Inference

Create a message (native Anthropic Messages API)

Native Anthropic Messages API for Claude models only — no translation layer, so Anthropic SDKs and Anthropic-format clients (Claude Code, Claude Desktop) point here directly. The compliance level in model selects the government cloud provider. For Google or OpenAI models, use /v1/chat/completions instead. The gateway validates model, messages, and max_tokens; every other Anthropic Messages API field passes through unchanged.

post/v1/messages

Request

  • Base URL: https://api.consus.io
  • URL: https://api.consus.io/v1/messages
  • Auth: API key in header x-api-key

Request body

modelstring required

A Claude model with a compliance level, e.g. claude-sonnet-4-5:itar. Bare model names return 400.

messagesobject[] required
max_tokensinteger required
systemstring
streamboolean
toolsobject[]
tool_choiceobject
thinkingobject

Response

Anthropic Messages API response (or, with stream: true, an Anthropic-format text/event-stream).

idstring
typestring
rolestring
contentobject[]
modelstring
stop_reasonstring
stop_sequencestring nullable
x_consus_governanceobject

Example response

{
  "type": "message",
  "role": "assistant"
}

Changes

No recorded changes to this operation across all 1 revision of this API.