curl https://llm.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="your-hanzo-api-key",
    base_url="https://llm.hanzo.ai/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-5-20250929",
    messages=[{"role": "user", "content": "Explain quantum computing"}]
)
print(response.choices[0].message.content)

import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: process.env.HANZO_API_KEY,
  baseURL: 'https://llm.hanzo.ai/v1',
})

const completion = await client.chat.completions.create({
  model: 'claude-sonnet-4-5-20250929',
  messages: [{ role: 'user', content: 'Explain quantum computing' }],
})
console.log(completion.choices[0].message.content)

model_list:
  - model_name: "default"
    litellm_params:
      model: "anthropic/claude-sonnet-4-5-20250929"
      api_key: "os.environ/ANTHROPIC_API_KEY"

  - model_name: "default"
    litellm_params:
      model: "openai/gpt-4o"
      api_key: "os.environ/OPENAI_API_KEY"

  - model_name: "fast"
    litellm_params:
      model: "groq/llama-3.1-70b"
      api_key: "os.environ/GROQ_API_KEY"

router_settings:
  routing_strategy: "latency-based-routing"
  fallbacks:
    - default: ["fast"]