Messages (Anthropic-compatible)

Compatible with the Anthropic Messages API. Under the hood it shares the same routing pipeline as Chat Completions — only the request/response shape is adapted to Anthropic style.

Example

from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.modelsite.ai",   # SDK appends /v1/messages
    auth_token="ms_live_sk_xxxxxxxx",       # Authorization: Bearer (required — not api_key)
)
resp = client.messages.create(
    model="claude-sonnet-4.6",
    max_tokens=256,
    messages=[{"role": "user", "content": "Explain quantum entanglement in one sentence"}],
)
print(resp.content[0].text)

The API card below is rendered from the OpenAPI spec (auth, Request-body parameter table, Response schema).

curl -X POST "https://example.com/messages" \  -H "anthropic-version: 2023-06-01" \  -H "Content-Type: application/json" \  -d '{    "model": "string",    "messages": [      {}    ],    "max_tokens": 0  }'

{  "id": "string",  "type": "string",  "role": "string",  "model": "string",  "content": [    {      "type": "string",      "text": "string"    }  ],  "stop_reason": "end_turn",  "stop_sequence": "string",  "usage": {    "input_tokens": 0,    "output_tokens": 0,    "cache_creation_input_tokens": 0,    "cache_read_input_tokens": 0  }}

Streaming

stream: true returns an event sequence: message_start → content_block_start → content_block_delta (many) → content_block_stop → message_delta → message_stop.

Which format?

Both entry points reach the same set of models.