litellm/docs/my-website/docs/proxy/users.md

import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem';

💰 Budgets, Rate Limits

Requirements:

• Need to a postgres database (e.g. Supabase, Neon, etc)

Set Budgets

You can set budgets at 3 levels:

• For the proxy
• For a user
• For a 'user' passed to /chat/completions, /embeddings etc
• For a key
• For a key (model specific budgets)

Apply a budget across all calls on the proxy

Step 1. Modify config.yaml

general_settings:
  master_key: sk-1234

litellm_settings:
  # other litellm settings
  max_budget: 0 # (float) sets max budget as $0 USD
  budget_duration: 30d # (str) frequency of reset - You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").

Step 2. Start proxy

litellm /path/to/config.yaml

Step 3. Send test call

curl --location 'http://0.0.0.0:4000/chat/completions' \
    --header 'Autherization: Bearer sk-1234' \
    --header 'Content-Type: application/json' \
    --data '{
    "model": "gpt-3.5-turbo",
    "messages": [
        {
        "role": "user",
        "content": "what llm are you"
        }
    ],
}'

Apply a budget across multiple keys.

LiteLLM exposes a /user/new endpoint to create budgets for this.

You can:

• Add budgets to users Jump
• Add budget durations, to reset spend Jump

By default the max_budget is set to null and is not checked for keys

Add budgets to users

curl --location 'http://localhost:4000/user/new' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data-raw '{"models": ["azure-models"], "max_budget": 0, "user_id": "krrish3@berri.ai"}' 

See Swagger

Sample Response

{
    "key": "sk-YF2OxDbrgd1y2KgwxmEA2w",
    "expires": "2023-12-22T09:53:13.861000Z",
    "user_id": "krrish3@berri.ai",
    "max_budget": 0.0
}

Add budget duration to users

budget_duration: Budget is reset at the end of specified duration. If not set, budget is never reset. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").

curl 'http://0.0.0.0:4000/user/new' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data-raw '{
  "team_id": "core-infra", # [OPTIONAL]
  "max_budget": 10,
  "budget_duration": 10s,
}'

Create new keys for existing user

Now you can just call /key/generate with that user_id (i.e. krrish3@berri.ai) and:

• Budget Check: krrish3@berri.ai's budget (i.e. $10) will be checked for this key
• Spend Tracking: spend for this key will update krrish3@berri.ai's spend as well

curl --location 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data '{"models": ["azure-models"], "user_id": "krrish3@berri.ai"}'

You can: - Add budgets to Teams

Add budgets to users

curl --location 'http://localhost:4000/team/new' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data-raw '{
  "team_alias": "my-new-team_4",
  "members_with_roles": [{"role": "admin", "user_id": "5c4a0aa3-a1e1-43dc-bd87-3c2da8382a3a"}],
  "rpm_limit": 99
}' 

See Swagger

Sample Response

{
    "team_alias": "my-new-team_4",
    "team_id": "13e83b19-f851-43fe-8e93-f96e21033100",
    "admins": [],
    "members": [],
    "members_with_roles": [
        {
            "role": "admin",
            "user_id": "5c4a0aa3-a1e1-43dc-bd87-3c2da8382a3a"
        }
    ],
    "metadata": {},
    "tpm_limit": null,
    "rpm_limit": 99,
    "max_budget": null,
    "models": [],
    "spend": 0.0,
    "max_parallel_requests": null,
    "budget_duration": null,
    "budget_reset_at": null
}

Use this to budget user passed to /chat/completions, without needing to create a key for every user

Step 1. Modify config.yaml Define litellm.max_user_budget

general_settings:
  master_key: sk-1234

litellm_settings:
  max_budget: 10      # global budget for proxy 
  max_user_budget: 0.0001 # budget for 'user' passed to /chat/completions

2. Make a /chat/completions call, pass 'user' - First call Works

curl --location 'http://0.0.0.0:4000/chat/completions' \
        --header 'Content-Type: application/json' \
        --header 'Authorization: Bearer sk-zi5onDRdHGD24v0Zdn7VBA' \
        --data ' {
        "model": "azure-gpt-3.5",
        "user": "ishaan3",
        "messages": [
            {
            "role": "user",
            "content": "what time is it"
            }
        ]
        }'

3. Make a /chat/completions call, pass 'user' - Call Fails, since 'ishaan3' over budget

curl --location 'http://0.0.0.0:4000/chat/completions' \
        --header 'Content-Type: application/json' \
        --header 'Authorization: Bearer sk-zi5onDRdHGD24v0Zdn7VBA' \
        --data ' {
        "model": "azure-gpt-3.5",
        "user": "ishaan3",
        "messages": [
            {
            "role": "user",
            "content": "what time is it"
            }
        ]
        }'

Error

{"error":{"message":"Authentication Error, ExceededBudget: User ishaan3 has exceeded their budget. Current spend: 0.0008869999999999999; Max Budget: 0.0001","type":"auth_error","param":"None","code":401}}%                

Apply a budget on a key.

You can:

• Add budgets to keys Jump
• Add budget durations, to reset spend Jump

Expected Behaviour

• Costs Per key get auto-populated in LiteLLM_VerificationToken Table
• After the key crosses it's max_budget, requests fail
• If duration set, spend is reset at the end of the duration

By default the max_budget is set to null and is not checked for keys

Add budgets to keys

curl 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data-raw '{
  "team_id": "core-infra", # [OPTIONAL]
  "max_budget": 10,
}'

Example Request to /chat/completions when key has crossed budget

curl --location 'http://0.0.0.0:4000/chat/completions' \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <generated-key>' \
  --data ' {
  "model": "azure-gpt-3.5",
  "user": "e09b4da8-ed80-4b05-ac93-e16d9eb56fca",
  "messages": [
      {
      "role": "user",
      "content": "respond in 50 lines"
      }
  ],
}'

Expected Response from /chat/completions when key has crossed budget

{
  "detail":"Authentication Error, ExceededTokenBudget: Current spend for token: 7.2e-05; Max Budget for Token: 2e-07"
}   

Add budget duration to keys

budget_duration: Budget is reset at the end of specified duration. If not set, budget is never reset. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").

curl 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data-raw '{
  "team_id": "core-infra", # [OPTIONAL]
  "max_budget": 10,
  "budget_duration": 10s,
}'

Apply model specific budgets on a key.

Expected Behaviour

• model_spend gets auto-populated in LiteLLM_VerificationToken Table
• After the key crosses the budget set for the model in model_max_budget, calls fail

By default the model_max_budget is set to {} and is not checked for keys

:::info

• LiteLLM will track the cost/budgets for the model passed to LLM endpoints (/chat/completions, /embeddings)

:::

Add model specific budgets to keys

curl 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data-raw '{
  model_max_budget={"gpt4": 0.5, "gpt-5": 0.01}
}'

Set Rate Limits

You can set:

• tpm limits (tokens per minute)
• rpm limits (requests per minute)
• max parallel requests

Use /user/new, to persist rate limits across multiple keys.

curl --location 'http://0.0.0.0:4000/user/new' \
--header 'Authorization: Bearer sk-1234' \
--header 'Content-Type: application/json' \
--data '{"user_id": "krrish@berri.ai", "max_parallel_requests": 10, "tpm_limit": 20, "rpm_limit": 4}' 

See Swagger

Expected Response

{
    "key": "sk-sA7VDkyhlQ7m8Gt77Mbt3Q",
    "expires": "2024-01-19T01:21:12.816168",
    "user_id": "krrish@berri.ai",
}

Use /key/generate, if you want them for just that key.

curl --location 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer sk-1234' \
--header 'Content-Type: application/json' \
--data '{"max_parallel_requests": 10, "tpm_limit": 20, "rpm_limit": 4}' 

Expected Response

{
    "key": "sk-ulGNRXWtv7M0lFnnsQk0wQ",
    "expires": "2024-01-18T20:48:44.297973",
    "user_id": "78c2c8fc-c233-43b9-b0c3-eb931da27b84"  // 👈 auto-generated
}

Grant Access to new model

Use model access groups to give users access to select models, and add new ones to it over time (e.g. mistral, llama-2, etc.).

Difference between doing this with /key/generate vs. /user/new? If you do it on /user/new it'll persist across multiple keys generated for that user.

Step 1. Assign model, access group in config.yaml

model_list:
  - model_name: text-embedding-ada-002
    litellm_params:
      model: azure/azure-embedding-model
      api_base: "os.environ/AZURE_API_BASE"
      api_key: "os.environ/AZURE_API_KEY"
      api_version: "2023-07-01-preview"
    model_info:
      access_groups: ["beta-models"] # 👈 Model Access Group

Step 2. Create key with access group

curl --location 'http://localhost:4000/user/new' \
-H 'Authorization: Bearer <your-master-key>' \
-H 'Content-Type: application/json' \
-d '{"models": ["beta-models"], # 👈 Model Access Group
			"max_budget": 0}'

Create new keys for existing user

Just include user_id in the /key/generate request.

curl --location 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data '{"models": ["azure-models"], "user_id": "krrish@berri.ai"}'