Messages

The Messages API is the primary way to interact with Claude models through Claudexia. Send a structured list of messages and receive a model-generated response.

Endpoint

http

POST https://api.claudexia.tech/v1/messages

Authentication

Include your API key in the x-api-key header:

http

x-api-key: sk_cdx_YOUR_KEY

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	The model ID to use (e.g. claude-sonnet-4-20250514).
`max_tokens`	integer	Yes	Maximum number of tokens to generate.
`messages`	array	Yes	Array of message objects with role ("user" or "assistant") and content (string or array of content blocks).
`system`	string	No	System prompt to guide the model's behavior.
`temperature`	number	No	Sampling temperature between 0 and 1. Default: 1.
`top_p`	number	No	Nucleus sampling parameter. Default: 0.999.
`stream`	boolean	No	If true, returns a stream of Server-Sent Events. Default: false.
`thinking`	object	No	Enable extended thinking. See Thinking below.

Response

Field	Type	Description
`id`	string	Unique message ID (e.g. msg_01XFDUDYJgAACzvnptvVoYEL).
`type`	string	Always "message".
`role`	string	Always "assistant".
`content`	array	Array of content blocks. Each block has type ("text") and text.
`model`	string	The model that generated the response.
`stop_reason`	string	Why the model stopped: "end_turn", "max_tokens", or "stop_sequence".
`usage`	object	Token usage with input_tokens and output_tokens.

Example

Request

bash

curl https://api.claudexia.tech/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk_cdx_YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4.5",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello, Claude!"}
    ]
  }'

Response

json

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "model": "claude-sonnet-4.5",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 10
  }
}

Streaming

Set stream: true in the request body to receive the response as a stream of Server-Sent Events (SSE). See the Streaming page for details on the event format.

bash

curl --no-buffer https://api.claudexia.tech/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk_cdx_<YOUR_KEY>" \
  -H "anthropic-version: 2023-06-01" \
  -H "accept: text/event-stream" \
  -d '{
    "model": "claude-opus-4.7",
    "max_tokens": 1024,
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vision (image blocks)

When using vision-capable models, send multimodal content: mix text with image blocks (URL source shown below).

json

{
  "model": "claude-sonnet-4.5",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "What is in this image?"},
        {
          "type": "image",
          "source": {"type": "url", "url": "https://example.com/picture.jpg"}
        }
      ]
    }
  ]
}

Thinking (Extended Thinking)

Enable extended thinking to let the model reason through complex problems before responding. Pass a thinking object in the request body:

json

{
  "model": "claude-sonnet-4.5",
  "max_tokens": 16000,
  "thinking": {
    "type": "enabled",
    "budget_tokens": 10000
  },
  "messages": [
    {"role": "user", "content": "What is the derivative of x^3 * sin(x)?"}
  ]
}

When thinking is enabled, the response content array may include a block with type: "thinking" containing the model's reasoning, followed by the final type: "text" response. The budget_tokens parameter controls the maximum tokens allocated for the thinking process.

Overview

Models