どこからでも安全に llama.cpp サーバーを利用可能

curl https://api.tokios.com/v1/chat/completions \
  -H "Authorization: Bearer sk-tok-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-tunnel",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.tokios.com/v1",
    api_key="sk-tok-YOUR_KEY",
)

response = client.chat.completions.create(
    model="llama-tunnel",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)

for chunk in response:
    print(chunk.choices[0].delta.content or "", end="")

export ANTHROPIC_BASE_URL=https://api.tokios.com
export ANTHROPIC_API_KEY=sk-tok-YOUR_KEY
claude --model llama-tunnel