프로바이더별 파라미터

프로바이더별 파라미터 (Provider-specific Params)

프로바이더는 OpenAI가 지원하지 않는 파라미터(예: top_k)를 제공할 수 있어요. LiteLLM은 비-openai 파라미터를 프로바이더별 파라미터로 취급하고, 요청 본문에서 kwarg로 프로바이더에 전달합니다. Reserved Params 참고.

두 가지 방법으로 전달할 수 있어요:

completion() 을 통해서: 비-openai 파라미터를 요청 본문의 일부로 프로바이더에 직접 전달합니다. 예: completion(model="claude-sonnet-5", top_k=3)
프로바이더별 config 변수(예: litellm.OpenAIConfig())를 통해서.

SDK 사용법

OpenAI
OpenAI Text Completion
Azure OpenAI
Anthropic
Huggingface
TogetherAI
Ollama
Replicate
Petals
Palm
AI21
Cohere

OpenAI:

import litellm, os

# set env variables
os.environ["OPENAI_API_KEY"] = "your-openai-key"

## SET MAX TOKENS - via completion() 
response_1 = litellm.completion(
            model="gpt-5.6-luna",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.OpenAIConfig(max_tokens=10)

response_2 = litellm.completion(
            model="gpt-5.6-luna",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

OpenAI Text Completion:

import litellm, os

# set env variables
os.environ["OPENAI_API_KEY"] = "your-openai-key"

## SET MAX TOKENS - via completion() 
response_1 = litellm.completion(
            model="gpt-3.5-turbo-instruct",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.OpenAITextCompletionConfig(max_tokens=10)
response_2 = litellm.completion(
            model="gpt-3.5-turbo-instruct",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

Azure OpenAI:

import litellm, os

# set env variables
os.environ["AZURE_API_BASE"] = "your-azure-api-base"
os.environ["AZURE_API_TYPE"] = "azure" # [OPTIONAL] 
os.environ["AZURE_API_VERSION"] = "2023-07-01-preview" # [OPTIONAL]

## SET MAX TOKENS - via completion() 
response_1 = litellm.completion(
            model="azure/chatgpt-v-2",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.AzureOpenAIConfig(max_tokens=10)
response_2 = litellm.completion(
            model="azure/chatgpt-v-2",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

Anthropic:

import litellm, os 

# set env variables
os.environ["ANTHROPIC_API_KEY"] = "your-anthropic-key"

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="claude-sonnet-5",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.AnthropicConfig(max_tokens=200)
response_2 = litellm.completion(
            model="claude-sonnet-5",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

Huggingface:

import litellm, os 

# set env variables
os.environ["HUGGINGFACE_API_KEY"] = "your-huggingface-key" #[OPTIONAL]

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="huggingface/mistralai/Mistral-7B-Instruct-v0.1",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            api_base="https://your-huggingface-api-endpoint",
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.HuggingfaceConfig(max_new_tokens=200)
response_2 = litellm.completion(
            model="huggingface/mistralai/Mistral-7B-Instruct-v0.1",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            api_base="https://your-huggingface-api-endpoint"
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

TogetherAI:

import litellm, os 

# set env variables
os.environ["TOGETHERAI_API_KEY"] = "your-togetherai-key" 

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="together_ai/togethercomputer/llama-2-70b-chat",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.TogetherAIConfig(max_tokens=200)
response_2 = litellm.completion(
            model="together_ai/togethercomputer/llama-2-70b-chat",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

Ollama:

import litellm, os 

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="ollama/llama2",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.OllamConfig(num_predict=200)
response_2 = litellm.completion(
            model="ollama/llama2",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

Replicate:

import litellm, os 

# set env variables
os.environ["REPLICATE_API_KEY"] = "your-replicate-key" 

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="replicate/meta/llama-2-70b-chat:02e509c789964a7ea8736978a43525956ef40397be9033abf9fd2badfe68c9e3",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.ReplicateConfig(max_new_tokens=200)
response_2 = litellm.completion(
            model="replicate/meta/llama-2-70b-chat:02e509c789964a7ea8736978a43525956ef40397be9033abf9fd2badfe68c9e3",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

Petals:

import litellm

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="petals/petals-team/StableBeluga2",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            api_base="https://chat.petals.dev/api/v1/generate",
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.PetalsConfig(max_new_tokens=10)
response_2 = litellm.completion(
            model="petals/petals-team/StableBeluga2",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            api_base="https://chat.petals.dev/api/v1/generate",
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

Palm:

import litellm, os 

# set env variables
os.environ["PALM_API_KEY"] = "your-palm-key"  

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="palm/chat-bison",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.PalmConfig(max_output_tokens=10)
response_2 = litellm.completion(
            model="palm/chat-bison",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

AI21:

import litellm, os 

# set env variables
os.environ["AI21_API_KEY"] = "your-ai21-key"  

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="j2-mid",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.AI21Config(maxOutputTokens=10)
response_2 = litellm.completion(
            model="j2-mid",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

Cohere:

import litellm, os 

# set env variables
os.environ["COHERE_API_KEY"] = "your-cohere-key"   

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="command-nightly",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
            max_tokens=10
        )

response_1_text = response_1.choices[0].message.content

## SET MAX TOKENS - via config
litellm.CohereChatConfig(max_tokens=200)
response_2 = litellm.completion(
            model="command-nightly",
            messages=[{ "content": "Hello, how are you?","role": "user"}],
        )

response_2_text = response_2.choices[0].message.content

## TEST OUTPUT
assert len(response_2_text) > len(response_1_text)

튜토리얼을 확인하세요!

출처: 문서

본문

Proxy 사용법

via Config:

model_list:
    - model_name: llama-3-8b-instruct
      litellm_params:
        model: predibase/llama-3-8b-instruct
        api_key: os.environ/PREDIBASE_API_KEY
        tenant_id: os.environ/PREDIBASE_TENANT_ID
        max_tokens: 256
        adapter_base: <my-special_base> # 👈 PROVIDER-SPECIFIC PARAM

via Request:

curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer ***" \
-d '{
  "model": "llama-3-8b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "What'\''s the weather like in Boston today?"
    }
  ],
  "adapater_id": "my-special-adapter-id"
}'

프로바이더별 메타데이터 파라미터

프로바이더	파라미터	사용 사례
AWS Bedrock	`requestMetadata`	비용 귀속, 로깅
Gemini/Vertex AI	`labels`	리소스 라벨링
Anthropic	`metadata`	사용자 식별

AWS Bedrock
Gemini/Vertex AI
Anthropic

import litellm

response = litellm.completion(
    model="bedrock/us.anthropic.claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello!"}],
    requestMetadata={"cost_center": "engineering"}
)

import litellm

response = litellm.completion(
    model="vertex_ai/gemini-3.8-flash",
    messages=[{"role": "user", "content": "Hello!"}],
    labels={"environment": "production"}
)

import litellm

response = litellm.completion(
    model="anthropic/claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello!"}],
    metadata={"user_id": "user123"}
)

프로바이더별 파라미터

프로바이더별 파라미터 (Provider-specific Params)

SDK 사용법

본문

Proxy 사용법

프로바이더별 메타데이터 파라미터

더 알아보기 (Learn more)