      ],
      "rpm_limit": 60,
      "spend": 12.48,
      "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
      "token": "8a9b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f6789",
      "tpm_limit": 100000,
      "user_id": "amelie@example.com"
    }
  ]
}

List models

List the models set up on your proxy, with who serves each, what it does, its token limits and prices.

Inputs

Modelmodeltext
Only this model's deployments. Leave empty for every model.

Outputs

countnumber
How many
modelslist
The models
Example output
{
  "count": 1,
  "models": [
    {
      "input_cost_per_token": 1.5e-07,
      "max_input_tokens": 128000,
      "max_output_tokens": 16384,
      "mode": "chat",
      "model_id": "112f74fab24a7a5245d2ced3536dd8f5",
      "model_info": {
        "id": "112f74fab24a7a5245d2ced3536dd8f5",
        "mode": "chat"
      },
      "model_name": "gpt-4o-mini",
      "output_cost_per_token": 6e-07,
      "provider": "openai",
      "provider_model": "openai/gpt-4o-mini"
    }
  ]
}

List request logs

List the requests made through your proxy in a time range, newest first, with each one's model, cost, tokens, key, team and any error.

Inputs

Fromstart_timedate and time
The earliest request to include. Defaults to 24 hours ago.
Toend_timedate and time
The latest request to include. Defaults to now.
Outcomestatustext
Only requests that succeeded, or only those that failed.One of: success (Succeeded), failure (Failed).
Modelmodeltext
Only requests to this model.
Keykey_idtext
Only requests made with this key.
Teamlitellm_team_idtext
Only requests made with this team's keys.
Userlitellm_user_idtext
Only this user's requests.
Most to returnlimitnumber
How many to return at most, newest first. Defaults to 100.From 1 to 1000.

Outputs

countnumber
How many
end_timetext
The end of the range
logslist
The requests
start_timetext
The start of the range
total_spendnumber
What these requests cost together, in US dollars
Example output
{
  "count": 1,
  "end_time": "2026-11-06T12:00:00+00:00",
  "logs": [
    {
      "cache_hit": false,
      "call_type": "acompletion",
      "completion_tokens": 0,
      "duration_ms": 812,
      "end_user": "customer-42",
      "ended_at": "2026-11-06T11:58:03Z",
      "error_class": "RateLimitError",
      "error_code": "429",
      "error_message": "Rate limit reached for gpt-4o-mini",
      "key_alias": "support-bot",
      "key_id": "8a9b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f6789",
      "model": "gpt-4o-mini",
      "prompt_tokens": 0,
      "provider": "openai",
      "provider_model": "gpt-4o-mini",
      "request_id": "chatcmpl-6dcb2540-d3d7-4e49-bb27-291f863f112e",
      "request_tags": [],
      "spend": 0.0,
      "started_at": "2026-11-06T11:58:02Z",
      "status": "failure",
      "team_alias": "Support",
      "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
      "total_tokens": 0,
      "user_id": "amelie@example.com"
    }
  ],
  "start_time": "2026-11-05T12:00:00+00:00",
  "total_spend": 0.0
}

List teams

List the proxy's teams with their members, budget, spend and models.

Inputs

Userlitellm_user_idtext
Only the teams this user is on.

Outputs

countnumber
How many
teamslist
The teams
Example output
{
  "count": 1,
  "teams": [
    {
      "blocked": false,
      "budget_duration": "1mo",
      "budget_reset_at": "2026-12-01T00:00:00Z",
      "created_at": "2026-10-01T09:00:00Z",
      "max_budget": 200.0,
      "members_with_roles": [
        {
          "role": "admin",
          "user_email": "amelie@example.com",
          "user_id": "amelie@example.com"
        }
      ],
      "metadata": {},
      "models": [
        "gpt-4o-mini",
        "claude-sonnet"
      ],
      "rpm_limit": 120,
      "spend": 31.2,
      "team_alias": "Support",
      "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
      "tpm_limit": 200000
    }
  ]
}

List users

List the proxy's users with their role, budget and spend, optionally only one role or team.

Inputs

Roleroletext
Only users with this role.One of: internal_user (Internal user (can create and use their own keys)), internal_user_viewer (Internal user, view only), proxy_admin (Admin (can do everything)), proxy_admin_viewer (Admin, view only).
Teamlitellm_team_idtext
Only this team's users.
Most to returnlimitnumber
How many to return at most, newest first. Defaults to 100.From 1 to 1000.

Outputs

countnumber
How many
userslist
The users
Example output
{
  "count": 1,
  "users": [
    {
      "budget_duration": "30d",
      "created_at": "2026-10-01T09:00:00Z",
      "max_budget": 20.0,
      "metadata": {},
      "models": [],
      "spend": 4.1,
      "teams": [
        "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab"
      ],
      "user_alias": "Amelie",
      "user_email": "amelie@example.com",
      "user_id": "amelie@example.com",
      "user_role": "internal_user"
    }
  ]
}

Remove team member

Take someone off a team, by user or by email address.

Inputs

Teamlitellm_team_idtextRequired
The team. Pick one, or give its ID from an earlier step.
Userlitellm_user_idtext
The user to remove. Give this or an email address.
Emailemailtext
The email address of who to remove.

Outputs

removedtrue/false
Always true once done
team_idtext
The team
user_emailtext
Who was removed, if named by email
user_idtext
Who was removed, if named by user
Example output
{
  "removed": true,
  "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
  "user_email": "",
  "user_id": "amelie@example.com"
}

Replace key

Replace a key with a new one that keeps its settings and spend; the old key stops working. Needs LiteLLM Enterprise. The new key is in the result once only, as 'api_key'.

Inputs

Keykey_idtextRequired
The key. Pick one, or give its ID (token) from an earlier step.

Outputs

api_keytext
The key itself (sk-...), shown only this once
detailsobject
Everything else LiteLLM returned
expirestext
When it stops working (ISO 8601)
key_aliastext
The key's name
key_idtext
The key's ID, for the other key steps
Example output
{
  "api_key": "sk-RV-l2BJEZ_LYNChSx2EueQ",
  "details": {
    "max_budget": 50.0,
    "models": [
      "gpt-4o-mini"
    ],
    "team_id": null
  },
  "expires": "2027-11-06T12:00:00Z",
  "key_alias": "support-bot",
  "key_id": "8a9b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f6789"
}

Send a prompt

Send a prompt to one of your proxy's models and get its reply, with the tokens it used and what it cost. The proxy's budgets and limits apply as usual.

Inputs

ModelmodeltextRequired
The model to ask, as named on your proxy.
PromptprompttextRequired
What to ask the model.
Instructionssystem_prompttext
How the model should answer, such as 'Reply in one sentence'.
Temperaturetemperaturenumber
From 0 (the same answer each time) to 2 (more varied). Leave empty for the model's default.From 0 to 2.
Longest reply (tokens)max_tokensnumber
The most tokens the reply may have.At least 1.

Outputs

completion_tokensnumber
Tokens in the reply
costnumber
What it cost in US dollars, as the proxy worked it out
finish_reasontext
Why it stopped, such as stop or length
modeltext
The model that replied
prompt_tokensnumber
Tokens sent
replytext
The model's reply
request_idtext
The request's ID, as in the request logs
total_tokensnumber
Tokens in all
Example output
{
  "completion_tokens": 8,
  "cost": 8.4e-06,
  "finish_reason": "stop",
  "model": "gpt-4o-mini",
  "prompt_tokens": 24,
  "reply": "Your order shipped this morning.",
  "request_id": "chatcmpl-6dcb2540-d3d7-4e49-bb27-291f863f112e",
  "total_tokens": 32
}

Update key

Change a key's name, models, budget, limits or end date. Fields left empty keep their value.

Inputs

Keykey_idtextRequired
The key. Pick one, or give its ID (token) from an earlier step.
Key namekey_aliastext
A new name for the key.
Modelsmodelslist
The models the key may call. Leave empty for every model.
Budget (US dollars)max_budgetnumber
The most the key may spend; requests are refused once it is used up.At least 0.
Budget starts againbudget_periodtext
How often the spend goes back to zero. Leave empty for never.One of: 1h (Every hour), 1d (Every day), 7d (Every 7 days), 30d (Every 30 days), 1mo (Every calendar month).
Works forlifetimetext
A new end date, counted from now.One of: 1h (1 hour), 1d (1 day), 7d (7 days), 30d (30 days), 90d (90 days), 365d (1 year).
Tokens a minutetpm_limitnumber
The most tokens the key may use a minute.At least 0.
Requests a minuterpm_limitnumber
The most requests the key may make a minute.At least 0.
Metadatametadataobject
Names and values to keep with the key, such as who it is for. Added to any it already has.

Outputs

keyobject
The key, as it is now
Example output
{
  "key": {
    "blocked": false,
    "budget_duration": "30d",
    "budget_reset_at": "2026-12-01T00:00:00Z",
    "created_at": "2026-11-06T12:00:00Z",
    "expires": "2027-11-06T12:00:00Z",
    "key_alias": "support-bot",
    "key_name": "sk-...Xy9Q",
    "max_budget": 50.0,
    "metadata": {
      "owner": "support"
    },
    "models": [
      "gpt-4o-mini"
    ],
    "rpm_limit": 60,
    "spend": 12.48,
    "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
    "token": "8a9b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f67890a1b2c3d4e5f6789",
    "tpm_limit": 100000,
    "user_id": "amelie@example.com"
  }
}

Update team

Change a team's name, models, budget or limits, or block it so none of its keys work. Fields left empty keep their value.

Inputs

Teamlitellm_team_idtextRequired
The team. Pick one, or give its ID from an earlier step.
Team nameteam_aliastext
A new name for the team.
Modelsmodelslist
The models the team may call. Leave empty for every model.
Budget (US dollars)max_budgetnumber
The most the team may spend; requests are refused once it is used up.At least 0.
Budget starts againbudget_periodtext
How often the spend goes back to zero. Leave empty for never.One of: 1h (Every hour), 1d (Every day), 7d (Every 7 days), 30d (Every 30 days), 1mo (Every calendar month).
Tokens a minutetpm_limitnumber
The most tokens the team may use a minute.At least 0.
Requests a minuterpm_limitnumber
The most requests the team may make a minute.At least 0.
Blockedblockedtrue/false
On: every key of the team stops working. Off: they work again.
Metadatametadataobject
Names and values to keep with the team, such as who it is for. Added to any it already has.

Outputs

keyslist
The team's keys
teamobject
The team
Example output
{
  "keys": [],
  "team": {
    "blocked": false,
    "budget_duration": "1mo",
    "budget_reset_at": "2026-12-01T00:00:00Z",
    "created_at": "2026-10-01T09:00:00Z",
    "max_budget": 200.0,
    "members_with_roles": [
      {
        "role": "admin",
        "user_email": "amelie@example.com",
        "user_id": "amelie@example.com"
      }
    ],
    "metadata": {},
    "models": [
      "gpt-4o-mini",
      "claude-sonnet"
    ],
    "rpm_limit": 120,
    "spend": 31.2,
    "team_alias": "Support",
    "team_id": "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab",
    "tpm_limit": 200000
  }
}

Update user

Change a user's email, name, role, models or budget. Fields left empty keep their value.

Inputs

Userlitellm_user_idtextRequired
The user. Pick one, or give their ID from an earlier step.
Emailuser_emailtext
A new email address.
Nameuser_aliastext
A new name.
Roleuser_roletext
What they may do on the proxy.One of: internal_user (Internal user (can create and use their own keys)), internal_user_viewer (Internal user, view only), proxy_admin (Admin (can do everything)), proxy_admin_viewer (Admin, view only).
Modelsmodelslist
The models they may call. Leave empty for every model.
Budget (US dollars)max_budgetnumber
The most they may spend; requests are refused once it is used up.At least 0.
Budget starts againbudget_periodtext
How often the spend goes back to zero. Leave empty for never.One of: 1h (Every hour), 1d (Every day), 7d (Every 7 days), 30d (Every 30 days), 1mo (Every calendar month).
Metadatametadataobject
Names and values to keep with the user, such as who it is for. Added to any it already has.

Outputs

userobject
The user, as they are now
Example output
{
  "user": {
    "budget_duration": "30d",
    "created_at": "2026-10-01T09:00:00Z",
    "max_budget": 20.0,
    "metadata": {},
    "models": [],
    "spend": 4.1,
    "teams": [
      "4f1d2c3b-aaaa-bbbb-cccc-1234567890ab"
    ],
    "user_alias": "Amelie",
    "user_email": "amelie@example.com",
    "user_id": "amelie@example.com",
    "user_role": "internal_user"
  }
}

On this page