Messages

Create a model response using the Anthropic Messages API format through the attested Confidential AI gateway.

POST /messages

Messages

cURL

curl --request POST \
  --url https://api.example.com/messages \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "max_tokens": 123,
  "messages": [
    {}
  ],
  "system": "<string>",
  "temperature": 123,
  "stream": true,
  "provider": {}
}
'

import requests

url = "https://api.example.com/messages"

payload = {
    "model": "<string>",
    "max_tokens": 123,
    "messages": [{}],
    "system": "<string>",
    "temperature": 123,
    "stream": True,
    "provider": {}
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    max_tokens: 123,
    messages: [{}],
    system: '<string>',
    temperature: 123,
    stream: true,
    provider: {}
  })
};

fetch('https://api.example.com/messages', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/messages",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => '<string>',
    'max_tokens' => 123,
    'messages' => [
        [
                
        ]
    ],
    'system' => '<string>',
    'temperature' => 123,
    'stream' => true,
    'provider' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/messages"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"max_tokens\": 123,\n  \"messages\": [\n    {}\n  ],\n  \"system\": \"<string>\",\n  \"temperature\": 123,\n  \"stream\": true,\n  \"provider\": {}\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/messages")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"max_tokens\": 123,\n  \"messages\": [\n    {}\n  ],\n  \"system\": \"<string>\",\n  \"temperature\": 123,\n  \"stream\": true,\n  \"provider\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/messages")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"max_tokens\": 123,\n  \"messages\": [\n    {}\n  ],\n  \"system\": \"<string>\",\n  \"temperature\": 123,\n  \"stream\": true,\n  \"provider\": {}\n}"

response = http.request(request)
puts response.read_body

Creates a model response using the Anthropic Messages request and response format. Requests are served through the attested gateway and return an x-receipt-id header for verification.

Endpoint

POST https://inference.phala.com/v1/messages

Request Body

model · string · required

Model id returned by List Models.

max_tokens · integer · required

Maximum number of tokens to generate.

messages · array · required

Conversation turns. Each item has a role (user or assistant) and content.

system · string

System prompt, sent as a top-level field.

temperature · number

Sampling temperature.

stream · boolean

Stream the response as server-sent events.

provider · object

Routing constraints for this request, applied together. zdr restricts routing to providers that do not retain content; aci_verified restricts it to an upstream verified inside the TEE; aci_session_ids pins it to specific attested channels.

{"provider": {"aci_verified": true}}

If no provider satisfies the constraints the request fails before the prompt is sent, and failover retries stay inside the allowed set. Field reference: Chat Completions. See Attested Routing and Zero Data Retention.

Example

curl https://inference.phala.com/v1/messages \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4.5",
    "max_tokens": 100,
    "messages": [
      {"role": "user", "content": "Say hello in three words."}
    ]
  }'

Response

{
  "id": "msg_01ABC...",
  "type": "message",
  "role": "assistant",
  "model": "anthropic/claude-sonnet-4.5",
  "content": [
    { "type": "text", "text": "Hello, howdy, hi!" }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": { "input_tokens": 14, "output_tokens": 8 }
}

Read assistant text from content[].text on blocks with type: "text". stop_reason is usually end_turn, max_tokens, stop_sequence, or tool_use.

Verification

Use the response x-receipt-id header with Get Receipt. A confidential response has upstream.verified.result = verified and required = true.

Related

Responses

Trust Boundary