mirror of
https://github.com/tiennm99/litellm.git
synced 2026-08-18 08:25:10 +00:00
spend tracking details
This commit is contained in:
mubashir1osmani
@@ -357,308 +357,13 @@ curl -X GET "http://0.0.0.0:4000/spend/tags" \
|
||||
"total_spend": 0.000224
|
||||
}
|
||||
]
|
||||
|
||||
```
|
||||
|
||||
:::tip
|
||||
For comprehensive spend tracking features including budgets, alerts, and detailed analytics, check out [Spend Tracking](https://docs.litellm.ai/docs/proxy/cost_tracking).
|
||||
|
||||
### Tracking Spend with custom metadata
|
||||
:::
|
||||
|
||||
Requirements:
|
||||
|
||||
- Virtual Keys & a database should be set up, see [virtual keys](https://docs.litellm.ai/docs/proxy/virtual_keys)
|
||||
|
||||
#### Usage - /chat/completions requests with special spend logs metadata
|
||||
|
||||
|
||||
<Tabs>
|
||||
<TabItem value="key" label="Set on Key">
|
||||
|
||||
```bash
|
||||
curl -L -X POST 'http://0.0.0.0:4000/key/generate' \
|
||||
-H 'Authorization: Bearer sk-1234' \
|
||||
-H 'Content-Type: application/json' \
|
||||
-d '{
|
||||
"metadata": {
|
||||
"spend_logs_metadata": {
|
||||
"hello": "world"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
'
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="team" label="Set on Team">
|
||||
|
||||
```bash
|
||||
curl -L -X POST 'http://0.0.0.0:4000/team/new' \
|
||||
-H 'Authorization: Bearer sk-1234' \
|
||||
-H 'Content-Type: application/json' \
|
||||
-d '{
|
||||
"metadata": {
|
||||
"spend_logs_metadata": {
|
||||
"hello": "world"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
'
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
|
||||
<TabItem value="openai" label="OpenAI Python v1.0.0+">
|
||||
|
||||
Set `extra_body={"metadata": { }}` to `metadata` you want to pass
|
||||
|
||||
```python
|
||||
import openai
|
||||
client = openai.OpenAI(
|
||||
api_key="anything",
|
||||
base_url="http://0.0.0.0:4000"
|
||||
)
|
||||
|
||||
# request sent to model set on litellm proxy, `litellm --model`
|
||||
response = client.chat.completions.create(
|
||||
model="gpt-3.5-turbo",
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "this is a test request, write a short poem"
|
||||
}
|
||||
],
|
||||
extra_body={
|
||||
"metadata": {
|
||||
"spend_logs_metadata": {
|
||||
"hello": "world"
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
print(response)
|
||||
```
|
||||
|
||||
**Using Headers:**
|
||||
|
||||
```python
|
||||
import openai
|
||||
client = openai.OpenAI(
|
||||
api_key="sk-1234",
|
||||
base_url="http://0.0.0.0:4000"
|
||||
)
|
||||
|
||||
# Pass spend logs metadata via headers
|
||||
response = client.chat.completions.create(
|
||||
model="gpt-3.5-turbo",
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "this is a test request, write a short poem"
|
||||
}
|
||||
],
|
||||
extra_headers={
|
||||
"x-litellm-spend-logs-metadata": '{"user_id": "12345", "project_id": "proj_abc", "request_type": "chat_completion"}'
|
||||
}
|
||||
)
|
||||
|
||||
print(response)
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
|
||||
|
||||
<TabItem value="openai js" label="OpenAI JS">
|
||||
|
||||
```js
|
||||
const openai = require('openai');
|
||||
|
||||
async function runOpenAI() {
|
||||
const client = new openai.OpenAI({
|
||||
apiKey: 'sk-1234',
|
||||
baseURL: 'http://0.0.0.0:4000'
|
||||
});
|
||||
|
||||
try {
|
||||
const response = await client.chat.completions.create({
|
||||
model: 'gpt-3.5-turbo',
|
||||
messages: [
|
||||
{
|
||||
role: 'user',
|
||||
content: "this is a test request, write a short poem"
|
||||
},
|
||||
],
|
||||
metadata: {
|
||||
spend_logs_metadata: { // 👈 Key Change
|
||||
hello: "world"
|
||||
}
|
||||
}
|
||||
});
|
||||
console.log(response);
|
||||
} catch (error) {
|
||||
console.log("got this exception from server");
|
||||
console.error(error);
|
||||
}
|
||||
}
|
||||
|
||||
// Call the asynchronous function
|
||||
runOpenAI();
|
||||
```
|
||||
|
||||
**Using Headers:**
|
||||
|
||||
```js
|
||||
const openai = require('openai');
|
||||
|
||||
async function runOpenAI() {
|
||||
const client = new openai.OpenAI({
|
||||
apiKey: 'sk-1234',
|
||||
baseURL: 'http://0.0.0.0:4000'
|
||||
});
|
||||
|
||||
try {
|
||||
const response = await client.chat.completions.create({
|
||||
model: 'gpt-3.5-turbo',
|
||||
messages: [
|
||||
{
|
||||
role: 'user',
|
||||
content: "this is a test request, write a short poem"
|
||||
},
|
||||
]
|
||||
}, {
|
||||
headers: {
|
||||
'x-litellm-spend-logs-metadata': '{"user_id": "12345", "project_id": "proj_abc", "request_type": "chat_completion"}'
|
||||
}
|
||||
});
|
||||
console.log(response);
|
||||
} catch (error) {
|
||||
console.log("got this exception from server");
|
||||
console.error(error);
|
||||
}
|
||||
}
|
||||
|
||||
// Call the asynchronous function
|
||||
runOpenAI();
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
|
||||
<TabItem value="Curl" label="Curl Request">
|
||||
|
||||
Pass `metadata` as part of the request body
|
||||
|
||||
```shell
|
||||
curl --location 'http://0.0.0.0:4000/chat/completions' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"model": "gpt-3.5-turbo",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "what llm are you"
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"spend_logs_metadata": {
|
||||
"hello": "world"
|
||||
}
|
||||
}
|
||||
}'
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
|
||||
<TabItem value="headers" label="Using Headers">
|
||||
|
||||
Pass `x-litellm-spend-logs-metadata` as a request header with JSON string
|
||||
|
||||
```shell
|
||||
curl --location 'http://0.0.0.0:4000/chat/completions' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--header 'Authorization: Bearer sk-1234' \
|
||||
--header 'x-litellm-spend-logs-metadata: {"user_id": "12345", "project_id": "proj_abc", "request_type": "chat_completion"}' \
|
||||
--data '{
|
||||
"model": "gpt-3.5-turbo",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "what llm are you"
|
||||
}
|
||||
]
|
||||
}'
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="langchain" label="Langchain">
|
||||
|
||||
```python
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
from langchain.prompts.chat import (
|
||||
ChatPromptTemplate,
|
||||
HumanMessagePromptTemplate,
|
||||
SystemMessagePromptTemplate,
|
||||
)
|
||||
from langchain.schema import HumanMessage, SystemMessage
|
||||
|
||||
chat = ChatOpenAI(
|
||||
openai_api_base="http://0.0.0.0:4000",
|
||||
model = "gpt-3.5-turbo",
|
||||
temperature=0.1,
|
||||
extra_body={
|
||||
"metadata": {
|
||||
"spend_logs_metadata": {
|
||||
"hello": "world"
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
messages = [
|
||||
SystemMessage(
|
||||
content="You are a helpful assistant that im using to make a test request to."
|
||||
),
|
||||
HumanMessage(
|
||||
content="test from litellm. tell me why it's amazing in 1 sentence"
|
||||
),
|
||||
]
|
||||
response = chat(messages)
|
||||
|
||||
print(response)
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
|
||||
#### Viewing Spend w/ custom metadata
|
||||
|
||||
#### `/spend/logs` Request Format
|
||||
|
||||
```bash
|
||||
curl -X GET "http://0.0.0.0:4000/spend/logs?request_id=<your-call-id" \ # e.g.: chatcmpl-9ZKMURhVYSi9D6r6PJ9vLcayIK0Vm
|
||||
-H "Authorization: Bearer sk-1234"
|
||||
```
|
||||
|
||||
#### `/spend/logs` Response Format
|
||||
```bash
|
||||
[
|
||||
{
|
||||
"request_id": "chatcmpl-9ZKMURhVYSi9D6r6PJ9vLcayIK0Vm",
|
||||
"call_type": "acompletion",
|
||||
"metadata": {
|
||||
"user_api_key": "88dc28d0f030c55ed4ab77ed8faf098196cb1c05df778539800c9f1243fe6b4b",
|
||||
"user_api_key_alias": null,
|
||||
"spend_logs_metadata": { # 👈 LOGGED CUSTOM METADATA
|
||||
"hello": "world"
|
||||
},
|
||||
"user_api_key_team_id": null,
|
||||
"user_api_key_user_id": "116544810872468347480",
|
||||
"user_api_key_team_alias": null
|
||||
},
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
## Guardrails - Secret Detection/Redaction
|
||||
❓ Use this to REDACT API Keys, Secrets sent in requests to an LLM.
|
||||
|
||||
Reference in New Issue
Block a user