Messages

Anthropic native messages endpoint, used by Claude models. Compared to OpenAI's Chat Completions, the differences are: system is a top-level field, content supports a block array, and tool calls flow through tool_use / tool_result.

Protocol boundary

This is the Anthropic request/response format. Claude and Deepseek groups are the primary use case; some OpenAI groups may also expose /v1/messages through gateway translation, but support depends on group configuration.

Endpoint

POST https://api.sakrylle.com/v1/messages

Headers

Name	Required	Description
`Authorization`	Yes	`Bearer sk-xxxxxxxxxxxxxxxx`
`Content-Type`	Yes	`application/json`
`anthropic-version`	No	Matches Anthropic's official header, e.g. `2023-06-01`. Passed through to upstream.
`Accept`	No	Set `text/event-stream` for streaming

Request body

Field	Type	Required	Description
`model`	string	Yes	Claude model ID, e.g. `claude-haiku-4-5-20251001`
`messages`	array	Yes	Conversation history; each item has `role` (`user` or `assistant`) and `content` (string or block array)
`max_tokens`	integer	Yes	Maximum output tokens
`system`	string \| array	No	System prompt at the top level (do not put it inside `messages`)
`stream`	boolean	No	Defaults to `false`; `true` returns SSE
`temperature`	number	No	0–1
`top_p`	number	No	Nucleus sampling probability
`top_k`	integer	No	Top-k sampling
`stop_sequences`	array	No	Stop sequences
`tools`	array	No	Tool definitions, each with `name`, `description`, `input_schema`
`tool_choice`	object	No	`{"type":"auto"}` / `{"type":"any"}` / `{"type":"tool","name":"..."}`
`metadata`	object	No	e.g. `{"user_id":"..."}`

The gateway only validates that model is present; all other fields pass through to upstream.

Example request

json

{
  "model": "claude-haiku-4-5-20251001",
  "max_tokens": 1024,
  "system": "You are a concise assistant.",
  "messages": [
    { "role": "user", "content": "Hi, please introduce yourself." }
  ]
}

Example response

json

{
  "id": "msg_xxxxxxxxxxxxxxxxxxxxxxxx",
  "type": "message",
  "role": "assistant",
  "model": "claude-haiku-4-5-20251001",
  "content": [
    { "type": "text", "text": "Hi! I'm Claude, an assistant trained by Anthropic." }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 24,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "output_tokens": 18
  }
}

Tool calls

Declare tools in the request:

json

{
  "model": "claude-haiku-4-5-20251001",
  "max_tokens": 1024,
  "tools": [
    {
      "name": "get_weather",
      "description": "Look up the current weather for a city",
      "input_schema": {
        "type": "object",
        "properties": {
          "city": { "type": "string" }
        },
        "required": ["city"]
      }
    }
  ],
  "messages": [
    { "role": "user", "content": "What's the weather in Shanghai right now?" }
  ]
}

When the model decides to call a tool, the response content includes a tool_use block:

json

{
  "id": "msg_xxxxxxxxxxxxxxxxxxxxxxxx",
  "type": "message",
  "role": "assistant",
  "model": "claude-haiku-4-5-20251001",
  "content": [
    {
      "type": "tool_use",
      "id": "toolu_xxxxxxxxxxxxxxxx",
      "name": "get_weather",
      "input": { "city": "Shanghai" }
    }
  ],
  "stop_reason": "tool_use",
  "usage": { "input_tokens": 312, "output_tokens": 47 }
}

Continue the conversation by writing the tool result back as a tool_result block:

json

{
  "model": "claude-haiku-4-5-20251001",
  "max_tokens": 1024,
  "messages": [
    { "role": "user", "content": "What's the weather in Shanghai right now?" },
    {
      "role": "assistant",
      "content": [
        {
          "type": "tool_use",
          "id": "toolu_xxxxxxxxxxxxxxxx",
          "name": "get_weather",
          "input": { "city": "Shanghai" }
        }
      ]
    },
    {
      "role": "user",
      "content": [
        {
          "type": "tool_result",
          "tool_use_id": "toolu_xxxxxxxxxxxxxxxx",
          "content": "Sunny, 26°C"
        }
      ]
    }
  ]
}

Streaming response

With stream: true, the server returns SSE events. The minimum skeleton:

event: message_start
data: {"type":"message_start","message":{"id":"msg_xxx","type":"message","role":"assistant","model":"claude-haiku-4-5-20251001","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":24,"output_tokens":0}}}

event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hi"}}

event: content_block_stop
data: {"type":"content_block_stop","index":0}

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":24,"output_tokens":18}}

event: message_stop
data: {"type":"message_stop"}

Errors

400 invalid_request_error — missing model, body is not JSON, or parse failure
401 authentication_error — invalid API key
403 billing_error — balance or subscription quota exhausted
403 permission_error — group is restricted to Claude Code clients and rejects others
429 rate_limit_error — concurrency or rate limit hit
502 upstream_error — upstream repeatedly failed, please retry later

For the full table, see Errors.

Code samples

bash

curl https://api.sakrylle.com/v1/messages \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-haiku-4-5-20251001",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

python

from anthropic import Anthropic

client = Anthropic(
    api_key="sk-xxxxxxxxxxxxxxxx",
    base_url="https://api.sakrylle.com",
)

msg = client.messages.create(
    model="claude-haiku-4-5-20251001",
    max_tokens=1024,
    system="You are a concise assistant.",
    messages=[{"role": "user", "content": "Hello"}],
)
print(msg.content[0].text)

javascript

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "sk-xxxxxxxxxxxxxxxx",
  baseURL: "https://api.sakrylle.com",
});

const msg = await client.messages.create({
  model: "claude-haiku-4-5-20251001",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(msg.content[0].text);

package main

import (
    "context"
    "fmt"

    "github.com/anthropics/anthropic-sdk-go"
    "github.com/anthropics/anthropic-sdk-go/option"
)

func main() {
    client := anthropic.NewClient(
        option.WithAPIKey("sk-xxxxxxxxxxxxxxxx"),
        option.WithBaseURL("https://api.sakrylle.com/"),
    )
    msg, err := client.Messages.New(context.Background(), anthropic.MessageNewParams{
        Model:     anthropic.F(anthropic.Model("claude-haiku-4-5-20251001")),
        MaxTokens: anthropic.F(int64(1024)),
        Messages: anthropic.F([]anthropic.MessageParam{
            anthropic.NewUserMessage(anthropic.NewTextBlock("Hello")),
        }),
    })
    if err != nil {
        panic(err)
    }
    fmt.Println(msg.Content[0].Text)
}

rust

use reqwest::Client;
use serde_json::json;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    let client = Client::new();
    let resp: serde_json::Value = client
        .post("https://api.sakrylle.com/v1/messages")
        .bearer_auth("sk-xxxxxxxxxxxxxxxx")
        .header("anthropic-version", "2023-06-01")
        .json(&json!({
            "model": "claude-haiku-4-5-20251001",
            "max_tokens": 1024,
            "messages": [{"role": "user", "content": "Hello"}]
        }))
        .send()
        .await?
        .json()
        .await?;
    println!("{resp:#}");
    Ok(())
}

java

import java.net.URI;
import java.net.http.*;

public class Messages {
  public static void main(String[] args) throws Exception {
    String body = """
      {"model":"claude-haiku-4-5-20251001","max_tokens":1024,
       "messages":[{"role":"user","content":"Hello"}]}
      """;
    HttpRequest req = HttpRequest.newBuilder()
      .uri(URI.create("https://api.sakrylle.com/v1/messages"))
      .header("Authorization", "Bearer sk-xxxxxxxxxxxxxxxx")
      .header("Content-Type", "application/json")
      .header("anthropic-version", "2023-06-01")
      .POST(HttpRequest.BodyPublishers.ofString(body))
      .build();
    HttpResponse<String> resp = HttpClient.newHttpClient()
      .send(req, HttpResponse.BodyHandlers.ofString());
    System.out.println(resp.body());
  }
}

csharp

using System.Net.Http.Headers;
using System.Text;

var http = new HttpClient();
http.DefaultRequestHeaders.Authorization =
    new AuthenticationHeaderValue("Bearer", "sk-xxxxxxxxxxxxxxxx");
http.DefaultRequestHeaders.Add("anthropic-version", "2023-06-01");

var payload = """
  {"model":"claude-haiku-4-5-20251001","max_tokens":1024,
   "messages":[{"role":"user","content":"Hello"}]}
  """;
var resp = await http.PostAsync(
    "https://api.sakrylle.com/v1/messages",
    new StringContent(payload, Encoding.UTF8, "application/json"));
Console.WriteLine(await resp.Content.ReadAsStringAsync());

Messages ​

Endpoint ​

Headers ​

Request body ​

Example request ​

Example response ​

Tool calls ​

Streaming response ​

Errors ​

Code samples ​

Messages

Endpoint

Headers

Request body

Example request

Example response

Tool calls

Streaming response

Errors

Code samples