Use the Anthropic SDK with Meridian

Drop-in replacement — point the official SDK at the Meridian gateway.

Anthropic models currently 401 — upstream key rotation in progress. Use the OpenAI-compatible path with the Claude proxy bridge.

Step 1

pip install anthropic

Step 2

from anthropic import Anthropic

client = Anthropic(
    api_key="nim_live_***",
    base_url="https://meridian.getnimbus.net/api/v1",
)

Step 3

msg = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "hello"}],
)

Step 4

print(msg.content[0].text)

Streaming

Use the .stream() method for token-by-token output.

with client.messages.stream(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "hello"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

Tool use

Pass a tools array with name, description, and input_schema.

tools = [
    {
        "name": "get_weather",
        "description": "Get current weather for a city",
        "input_schema": {
            "type": "object",
            "properties": {
                "city": {"type": "string"}
            },
            "required": ["city"],
        },
    }
]

msg = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "What's the weather in London?"}],
    tools=tools,
)

All requests route through meridian.getnimbus.net. Keys are logged and rate-limited per plan tier.