LiteLLM

model_list:
  - model_name: deepseek-v4.1-flash-uncensored
    litellm_params:
      model: openai/deepseek-v4.1-flash-uncensored
      api_base: https://nokeep.ai/v1
      api_key: os.environ/NOKEEP_API_KEY
    model_info:
      input_cost_per_token: 0.00000045
      cache_read_input_token_cost: 0.000000011
      output_cost_per_token: 0.00000175
  - model_name: glm-5.3-flash-uncensored
    litellm_params:
      model: openai/glm-5.3-flash-uncensored
      api_base: https://nokeep.ai/v1
      api_key: os.environ/NOKEEP_API_KEY
    model_info:
      input_cost_per_token: 0.0000002
      cache_read_input_token_cost: 0.00000004
      output_cost_per_token: 0.00000065

pip install 'litellm[proxy]'
export NOKEEP_API_KEY="sk-nokeep-test"  # your own key once it connects
litellm --config config.yaml

pip install litellm
export NOKEEP_API_KEY="sk-nokeep-test"  # your own key once it connects

import os
import litellm

reply = litellm.completion(
    model="openai/deepseek-v4.1-flash-uncensored",
    api_base="https://nokeep.ai/v1",
    api_key=os.environ["NOKEEP_API_KEY"],
    messages=[{"role": "user", "content": "Name three good names for a tavern."}],
)
print(reply.choices[0].message.content)
print(reply.usage)

import os
import litellm

stream = litellm.completion(
    model="openai/deepseek-v4.1-flash-uncensored",
    api_base="https://nokeep.ai/v1",
    api_key=os.environ["NOKEEP_API_KEY"],
    messages=[{"role": "user", "content": "Tell me a story in three lines."}],
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="", flush=True)
    if getattr(chunk, "usage", None):
        print("\n", chunk.usage)

import os
import litellm

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get the weather in a city",
        "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string"}},
            "required": ["city"],
        },
    },
}]

reply = litellm.completion(
    model="openai/deepseek-v4.1-flash-uncensored",
    api_base="https://nokeep.ai/v1",
    api_key=os.environ["NOKEEP_API_KEY"],
    messages=[{"role": "user", "content": "What's the weather in Lisbon?"}],
    tools=tools,
    reasoning_effort="high",
    max_tokens=4000,
    extra_body={"min_p": 0.05},  # fields LiteLLM has no argument for
)
print(reply.choices[0].message.tool_calls)