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 109

docs: replace gpt-3.5-turbo with gpt-4o in provider and guide examples

Browse source 
Update model strings across OpenRouter, Azure, caching, LangChain, Letta,
and related docs using StrReplace (replace_all) for consistency with gpt-4o.

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
This commit is contained in:
Cursor Agent 2026-03-21 18:03:31 +00:00
parent 2a2386071d
commit c4c2afc579
No known key found for this signature in database
14 changed files with 93 additions and 93 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/my-website/docs/adding_provider/adding_guardrail_support.md
View file

@ -321,7 +321,7 @@ curl -X POST 'http://localhost:4000/{my_endpoint}' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer your-api-key' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello"}],
"guardrails": ["test"]
}'

4
docs/my-website/docs/adding_provider/generic_prompt_management_api.md
View file

@ -131,9 +131,9 @@ Add to `config.yaml`:
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: openai/gpt-3.5-turbo
model: openai/gpt-4o
api_key: os.environ/OPENAI_API_KEY
prompts:

44
docs/my-website/docs/caching/all_caches.md
View file

@ -39,11 +39,11 @@ litellm.cache = Cache(type="redis", host=<host>, port=<port>, password=<password
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
@ -77,11 +77,11 @@ litellm.cache = RedisClusterCache(
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
@ -132,11 +132,11 @@ from litellm.caching.caching import Cache
litellm.cache = Cache(type="gcs", gcs_bucket_name="my-cache-bucket", gcs_path_service_account="/path/to/service_account.json")
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
@ -170,11 +170,11 @@ litellm.cache = Cache(type="s3", s3_bucket_name="cache-bucket-litellm", s3_regio
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
@ -201,11 +201,11 @@ litellm.cache = Cache(type="azure-blob", azure_account_url="https://example.blob
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
)
@ -244,7 +244,7 @@ litellm.cache = Cache(
redis_semantic_cache_embedding_model="text-embedding-ada-002", # this model is passed to litellm.embedding(), any litellm.embedding() model is supported here
)
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{
"role": "user",
@ -258,7 +258,7 @@ print(f"response1: {response1}")
random_number = random.randint(1, 100000)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{
"role": "user",
@ -301,7 +301,7 @@ litellm.cache = Cache(
)
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{
"role": "user",
@ -315,7 +315,7 @@ print(f"response1: {response1}")
random_number = random.randint(1, 100000)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{
"role": "user",
@ -343,12 +343,12 @@ litellm.cache = Cache()
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
caching=True
)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
caching=True
)
@ -379,12 +379,12 @@ litellm.cache = Cache(type="disk")
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
caching=True
)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
caching=True
)
@ -416,7 +416,7 @@ Example usage `no-cache` - When `True`, Will not return a cached response
```python
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{
"role": "user",
@ -435,7 +435,7 @@ Example usage `no-store` - When `True`, Will not cache the response.
```python
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{
"role": "user",
@ -453,7 +453,7 @@ Example usage `ttl` - cache the response for 10 seconds
```python
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{
"role": "user",
@ -471,7 +471,7 @@ Example usage `s-maxage` - Will only accept cached responses for 60 seconds
```python
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{
"role": "user",

8
docs/my-website/docs/caching/caching_api.md
View file

@ -11,13 +11,13 @@ litellm.cache = Cache(type="hosted") # init cache to use api.litellm.ai
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
caching=True
)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
caching=True
)
@ -59,7 +59,7 @@ litellm.cache = Cache(type="hosted")
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
stream=True,
caching=True)
@ -69,7 +69,7 @@ for chunk in response1:
time.sleep(1) # cache is updated asynchronously
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
stream=True,
caching=True)

8
docs/my-website/docs/caching/local_caching.md
View file

@ -18,12 +18,12 @@ litellm.cache = Cache()
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}]
caching=True
)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
caching=True
)
@ -55,14 +55,14 @@ litellm.cache = Cache()
# Make completion calls
response1 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
stream=True,
caching=True)
for chunk in response1:
print(chunk)
response2 = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a joke."}],
stream=True,
caching=True)

6
docs/my-website/docs/contribute_integration/custom_webhook_api.md
View file

@ -50,9 +50,9 @@ a. Setup config.yaml
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: openai/gpt-3.5-turbo
model: openai/gpt-4o
api_key: os.environ/OPENAI_API_KEY
- model_name: anthropic-claude
litellm_params:
@ -80,7 +80,7 @@ curl -L -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": "system",

4
docs/my-website/docs/debugging/local_debugging.md
View file

@ -17,7 +17,7 @@ os.environ["COHERE_API_KEY"] = "cohere key"
messages = [{ "content": "Hello, how are you?","role": "user"}]
# openai call
response = completion(model="gpt-3.5-turbo", messages=messages)
response = completion(model="gpt-4o", messages=messages)
# cohere call
response = completion("command-nightly", messages)
@ -59,7 +59,7 @@ os.environ["COHERE_API_KEY"] = "cohere key"
messages = [{ "content": "Hello, how are you?","role": "user"}]
# openai call
response = completion(model="gpt-3.5-turbo", messages=messages, logger_fn=my_custom_logging_fn)
response = completion(model="gpt-4o", messages=messages, logger_fn=my_custom_logging_fn)
# cohere call
response = completion("command-nightly", messages, logger_fn=my_custom_logging_fn)

6
docs/my-website/docs/guides/finetuned_models.md
View file

@ -11,9 +11,9 @@ import TabItem from '@theme/TabItem';
|---------------------------|-----------------------------------------------------------------|
| fine tuned `gpt-4-0613` | `response = completion(model="ft:gpt-4-0613", messages=messages)` |
| fine tuned `gpt-4o-2024-05-13` | `response = completion(model="ft:gpt-4o-2024-05-13", messages=messages)` |
| fine tuned `gpt-3.5-turbo-0125` | `response = completion(model="ft:gpt-3.5-turbo-0125", messages=messages)` |
| fine tuned `gpt-3.5-turbo-1106` | `response = completion(model="ft:gpt-3.5-turbo-1106", messages=messages)` |
| fine tuned `gpt-3.5-turbo-0613` | `response = completion(model="ft:gpt-3.5-turbo-0613", messages=messages)` |
| fine tuned `gpt-4o-0125` | `response = completion(model="ft:gpt-4o-0125", messages=messages)` |
| fine tuned `gpt-4o-1106` | `response = completion(model="ft:gpt-4o-1106", messages=messages)` |
| fine tuned `gpt-4o-0613` | `response = completion(model="ft:gpt-4o-0613", messages=messages)` |
## Vertex AI

10
docs/my-website/docs/integrations/letta.md
View file

@ -41,7 +41,7 @@ model_list:
model: anthropic/claude-3-sonnet-20240229
api_key: os.environ/ANTHROPIC_API_KEY
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/gpt-35-turbo
api_key: os.environ/AZURE_API_KEY
@ -726,7 +726,7 @@ agents['reviewer'] = client.create_agent(
name="reviewer",
system="You are an editor. Review and improve content quality.",
llm_config=LLMConfig(
model="openai/gpt-3.5-turbo",
model="openai/gpt-4o",
model_endpoint_type="openai"
)
)
@ -795,7 +795,7 @@ print(article)
1. **Model Selection**: Choose models based on task requirements:
- Use `openai/gpt-4` for complex reasoning
- Use `anthropic/claude-3-sonnet-20240229` for analysis
- Use `openai/gpt-3.5-turbo` for cost-effective simple tasks
- Use `openai/gpt-4o` for cost-effective simple tasks
2. **Error Handling**: Implement robust error handling with retries:
```python
@ -813,7 +813,7 @@ print(article)
except Exception as e:
print(f"LLM call failed: {e}")
# Implement fallback logic
return completion(model="openai/gpt-3.5-turbo", **kwargs)
return completion(model="openai/gpt-4o", **kwargs)
```
3. **Cost Management**:
@ -882,7 +882,7 @@ print("Anthropic Key:", os.environ.get("ANTHROPIC_API_KEY", "Not set"))
# Test direct LiteLLM call
try:
response = litellm.completion(
model="openai/gpt-3.5-turbo",
model="openai/gpt-4o",
messages=[{"role": "user", "content": "Hello"}]
)
print("LiteLLM working:", response.choices[0].message.content)

4
docs/my-website/docs/langchain/langchain.md
View file

@ -24,7 +24,7 @@ from langchain_core.prompts import (
from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
os.environ['OPENAI_API_KEY'] = ""
chat = ChatLiteLLM(model="gpt-3.5-turbo")
chat = ChatLiteLLM(model="gpt-4o")
messages = [
HumanMessage(
content="what model are you"
@ -455,7 +455,7 @@ tag_routing:
- tags: ["premium", "high-priority"]
models: ["gpt-4o", "claude-3-opus"]
- tags: ["standard"]
models: ["gpt-3.5-turbo", "claude-3-haiku"]
models: ["gpt-4o", "claude-3-haiku"]
```
### Monitoring and Analytics

48
docs/my-website/docs/providers/azure/azure.md
View file

@ -100,7 +100,7 @@ export AZURE_API_KEY=""
```yaml
model_list:
- 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/
@ -117,7 +117,7 @@ model_list:
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",
@ -137,7 +137,7 @@ client = openai.OpenAI(
base_url="http://0.0.0.0:4000"
)
response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
response = client.chat.completions.create(model="gpt-4o", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
@ -161,7 +161,7 @@ from langchain.schema import HumanMessage, SystemMessage
chat = ChatOpenAI(
openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
model = "gpt-3.5-turbo",
model = "gpt-4o",
temperature=0.1
)
@ -224,11 +224,11 @@ model_list:
| gpt-4-32k-0613 | `completion('azure/<your deployment name>', messages)` |
| gpt-4-1106-preview | `completion('azure/<your deployment name>', messages)` |
| gpt-4-0125-preview | `completion('azure/<your deployment name>', messages)` |
| gpt-3.5-turbo | `completion('azure/<your deployment name>', messages)` |
| gpt-3.5-turbo-0301 | `completion('azure/<your deployment name>', messages)` |
| gpt-3.5-turbo-0613 | `completion('azure/<your deployment name>', messages)` |
| gpt-3.5-turbo-16k | `completion('azure/<your deployment name>', messages)` |
| gpt-3.5-turbo-16k-0613 | `completion('azure/<your deployment name>', messages)`
| gpt-4o | `completion('azure/<your deployment name>', messages)` |
| gpt-4o-0301 | `completion('azure/<your deployment name>', messages)` |
| gpt-4o-0613 | `completion('azure/<your deployment name>', messages)` |
| gpt-4o-16k | `completion('azure/<your deployment name>', messages)` |
| gpt-4o-16k-0613 | `completion('azure/<your deployment name>', messages)`
## Azure OpenAI Vision Models
| Model Name | Function Call |
@ -524,8 +524,8 @@ Use `model="azure_text/<your-deployment>"`
| Model Name | Function Call |
|---------------------|----------------------------------------------------|
| gpt-3.5-turbo-instruct | `response = completion(model="azure_text/<your deployment name>", messages=messages)` |
| gpt-3.5-turbo-instruct-0914 | `response = completion(model="azure_text/<your deployment name>", messages=messages)` |
| gpt-4o-instruct | `response = completion(model="azure_text/<your deployment name>", messages=messages)` |
| gpt-4o-instruct-0914 | `response = completion(model="azure_text/<your deployment name>", messages=messages)` |
```python
@ -604,7 +604,7 @@ response = litellm.completion(
```yaml
model_list:
- 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/
@ -620,7 +620,7 @@ model_list:
Here is an example of setting up `tenant_id`, `client_id`, `client_secret` in your litellm proxy `config.yaml`
```yaml
model_list:
- 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/
@ -637,7 +637,7 @@ Test it
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",
@ -657,7 +657,7 @@ Example video of using `tenant_id`, `client_id`, `client_secret` with LiteLLM Pr
Here is an example of setting up `client_id`, `azure_username`, `azure_password` in your litellm proxy `config.yaml`
```yaml
model_list:
- 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/
@ -674,7 +674,7 @@ Test it
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",
@ -746,7 +746,7 @@ export AZURE_CLIENT_SECRET=""
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/your-deployment-name
api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@ -761,7 +761,7 @@ Perfect for AKS clusters, Azure VMs, or other managed environments where Azure a
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/your-deployment-name
api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@ -776,7 +776,7 @@ If you're authenticated via `az login`, no additional configuration needed:
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: azure/your-deployment-name
api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@ -1150,7 +1150,7 @@ pip install litellm
from litellm import Router
model_list = [{ # list of model deployments
"model_name": "gpt-3.5-turbo", # openai model name
"model_name": "gpt-4o", # openai model name
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-v-2",
"api_key": os.getenv("AZURE_API_KEY"),
@ -1160,7 +1160,7 @@ model_list = [{ # list of model deployments
"tpm": 240000,
"rpm": 1800
}, {
"model_name": "gpt-3.5-turbo", # openai model name
"model_name": "gpt-4o", # openai model name
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/chatgpt-functioncalling",
"api_key": os.getenv("AZURE_API_KEY"),
@ -1170,9 +1170,9 @@ model_list = [{ # list of model deployments
"tpm": 240000,
"rpm": 1800
}, {
"model_name": "gpt-3.5-turbo", # openai model name
"model_name": "gpt-4o", # openai model name
"litellm_params": { # params for litellm completion/embedding call
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"api_key": os.getenv("OPENAI_API_KEY"),
},
"tpm": 1000000,
@ -1182,7 +1182,7 @@ model_list = [{ # list of model deployments
router = Router(model_list=model_list)
# openai.chat.completions.create replacement
response = router.completion(model="gpt-3.5-turbo",
response = router.completion(model="gpt-4o",
messages=[{"role": "user", "content": "Hey, how's it going?"}]
print(response)

14
docs/my-website/docs/providers/custom_llm_server.md
View file

@ -31,7 +31,7 @@ from litellm import CustomLLM, completion, get_llm_provider
class MyCustomLLM(CustomLLM):
def completion(self, *args, **kwargs) -> litellm.ModelResponse:
return litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello world"}],
mock_response="Hi!",
) # type: ignore
@ -62,14 +62,14 @@ from litellm import CustomLLM, completion, get_llm_provider
class MyCustomLLM(CustomLLM):
def completion(self, *args, **kwargs) -> litellm.ModelResponse:
return litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello world"}],
mock_response="Hi!",
) # type: ignore
async def acompletion(self, *args, **kwargs) -> litellm.ModelResponse:
return litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello world"}],
mock_response="Hi!",
) # type: ignore
@ -135,7 +135,7 @@ Expected Response
}
],
"created": 1721955063,
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"object": "chat.completion",
"system_fingerprint": null,
"usage": {
@ -356,7 +356,7 @@ from litellm import CustomLLM, completion, get_llm_provider
class MyCustomLLM(CustomLLM):
async def acompletion(self, *args, **kwargs) -> litellm.ModelResponse:
return litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello world"}],
mock_response="Hi!",
) # type: ignore
@ -420,7 +420,7 @@ Expected Response
"id": "chatcmpl-Bm4qEp4h4vCe7Zi4Gud1MAxTWgibO",
"type": "message",
"role": "assistant",
"model": "gpt-3.5-turbo-0125",
"model": "gpt-4o-0125",
"stop_sequence": null,
"usage": {
"input_tokens": 18,
@ -455,7 +455,7 @@ class MyCustomLLM(CustomLLM):
def completion(self, *args, **kwargs) -> litellm.ModelResponse:
assert kwargs["optional_params"] == {"my_custom_param": "my-custom-param"} # 👈 CHECK HERE
return litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello world"}],
mock_response="Hi!",
) # type: ignore

4
docs/my-website/docs/providers/openrouter.md
View file

@ -51,8 +51,8 @@ This approach provides better flexibility for managing configurations across dif
| Model Name | Function Call |
|---------------------------|-----------------------------------------------------|
| openrouter/openai/gpt-3.5-turbo | `completion('openrouter/openai/gpt-3.5-turbo', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
| openrouter/openai/gpt-3.5-turbo-16k | `completion('openrouter/openai/gpt-3.5-turbo-16k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
| openrouter/openai/gpt-4o | `completion('openrouter/openai/gpt-4o', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
| openrouter/openai/gpt-4o-16k | `completion('openrouter/openai/gpt-4o-16k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
| openrouter/openai/gpt-4 | `completion('openrouter/openai/gpt-4', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
| openrouter/openai/gpt-4-32k | `completion('openrouter/openai/gpt-4-32k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
| openrouter/anthropic/claude-2 | `completion('openrouter/anthropic/claude-2', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |

24
docs/my-website/docs/providers/text_completion_openai.md
View file

@ -21,7 +21,7 @@ os.environ["OPENAI_API_KEY"] = "your-api-key"
# openai call
response = completion(
model = "gpt-3.5-turbo-instruct",
model = "gpt-4o-instruct",
messages=[{ "content": "Hello, how are you?","role": "user"}]
)
```
@ -43,20 +43,20 @@ export OPENAI_API_KEY=""
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: openai/gpt-3.5-turbo # The `openai/` prefix will call openai.chat.completions.create
model: openai/gpt-4o # The `openai/` prefix will call openai.chat.completions.create
api_key: os.environ/OPENAI_API_KEY
- model_name: gpt-3.5-turbo-instruct
- model_name: gpt-4o-instruct
litellm_params:
model: text-completion-openai/gpt-3.5-turbo-instruct # The `text-completion-openai/` prefix will call openai.completions.create
model: text-completion-openai/gpt-4o-instruct # The `text-completion-openai/` prefix will call openai.completions.create
api_key: os.environ/OPENAI_API_KEY
```
</TabItem>
<TabItem value="config-*" label="config.yaml - proxy all OpenAI models">
Use this to add all openai models with one API Key. **WARNING: This will not do any load balancing**
This means requests to `gpt-4`, `gpt-3.5-turbo` , `gpt-4-turbo-preview` will all go through this route
This means requests to `gpt-4`, `gpt-4o` , `gpt-4-turbo-preview` will all go through this route
```yaml
model_list:
@ -69,7 +69,7 @@ model_list:
<TabItem value="cli" label="CLI">
```bash
$ litellm --model gpt-3.5-turbo-instruct
$ litellm --model gpt-4o-instruct
# Server running on http://0.0.0.0:4000
```
@ -87,7 +87,7 @@ $ litellm --model gpt-3.5-turbo-instruct
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
"model": "gpt-3.5-turbo-instruct",
"model": "gpt-4o-instruct",
"messages": [
{
"role": "user",
@ -108,7 +108,7 @@ client = openai.OpenAI(
)
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="gpt-3.5-turbo-instruct", messages = [
response = client.chat.completions.create(model="gpt-4o-instruct", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
@ -132,7 +132,7 @@ from langchain.schema import HumanMessage, SystemMessage
chat = ChatOpenAI(
openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
model = "gpt-3.5-turbo-instruct",
model = "gpt-4o-instruct",
temperature=0.1
)
@ -156,8 +156,8 @@ print(response)
| Model Name | Function Call |
|---------------------|----------------------------------------------------|
| gpt-3.5-turbo-instruct | `response = completion(model="gpt-3.5-turbo-instruct", messages=messages)` |
| gpt-3.5-turbo-instruct-0914 | `response = completion(model="gpt-3.5-turbo-instruct-0914", messages=messages)` |
| gpt-4o-instruct | `response = completion(model="gpt-4o-instruct", messages=messages)` |
| gpt-4o-instruct-0914 | `response = completion(model="gpt-4o-instruct-0914", messages=messages)` |
| text-davinci-003 | `response = completion(model="text-davinci-003", messages=messages)` |
| ada-001 | `response = completion(model="ada-001", messages=messages)` |
| curie-001 | `response = completion(model="curie-001", messages=messages)` |