Anthropic Messages - Planck

POST /v1/messages accepts an Anthropic Messages-style request and routes it through the Planck gateway pipeline. Use this route when you want Anthropic-style inputs with Planck billing, logging, routing, and observability.

max_tokens is required. Planck does not supply a default for an Anthropic-compatible Messages request.

Endpoint URL

https://api.inquantum.ai/v1/messages

Example Request

curl https://api.inquantum.ai/v1/messages \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-4.5-sonnet",
    "max_tokens": 256,
    "messages": [
      {
        "role": "user",
        "content": "Say hello."
      }
    ]
  }'

Native Anthropic

When using the Anthropic SDK, set base_url to https://api.inquantum.ai/anthropic and give the SDK your Planck API key. The SDK appends /v1/messages, and the resulting POST /anthropic/v1/messages request uses the same mapped gateway pipeline as this route.

import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ["PLANCK_API_KEY"],
    base_url="https://api.inquantum.ai/anthropic",
)

message = client.messages.create(
    model="claude-4.5-sonnet",
    max_tokens=256,
    messages=[{"role": "user", "content": "Say hello."}],
)

Use other paths under /anthropic/v1/* only for Anthropic-native endpoints not covered by Messages. See Anthropic-compatible routes for details. For thinking and output_config.effort examples, see Reasoning and thinking.

This endpoint uses the shared AI Gateway error envelope. See the Error Handling & Fallback guide for response examples, retry rules, fallback behavior, and streaming errors.