phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs(billing.md): update billing tutorial to show how to bill internal teams

Browse source
This commit is contained in:
Krrish Dholakia 2024-05-16 17:49:01 -07:00
parent 2b7f4dac70
commit 28dd97e8e8
1 changed files with 14 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

28
docs/my-website/docs/proxy/billing.md
View file

@ -4,7 +4,7 @@ import TabItem from '@theme/TabItem';
# 💵 Billing # 💵 Billing
Bill users for their usage. Bill internal teams, external customers for their usage
**🚨 Requirements** **🚨 Requirements**
- [Setup Lago](https://docs.getlago.com/guide/self-hosted/docker#run-the-app), for usage-based billing. We recommend following [their Stripe tutorial](https://docs.getlago.com/templates/per-transaction/stripe#step-1-create-billable-metrics-for-transaction) - [Setup Lago](https://docs.getlago.com/guide/self-hosted/docker#run-the-app), for usage-based billing. We recommend following [their Stripe tutorial](https://docs.getlago.com/templates/per-transaction/stripe#step-1-create-billable-metrics-for-transaction)
@ -16,7 +16,7 @@ Steps:
## Quick Start ## Quick Start
Bill internal users for their usage Bill internal teams for their usage
### 1. Connect proxy to Lago ### 1. Connect proxy to Lago
@ -43,7 +43,7 @@ Add your Lago keys to the environment
export LAGO_API_BASE="http://localhost:3000" # self-host - https://docs.getlago.com/guide/self-hosted/docker#run-the-app export LAGO_API_BASE="http://localhost:3000" # self-host - https://docs.getlago.com/guide/self-hosted/docker#run-the-app
export LAGO_API_KEY="3e29d607-de54-49aa-a019-ecf585729070" # Get key - https://docs.getlago.com/guide/self-hosted/docker#find-your-api-key export LAGO_API_KEY="3e29d607-de54-49aa-a019-ecf585729070" # Get key - https://docs.getlago.com/guide/self-hosted/docker#find-your-api-key
export LAGO_API_EVENT_CODE="openai_tokens" # name of lago billing code export LAGO_API_EVENT_CODE="openai_tokens" # name of lago billing code
export LAGO_API_CHARGE_BY="user_id" # 👈 Charges 'user_id' attached to proxy key export LAGO_API_CHARGE_BY="team_id" # 👈 Charges 'team_id' attached to proxy key
``` ```
Start proxy Start proxy
@ -52,13 +52,13 @@ Start proxy
litellm --config /path/to/config.yaml litellm --config /path/to/config.yaml
``` ```
### 2. Create Key for Internal User ### 2. Create Key for Internal Team
```bash ```bash
curl 'http://0.0.0.0:4000/key/generate' \ curl 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer sk-1234' \ --header 'Authorization: Bearer sk-1234' \
--header 'Content-Type: application/json' \ --header 'Content-Type: application/json' \
--data-raw '{"user_id": "my-unique-id"}' # 👈 Internal User's ID --data-raw '{"team_id": "my-unique-id"}' # 👈 Internal Team's ID
``` ```
Response Object: Response Object:
@ -78,7 +78,7 @@ Response Object:
```bash ```bash
curl --location 'http://0.0.0.0:4000/chat/completions' \ curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \ --header 'Content-Type: application/json' \
--header 'Authorization: Bearer sk-tXL0wt5-lOOVK9sfY2UacA' \ # 👈 User's Key --header 'Authorization: Bearer sk-tXL0wt5-lOOVK9sfY2UacA' \ # 👈 Team's Key
--data ' { --data ' {
"model": "fake-openai-endpoint", "model": "fake-openai-endpoint",
"messages": [ "messages": [
@ -96,7 +96,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
```python ```python
import openai import openai
client = openai.OpenAI( client = openai.OpenAI(
api_key="sk-tXL0wt5-lOOVK9sfY2UacA", # 👈 User's Key api_key="sk-tXL0wt5-lOOVK9sfY2UacA", # 👈 Team's Key
base_url="http://0.0.0.0:4000" base_url="http://0.0.0.0:4000"
) )
@ -123,7 +123,7 @@ from langchain.prompts.chat import (
from langchain.schema import HumanMessage, SystemMessage from langchain.schema import HumanMessage, SystemMessage
import os import os
os.environ["OPENAI_API_KEY"] = "sk-tXL0wt5-lOOVK9sfY2UacA" # 👈 User's Key os.environ["OPENAI_API_KEY"] = "sk-tXL0wt5-lOOVK9sfY2UacA" # 👈 Team's Key
chat = ChatOpenAI( chat = ChatOpenAI(
openai_api_base="http://0.0.0.0:4000", openai_api_base="http://0.0.0.0:4000",
@ -171,7 +171,7 @@ This is what LiteLLM will log to Lagos
} }
``` ```
## Advanced - Bill Customers, Internal Teams ## Advanced - Bill Customers, Internal Users
For: For:
- Customers (id passed via 'user' param in /chat/completion call) = 'end_user_id' - Customers (id passed via 'user' param in /chat/completion call) = 'end_user_id'
@ -271,21 +271,21 @@ For:
</Tabs> </Tabs>
</TabItem> </TabItem>
<TabItem value="teams" label="Team Billing"> <TabItem value="users" label="Internal User Billing">
1. Set 'LAGO_API_CHARGE_BY' to 'team_id' 1. Set 'LAGO_API_CHARGE_BY' to 'user_id'
```bash ```bash
export LAGO_API_CHARGE_BY="team_id" export LAGO_API_CHARGE_BY="user_id"
``` ```
2. Create a key for that team 2. Create a key for that user
```bash ```bash
curl 'http://0.0.0.0:4000/key/generate' \ curl 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer <your-master-key>' \ --header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \ --header 'Content-Type: application/json' \
--data-raw '{"team_id": "my-unique-id"}' --data-raw '{"user_id": "my-unique-id"}' # 👈 Internal User's id
``` ```
Response Object: Response Object: