scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 108

docs(proxy): replace gpt-3.5-turbo with gpt-4o in example configs

Browse source 
Update model name strings across proxy documentation pages for consistency
with current OpenAI model guidance.

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
This commit is contained in:
Cursor Agent 2026-03-21 17:59:31 +00:00
parent bb741e73fc
commit 831bc1b6fd
No known key found for this signature in database
15 changed files with 77 additions and 77 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/my-website/docs/proxy/arize_phoenix_prompts.md
View file

@ -42,7 +42,7 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"prompt_id": "simple_prompt",
"prompt_variables": {
"question": "Explain quantum computing"

4
docs/my-website/docs/proxy/cli.md
View file

@ -166,7 +166,7 @@ This page documents all command-line interface (CLI) arguments available for the
- The model name to pass to LiteLLM.
- **Usage:**
```shell
litellm --model gpt-3.5-turbo
litellm --model gpt-4o
```
### --alias
@ -214,7 +214,7 @@ This page documents all command-line interface (CLI) arguments available for the
- Save the model-specific config.
- **Usage:**
```shell
litellm --model gpt-3.5-turbo --save
litellm --model gpt-4o --save
```
## Model Parameters

8
docs/my-website/docs/proxy/custom_auth.md
View file

@ -182,7 +182,7 @@ async def user_api_key_auth(request: Request, api_key: str) -> UserAPIKeyAuth:
soft_budget=800.0,
tpm_limit=10000,
rpm_limit=100,
models=["gpt-4", "claude-3-sonnet", "gpt-3.5-turbo"],
models=["gpt-4", "claude-3-sonnet", "gpt-4o"],
allowed_routes=["/chat/completions", "/embeddings"],
expires=datetime.now() + timedelta(days=30),
metadata={"department": "engineering", "cost_center": "ai_ops"}
@ -198,7 +198,7 @@ async def user_api_key_auth(request: Request, api_key: str) -> UserAPIKeyAuth:
max_budget=100.0,
tpm_limit=1000,
rpm_limit=20,
models=["gpt-3.5-turbo", "claude-3-haiku"],
models=["gpt-4o", "claude-3-haiku"],
team_member_tpm_limit=500, # Limit within team
end_user_tpm_limit=100, # Per end-user limit
metadata={"project": "chatbot_v2"}
@ -218,7 +218,7 @@ e.g. if they're both in the same dir - `./config.yaml` and `./custom_auth.py`, t
model_list:
- model_name: "openai-model"
litellm_params:
model: "gpt-3.5-turbo"
model: "gpt-4o"
litellm_settings:
drop_params: True
@ -286,7 +286,7 @@ Key change set `mode: auto`. This will check both litellm api key auth + custom
model_list:
- model_name: "openai-model"
litellm_params:
model: "gpt-3.5-turbo"
model: "gpt-4o"
api_key: os.environ/OPENAI_API_KEY
general_settings:

6
docs/my-website/docs/proxy/customer_routing.md
View file

@ -37,13 +37,13 @@ Supported regions are 'eu' and 'us'.
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/gpt-35-turbo # 👈 EU azure model
api_base: https://my-endpoint-europe-berri-992.openai.azure.com/
api_key: os.environ/AZURE_EUROPE_API_KEY
region_name: "eu"
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/chatgpt-v-2
api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@ -70,7 +70,7 @@ curl -X POST --location 'http://localhost:4000/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer sk-1234' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",

4
docs/my-website/docs/proxy/customers.md
View file

@ -391,7 +391,7 @@ curl -X POST 'http://localhost:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello"}],
"user": "my-customer-id"
}'
@ -508,7 +508,7 @@ client = OpenAI(
)
completion = client.chat.completions.create(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}

10
docs/my-website/docs/proxy/dynamic_rate_limit.md
View file

@ -15,7 +15,7 @@ Dynamically allocate TPM/RPM quota to api keys, based on active keys in that min
model_list:
- model_name: my-fake-model
litellm_params:
model: gpt-3.5-turbo
model: gpt-4o
api_key: my-fake-key
mock_response: hello-world
tpm: 60
@ -130,9 +130,9 @@ Priority reservation allocates a percentage of your model's total TPM/RPM to spe
```yaml showLineNumbers title="config.yaml"
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: "gpt-3.5-turbo"
model: "gpt-4o"
api_key: os.environ/OPENAI_API_KEY
rpm: 10 # Total model capacity
@ -262,7 +262,7 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-prod-key' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello from prod"}]
}'
```
@ -273,7 +273,7 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-dev-key' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello from dev"}]
}'
```

2
docs/my-website/docs/proxy/endpoint_activity.md
View file

@ -32,7 +32,7 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \ # 👈 ENDPOINT AUTOMATICA
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer sk-1234' \ # 👈 YOUR PROXY KEY
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",

16
docs/my-website/docs/proxy/enterprise.md
View file

@ -103,7 +103,7 @@ curl --location 'http://localhost:4000/chat/completions' \
--header 'Authorization: Bearer sk-5fmYeaUEbAMpwBNT-QpxyA' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -128,7 +128,7 @@ curl --location 'http://localhost:4000/chat/completions' \
--header 'Authorization: Bearer sk-5fmYeaUEbAMpwBNT-QpxyA' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"user": "gm",
"messages": [
{
@ -155,7 +155,7 @@ curl --location 'http://localhost:4000/chat/completions' \
--header 'Authorization: Bearer sk-5fmYeaUEbAMpwBNT-QpxyA' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"user": "gm",
"messages": [
{
@ -170,7 +170,7 @@ curl --location 'http://localhost:4000/chat/completions' \
Expected Response
```shell
{"id":"chatcmpl-9XALnHqkCBMBKrOx7Abg0hURHqYtY","choices":[{"finish_reason":"stop","index":0,"message":{"content":"Hello! How can I assist you today?","role":"assistant"}}],"created":1717691639,"model":"gpt-3.5-turbo-0125","object":"chat.completion","system_fingerprint":null,"usage":{"completion_tokens":9,"prompt_tokens":8,"total_tokens":17}}%
{"id":"chatcmpl-9XALnHqkCBMBKrOx7Abg0hURHqYtY","choices":[{"finish_reason":"stop","index":0,"message":{"content":"Hello! How can I assist you today?","role":"assistant"}}],"created":1717691639,"model":"gpt-4o-0125","object":"chat.completion","system_fingerprint":null,"usage":{"completion_tokens":9,"prompt_tokens":8,"total_tokens":17}}%
```
</TabItem>
@ -481,7 +481,7 @@ client = openai.OpenAI(
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(
model="gpt-3.5-turbo",
model="gpt-4o",
messages = [
{
"role": "user",
@ -668,7 +668,7 @@ client = openai.OpenAI(
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(
model="gpt-3.5-turbo",
model="gpt-4o",
messages = [
{
"role": "user",
@ -688,7 +688,7 @@ print(response)
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -748,7 +748,7 @@ litellm_settings:
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",

30
docs/my-website/docs/proxy/fallback_management.md
View file

@ -20,7 +20,7 @@ Create or update fallbacks for a specific model.
**Request Body:**
```json
{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"fallback_models": ["gpt-4", "claude-3-haiku"],
"fallback_type": "general"
}
@ -37,7 +37,7 @@ Create or update fallbacks for a specific model.
**Response:**
```json
{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"fallback_models": ["gpt-4", "claude-3-haiku"],
"fallback_type": "general",
"message": "Fallback configuration created successfully"
@ -50,7 +50,7 @@ curl -X POST "http://localhost:4000/fallback" \
-H "Authorization: Bearer sk-1234" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"fallback_models": ["gpt-4", "claude-3-haiku"],
"fallback_type": "general"
}'
@ -67,7 +67,7 @@ response = requests.post(
"Content-Type": "application/json"
},
json={
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"fallback_models": ["gpt-4", "claude-3-haiku"],
"fallback_type": "general"
}
@ -87,7 +87,7 @@ Get fallback configuration for a specific model.
**Response:**
```json
{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"fallback_models": ["gpt-4", "claude-3-haiku"],
"fallback_type": "general"
}
@ -95,7 +95,7 @@ Get fallback configuration for a specific model.
**Example using cURL:**
```bash
curl -X GET "http://localhost:4000/fallback/gpt-3.5-turbo?fallback_type=general" \
curl -X GET "http://localhost:4000/fallback/gpt-4o?fallback_type=general" \
-H "Authorization: Bearer sk-1234"
```
@ -104,7 +104,7 @@ curl -X GET "http://localhost:4000/fallback/gpt-3.5-turbo?fallback_type=general"
import requests
response = requests.get(
"http://localhost:4000/fallback/gpt-3.5-turbo",
"http://localhost:4000/fallback/gpt-4o",
headers={"Authorization": "Bearer sk-1234"},
params={"fallback_type": "general"}
)
@ -123,7 +123,7 @@ Delete fallback configuration for a specific model.
**Response:**
```json
{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"fallback_type": "general",
"message": "Fallback configuration deleted successfully"
}
@ -131,7 +131,7 @@ Delete fallback configuration for a specific model.
**Example using cURL:**
```bash
curl -X DELETE "http://localhost:4000/fallback/gpt-3.5-turbo?fallback_type=general" \
curl -X DELETE "http://localhost:4000/fallback/gpt-4o?fallback_type=general" \
-H "Authorization: Bearer sk-1234"
```
@ -140,7 +140,7 @@ curl -X DELETE "http://localhost:4000/fallback/gpt-3.5-turbo?fallback_type=gener
import requests
response = requests.delete(
"http://localhost:4000/fallback/gpt-3.5-turbo",
"http://localhost:4000/fallback/gpt-4o",
headers={"Authorization": "Bearer sk-1234"},
params={"fallback_type": "general"}
)
@ -155,7 +155,7 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -186,7 +186,7 @@ The endpoints perform the following validations:
{
"detail": {
"error": "Invalid fallback models: ['non-existent-model']",
"available_models": ["gpt-3.5-turbo", "gpt-4", "claude-3-haiku"]
"available_models": ["gpt-4o", "gpt-4", "claude-3-haiku"]
}
}
```
@ -195,7 +195,7 @@ The endpoints perform the following validations:
```json
{
"detail": {
"error": "Model 'gpt-3.5-turbo' not found in router",
"error": "Model 'gpt-4o' not found in router",
"available_models": ["gpt-4", "claude-3-haiku"]
}
}
@ -219,7 +219,7 @@ Used for any type of error that occurs during model invocation. This is the most
```json
{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"fallback_models": ["gpt-4", "claude-3-haiku"],
"fallback_type": "general"
}
@ -232,7 +232,7 @@ Specifically triggered when a context window exceeded error occurs.
```json
{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"fallback_models": ["gpt-4-32k", "claude-3-opus"],
"fallback_type": "context_window"
}

34
docs/my-website/docs/proxy/load_balancing.md
View file

@ -37,22 +37,22 @@ Use the `order` parameter to prioritize specific deployments. [See Deployment Or
## Quick Start - Load Balancing
#### Step 1 - Set deployments on config
**Example config below**. Here requests with `model=gpt-3.5-turbo` will be routed across multiple instances of `azure/gpt-3.5-turbo`
**Example config below**. Here requests with `model=gpt-4o` will be routed across multiple instances of `azure/gpt-4o`
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/<your-deployment-name>
api_base: <your-azure-endpoint>
api_key: <your-azure-api-key>
rpm: 6 # Rate limit for this deployment: in requests per minute (rpm)
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/gpt-turbo-small-ca
api_base: https://my-endpoint-canada-berri992.openai.azure.com/
api_key: <your-azure-api-key>
rpm: 6
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/gpt-turbo-large
api_base: https://openai-france-1234.openai.azure.com/
@ -61,7 +61,7 @@ model_list:
router_settings:
routing_strategy: simple-shuffle # Literal["simple-shuffle", "least-busy", "usage-based-routing","latency-based-routing"], default="simple-shuffle"
model_group_alias: {"gpt-4": "gpt-3.5-turbo"} # all requests with `gpt-4` will be routed to models with `gpt-3.5-turbo`
model_group_alias: {"gpt-4": "gpt-4o"} # all requests with `gpt-4` will be routed to models with `gpt-4o`
num_retries: 2
timeout: 30 # 30 seconds
redis_host: <your redis host> # set this when using multiple litellm proxy deployments, load balancing state stored in redis
@ -142,9 +142,9 @@ $ litellm --config /path/to/config.yaml
### Test - Simple Call
Here requests with model=gpt-3.5-turbo will be routed across multiple instances of azure/gpt-3.5-turbo
Here requests with model=gpt-4o will be routed across multiple instances of azure/gpt-4o
👉 Key Change: `model="gpt-3.5-turbo"`
👉 Key Change: `model="gpt-4o"`
**Check the `model_id` in Response Headers to make sure the requests are being load balanced**
@ -160,7 +160,7 @@ client = openai.OpenAI(
)
response = client.chat.completions.create(
model="gpt-3.5-turbo",
model="gpt-4o",
messages = [
{
"role": "user",
@ -179,7 +179,7 @@ print(response)
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -202,7 +202,7 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{"role": "user", "content": "Hi there!"}
],
@ -221,13 +221,13 @@ Example config
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/<your-deployment-name>
api_base: <your-azure-endpoint>
api_key: <your-azure-api-key>
rpm: 6 # Rate limit for this deployment: in requests per minute (rpm)
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/gpt-turbo-small-ca
api_base: https://my-endpoint-canada-berri992.openai.azure.com/
@ -248,7 +248,7 @@ Expose an 'alias' for a 'model_name' on the proxy server.
```
model_group_alias: {
"gpt-4": "gpt-3.5-turbo"
"gpt-4": "gpt-4o"
}
```
@ -264,14 +264,14 @@ Example config with `router_settings`
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/<your-deployment-name>
api_base: <your-azure-endpoint>
api_key: <your-azure-api-key>
router_settings:
model_group_alias: {"gpt-4": "gpt-3.5-turbo"} # all requests with `gpt-4` will be routed to models
model_group_alias: {"gpt-4": "gpt-4o"} # all requests with `gpt-4` will be routed to models
```
### Hide Alias Models
@ -284,7 +284,7 @@ Use this if you want to set-up aliases for:
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/<your-deployment-name>
api_base: <your-azure-endpoint>
@ -293,7 +293,7 @@ model_list:
router_settings:
model_group_alias:
"GPT-3.5-turbo": # alias
model: "gpt-3.5-turbo" # Actual model name in 'model_list'
model: "gpt-4o" # Actual model name in 'model_list'
hidden: true # Exclude from `/v1/models`, `/v1/model/info`, `/v1/model_group/info`
```

6
docs/my-website/docs/proxy/model_access.md
View file

@ -12,12 +12,12 @@ Set allowed models for a key using the `models` param
curl 'http://0.0.0.0:4000/key/generate' \
--header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \
--data-raw '{"models": ["gpt-3.5-turbo", "gpt-4"]}'
--data-raw '{"models": ["gpt-4o", "gpt-4"]}'
```
:::info
This key can only make requests to `models` that are `gpt-3.5-turbo` or `gpt-4`
This key can only make requests to `models` that are `gpt-4o` or `gpt-4`
:::
@ -195,7 +195,7 @@ When `include_metadata=true` is specified, the response includes fallback inform
"created": 1677610602,
"owned_by": "openai",
"fallbacks": {
"general": ["gpt-3.5-turbo", "claude-3-sonnet"],
"general": ["gpt-4o", "claude-3-sonnet"],
"context_window": ["gpt-4-turbo", "claude-3-opus"],
"content_policy": ["claude-3-haiku"]
}

2
docs/my-website/docs/proxy/oauth2.md
View file

@ -47,7 +47,7 @@ general_settings:
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",

16
docs/my-website/docs/proxy/prompt_management.md
View file

@ -368,7 +368,7 @@ os.environ["LANGFUSE_SECRET_KEY"] = "secret_key" # [OPTIONAL] set here or in `.c
litellm.set_verbose = True # see raw request to provider
resp = litellm.completion(
model="langfuse/gpt-3.5-turbo",
model="langfuse/gpt-4o",
prompt_id="test-chat-prompt",
prompt_variables={"user_message": "this is used"}, # [OPTIONAL]
messages=[{"role": "user", "content": "<IGNORED>"}],
@ -391,7 +391,7 @@ model_list:
api_key: os.environ/OPENAI_API_KEY
- model_name: openai-model
litellm_params:
model: openai/gpt-3.5-turbo
model: openai/gpt-4o
api_key: os.environ/OPENAI_API_KEY
```
@ -435,7 +435,7 @@ client = openai.OpenAI(
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(
model="gpt-3.5-turbo",
model="gpt-4o",
messages = [
{
"role": "user",
@ -465,7 +465,7 @@ print(response)
POST Request Sent from LiteLLM:
curl -X POST \
https://api.openai.com/v1/ \
-d '{'model': 'gpt-3.5-turbo', 'messages': <YOUR LANGFUSE PROMPT TEMPLATE>}'
-d '{'model': 'gpt-4o', 'messages': <YOUR LANGFUSE PROMPT TEMPLATE>}'
```
## How to set model
@ -479,7 +479,7 @@ You can do `langfuse/<litellm_model_name>`
```python
litellm.completion(
model="langfuse/gpt-3.5-turbo", # or `langfuse/anthropic/claude-3-5-sonnet`
model="langfuse/gpt-4o", # or `langfuse/anthropic/claude-3-5-sonnet`
...
)
```
@ -489,9 +489,9 @@ litellm.completion(
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: langfuse/gpt-3.5-turbo # OR langfuse/anthropic/claude-3-5-sonnet
model: langfuse/gpt-4o # OR langfuse/anthropic/claude-3-5-sonnet
prompt_id: <langfuse_prompt_id>
api_key: os.environ/OPENAI_API_KEY
```
@ -507,7 +507,7 @@ If the model is specified in the Langfuse config, it will be used.
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/chatgpt-v-2
api_key: os.environ/AZURE_API_KEY

8
docs/my-website/docs/proxy/reject_clientside_metadata_tags.md
View file

@ -30,7 +30,7 @@ curl -X POST http://localhost:4000/chat/completions \
-H "Authorization: Bearer sk-1234" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello"}],
"metadata": {
"tags": ["custom-tag"] # This will be rejected
@ -56,7 +56,7 @@ curl -X POST http://localhost:4000/chat/completions \
-H "Authorization: Bearer sk-1234" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello"}],
"metadata": {
"custom_field": "value" # Other metadata fields are allowed
@ -89,9 +89,9 @@ These tags will be automatically inherited by all requests made with that API ke
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: gpt-3.5-turbo
model: gpt-4o
api_key: os.environ/OPENAI_API_KEY
general_settings:

6
docs/my-website/docs/proxy/self_serve.md
View file

@ -361,7 +361,7 @@ litellm_settings:
default_team_params: # Default Params to apply when litellm auto creates a team from SSO IDP provider
max_budget: 100 # Optional[float], optional): $100 budget for the team
budget_duration: 30d # Optional[str], optional): 30 days budget_duration for the team
models: ["gpt-3.5-turbo"] # Optional[List[str]], optional): models to be used by the team
models: ["gpt-4o"] # Optional[List[str]], optional): models to be used by the team
```
@ -384,7 +384,7 @@ litellm_settings:
user_role: "internal_user" # one of "internal_user", "internal_user_viewer", "proxy_admin", "proxy_admin_viewer". New SSO users not in litellm will be created as this user
max_budget: 100 # Optional[float], optional): $100 budget for a new SSO sign in user
budget_duration: 30d # Optional[str], optional): 30 days budget_duration for a new SSO sign in user
models: ["gpt-3.5-turbo"] # Optional[List[str]], optional): models to be used by a new SSO sign in user
models: ["gpt-4o"] # Optional[List[str]], optional): models to be used by a new SSO sign in user
teams: # Optional[List[NewUserRequestTeam]], optional): teams to be used by the user
- team_id: "team_id_1" # Required[str]: team_id to be used by the user
max_budget_in_team: 100 # Optional[float], optional): $100 budget for the team. Defaults to None.
@ -393,7 +393,7 @@ litellm_settings:
default_team_params: # Default Params to apply when litellm auto creates a team from SSO IDP provider
max_budget: 100 # Optional[float], optional): $100 budget for the team
budget_duration: 30d # Optional[str], optional): 30 days budget_duration for the team
models: ["gpt-3.5-turbo"] # Optional[List[str]], optional): models to be used by the team
models: ["gpt-4o"] # Optional[List[str]], optional): models to be used by the team
upperbound_key_generate_params: # Upperbound for /key/generate requests when self-serve flow is on