Deepseek

https://deepseek.com/

我们支持所有 Deepseek 模型，只需在发送补全请求时设置 deepseek/ 作为前缀即可

API Key

# env variable
os.environ['DEEPSEEK_API_KEY']

用法示例

from litellm import completion
import os

os.environ['DEEPSEEK_API_KEY'] = ""
response = completion(
    model="deepseek/deepseek-chat", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
)
print(response)

用法示例 - 流式

from litellm import completion
import os

os.environ['DEEPSEEK_API_KEY'] = ""
response = completion(
    model="deepseek/deepseek-chat", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
    stream=True
)

for chunk in response:
    print(chunk)

支持的模型 - 支持所有 Deepseek 模型！

我们支持所有 Deepseek 模型，只需在发送补全请求时设置 deepseek/ 作为前缀即可

模型名称	函数调用
deepseek-chat	completion(model="deepseek/deepseek-chat", messages)
deepseek-coder	completion(model="deepseek/deepseek-coder", messages)

推理模型

模型名称	函数调用
deepseek-reasoner	completion(model="deepseek/deepseek-reasoner", messages)

SDK

from litellm import completion
import os

os.environ['DEEPSEEK_API_KEY'] = ""
resp = completion(
    model="deepseek/deepseek-reasoner",
    messages=[{"role": "user", "content": "Tell me a joke."}],
)

print(
    resp.choices[0].message.reasoning_content
)

代理

1. 设置 config.yaml

model_list:
  - model_name: deepseek-reasoner
    litellm_params:
        model: deepseek/deepseek-reasoner
        api_key: os.environ/DEEPSEEK_API_KEY

2. 运行代理

python litellm/proxy/main.py

3. 测试！

curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
    "model": "deepseek-reasoner",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Hi, how are you ?"
          }
        ]
      }
    ]
}'