---
title: "提供者專屬參數"
url: "/docs/completion/provider_specific_params"
canonical_url: "https://docs.litellm.ai/docs/completion/provider_specific_params"
type: "docs"
last_updated: "2026-10-08"
related:
  - "/docs/guides/compatibility_extensibility"
  - "/docs/completion/drop_params"
---
# 提供者專屬參數

> Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt


提供者可能會提供 OpenAI 不支援的參數（例如 top_k）。LiteLLM 會將任何非 openai 參數視為提供者專屬參數，並在請求內文中以 kwargs 形式傳遞給提供者。[**請參閱保留參數**](https://github.com/BerriAI/litellm/blob/aa2fd29e48245f360e771a8810a69376464b195e/litellm/main.py#L700)

您可以透過 2 種方式傳遞這些參數： 
- 透過 completion()：我們會將非 openai 參數直接作為請求內文的一部分傳遞給提供者。
    - 例如 `completion(model="claude-sonnet-5", top_k=3)`
- 透過提供者專屬設定變數（例如 `litellm.OpenAIConfig()`）。

## SDK 使用方式 {#sdk-usage}
**OpenAI**

```python
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 文字完成**

```python
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**

```python
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**

```python
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**

```python
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
```

Huggingface 路由不會讀取提供者組態預設值，因此 `litellm.HuggingFaceChatConfig(max_tokens=...)` 不會對請求產生影響。請改為在每次 `completion()` 呼叫時傳入 `max_tokens`

**TogetherAI**

```python
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**

```python
import litellm, os 

## SET MAX TOKENS - via completion()
response_1 = litellm.completion(
            model="ollama_chat/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.OllamaChatConfig(num_predict=200)
response_2 = litellm.completion(
            model="ollama_chat/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**

```python
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**

```python
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)
```

**AI21**

```python
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**

```python
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)
```

[**查看教學！**](../tutorials/provider_specific_params.md)

## 代理程式使用方式  {#proxy-usage}

**透過設定**

```yaml
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
```

**透過請求**

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

## 提供者專屬中繼資料參數 {#provider-specific-metadata-parameters}

| 提供者 | 參數 | 使用情境 |
|----------|-----------|----------|
| **AWS Bedrock** | `requestMetadata` | 成本歸屬、記錄 |
| **Gemini/Vertex AI** | `labels` | 資源標記 |
| **Anthropic** | `metadata` | 使用者識別 |

**AWS Bedrock**

```python
import litellm

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

**Gemini/Vertex AI**

```python
import litellm

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

**Anthropic**

```python
import litellm

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

## Related pages

- [Compatibility & Extensibility](https://docs.litellm.ai/docs/guides/compatibility_extensibility.md)
- [移除不支援的參數](https://docs.litellm.ai/docs/completion/drop_params.md)