SDK & HTTP Clients

客户端 SDK

使用 OpenAI SDK、Anthropic SDK 或任意 HTTP 客户端接入 ClawdRouter。 推荐优先使用 OpenAI-compatible 接口完成文本、流式输出、图片等常规调用； 只有在需要 Anthropic 原生 Messages 协议时，再使用 Anthropic SDK 或 /v1/messages。

发起请求API 参考

准备 API Key安装 SDK发起请求处理响应或任务

选择接入方式

推荐OpenAI SDK

适合文本生成、流式输出、图片生成，以及希望用统一 OpenAI-compatible 格式接入多家模型的场景。

Base URL

DOCS_API_ORIGIN/v1

主要接口

/v1/chat/completions/v1/responses/v1/images/generations

查看文本生成示例

Claude 原生Anthropic SDK

适合已经使用 Anthropic SDK，或必须保留 Claude 原生 Messages 请求格式的项目。

Base URL

DOCS_API_ORIGIN

主要接口

/v1/messages

查看 Messages 示例

异步任务HTTP 客户端

适合 Go、Java、PHP、Ruby、C# 等语言，或需要直接控制请求头、超时、重试和日志的服务端接入。

Base URL

按接口选择

主要接口

所有 API endpoint

查看视频生成示例

语言切换会保持同步本页所有示例共享同一组 Tab。切换一次语言后，安装、聊天、流式、视频和 Anthropic 示例都会保持同一个语言视图。

准备 API Key

所有示例都使用同一个 API Key。建议通过环境变量管理密钥：

export CLAWDROUTER_API_KEY="YOUR_API_KEY"
export CLAWDROUTER_BASE_URL="__DOCS_API_ORIGIN__"

如果项目直接使用 OpenAI SDK 的默认环境变量，也可以这样配置：

export OPENAI_API_KEY="YOUR_API_KEY"
export OPENAI_BASE_URL="__DOCS_API_ORIGIN__/v1"

Anthropic SDK 使用同一个 API Key，但 base_url 应设置为 __DOCS_API_ORIGIN__，不要带 /v1。

安装 SDK

cURL

cURL 通常已经内置在 macOS 和 Linux 中。Windows 用户可以使用 PowerShell、Git Bash 或 WSL。

Python

pip install openai

Node.js

npm install openai

Go

Go 示例使用标准库 net/http，不需要额外安装依赖。

Java

Java 示例使用 JDK 11+ 内置的 java.net.http.HttpClient，不需要额外安装依赖。

PHP

PHP 示例使用内置 cURL 扩展。请确认运行环境已启用 curl。

Ruby

Ruby 示例使用标准库 net/http，不需要额外安装依赖。

C#

C# 示例使用 .NET 内置 HttpClient，不需要额外安装依赖。

发起文本生成请求

以下示例使用 OpenAI-compatible Chat Completions 接口。适合大多数聊天、问答和文本生成场景。

POST __DOCS_API_ORIGIN__/v1/chat/completions

cURL

curl __DOCS_API_ORIGIN__/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CLAWDROUTER_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "你是一个有用的助手"},
      {"role": "user", "content": "用简单的话解释什么是机器学习"}
    ]
  }'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["CLAWDROUTER_API_KEY"],
    base_url="__DOCS_API_ORIGIN__/v1",
)

completion = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "你是一个有用的助手"},
        {"role": "user", "content": "用简单的话解释什么是机器学习"},
    ],
)

print(completion.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CLAWDROUTER_API_KEY,
  baseURL: "__DOCS_API_ORIGIN__/v1",
});

const completion = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [
    { role: "system", content: "你是一个有用的助手" },
    { role: "user", content: "用简单的话解释什么是机器学习" },
  ],
});

console.log(completion.choices[0].message.content);

Go

package main

import (
	"bytes"
	"fmt"
	"io"
	"net/http"
	"os"
)

func main() {
	body := []byte(`{
	  "model": "gpt-4o",
	  "messages": [
	    {"role": "system", "content": "你是一个有用的助手"},
	    {"role": "user", "content": "用简单的话解释什么是机器学习"}
	  ]
	}`)

	req, _ := http.NewRequest(
		"POST",
		"__DOCS_API_ORIGIN__/v1/chat/completions",
		bytes.NewReader(body),
	)
	req.Header.Set("Content-Type", "application/json")
	req.Header.Set("Authorization", "Bearer "+os.Getenv("CLAWDROUTER_API_KEY"))

	resp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()

	data, _ := io.ReadAll(resp.Body)
	fmt.Println(string(data))
}

Java

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
  public static void main(String[] args) throws Exception {
    String body = """
      {
        "model": "gpt-4o",
        "messages": [
          {"role": "system", "content": "你是一个有用的助手"},
          {"role": "user", "content": "用简单的话解释什么是机器学习"}
        ]
      }
      """;

    HttpRequest request = HttpRequest.newBuilder()
        .uri(URI.create("__DOCS_API_ORIGIN__/v1/chat/completions"))
        .header("Content-Type", "application/json")
        .header("Authorization", "Bearer " + System.getenv("CLAWDROUTER_API_KEY"))
        .POST(HttpRequest.BodyPublishers.ofString(body))
        .build();

    HttpResponse<String> response = HttpClient.newHttpClient()
        .send(request, HttpResponse.BodyHandlers.ofString());

    System.out.println(response.body());
  }
}

PHP

<?php
$payload = [
    "model" => "gpt-4o",
    "messages" => [
        ["role" => "system", "content" => "你是一个有用的助手"],
        ["role" => "user", "content" => "用简单的话解释什么是机器学习"],
    ],
];

$ch = curl_init("__DOCS_API_ORIGIN__/v1/chat/completions");
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        "Content-Type: application/json",
        "Authorization: Bearer " . getenv("CLAWDROUTER_API_KEY"),
    ],
    CURLOPT_POSTFIELDS => json_encode($payload, JSON_UNESCAPED_UNICODE),
]);

$response = curl_exec($ch);
curl_close($ch);

echo $response . PHP_EOL;

Ruby

require "json"
require "net/http"
require "uri"

uri = URI("__DOCS_API_ORIGIN__/v1/chat/completions")
request = Net::HTTP::Post.new(uri)
request["Content-Type"] = "application/json"
request["Authorization"] = "Bearer #{ENV.fetch('CLAWDROUTER_API_KEY')}"
request.body = {
  model: "gpt-4o",
  messages: [
    { role: "system", content: "你是一个有用的助手" },
    { role: "user", content: "用简单的话解释什么是机器学习" },
  ],
}.to_json

response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
  http.request(request)
end

puts response.body

C#

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

using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization =
    new AuthenticationHeaderValue("Bearer", Environment.GetEnvironmentVariable("CLAWDROUTER_API_KEY"));

var json = """
{
  "model": "gpt-4o",
  "messages": [
    {"role": "system", "content": "你是一个有用的助手"},
    {"role": "user", "content": "用简单的话解释什么是机器学习"}
  ]
}
""";

var response = await client.PostAsync(
    "__DOCS_API_ORIGIN__/v1/chat/completions",
    new StringContent(json, Encoding.UTF8, "application/json")
);

Console.WriteLine(await response.Content.ReadAsStringAsync());

成功后，非流式响应会返回 choices[].message.content；如果需要完整字段说明，请查看 Chat Completions API 参考。

流式输出

流式输出适合聊天界面、长文本生成和需要更快首字响应的场景。请求体中设置 stream: true 即可。

cURL

curl __DOCS_API_ORIGIN__/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CLAWDROUTER_API_KEY" \
  -N \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "写一篇关于人工智能的短文"}
    ],
    "stream": true
  }'

-N 会关闭 cURL 输出缓冲，让内容实时显示。

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["CLAWDROUTER_API_KEY"],
    base_url="__DOCS_API_ORIGIN__/v1",
)

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "user", "content": "写一篇关于人工智能的短文"},
    ],
    stream=True,
)

for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CLAWDROUTER_API_KEY,
  baseURL: "__DOCS_API_ORIGIN__/v1",
});

const stream = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "写一篇关于人工智能的短文" }],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) {
    process.stdout.write(content);
  }
}

Go

package main

import (
	"bufio"
	"bytes"
	"fmt"
	"net/http"
	"os"
)

func main() {
	body := []byte(`{
	  "model": "gpt-4o",
	  "messages": [
	    {"role": "user", "content": "写一篇关于人工智能的短文"}
	  ],
	  "stream": true
	}`)

	req, _ := http.NewRequest(
		"POST",
		"__DOCS_API_ORIGIN__/v1/chat/completions",
		bytes.NewReader(body),
	)
	req.Header.Set("Content-Type", "application/json")
	req.Header.Set("Authorization", "Bearer "+os.Getenv("CLAWDROUTER_API_KEY"))

	resp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()

	scanner := bufio.NewScanner(resp.Body)
	for scanner.Scan() {
		fmt.Println(scanner.Text())
	}
}

Java

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
  public static void main(String[] args) throws Exception {
    String body = """
      {
        "model": "gpt-4o",
        "messages": [
          {"role": "user", "content": "写一篇关于人工智能的短文"}
        ],
        "stream": true
      }
      """;

    HttpRequest request = HttpRequest.newBuilder()
        .uri(URI.create("__DOCS_API_ORIGIN__/v1/chat/completions"))
        .header("Content-Type", "application/json")
        .header("Authorization", "Bearer " + System.getenv("CLAWDROUTER_API_KEY"))
        .POST(HttpRequest.BodyPublishers.ofString(body))
        .build();

    HttpClient.newHttpClient()
        .send(request, HttpResponse.BodyHandlers.ofLines())
        .body()
        .forEach(System.out::println);
  }
}

PHP

<?php
$payload = [
    "model" => "gpt-4o",
    "messages" => [
        ["role" => "user", "content" => "写一篇关于人工智能的短文"],
    ],
    "stream" => true,
];

$ch = curl_init("__DOCS_API_ORIGIN__/v1/chat/completions");
curl_setopt_array($ch, [
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        "Content-Type: application/json",
        "Authorization: Bearer " . getenv("CLAWDROUTER_API_KEY"),
    ],
    CURLOPT_POSTFIELDS => json_encode($payload, JSON_UNESCAPED_UNICODE),
    CURLOPT_WRITEFUNCTION => function ($ch, $chunk) {
        echo $chunk;
        flush();
        return strlen($chunk);
    },
]);

curl_exec($ch);
curl_close($ch);

Ruby

require "json"
require "net/http"
require "uri"

uri = URI("__DOCS_API_ORIGIN__/v1/chat/completions")
request = Net::HTTP::Post.new(uri)
request["Content-Type"] = "application/json"
request["Authorization"] = "Bearer #{ENV.fetch('CLAWDROUTER_API_KEY')}"
request.body = {
  model: "gpt-4o",
  messages: [
    { role: "user", content: "写一篇关于人工智能的短文" },
  ],
  stream: true,
}.to_json

Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
  http.request(request) do |response|
    response.read_body do |chunk|
      print chunk
    end
  end
end

C#

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

using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization =
    new AuthenticationHeaderValue("Bearer", Environment.GetEnvironmentVariable("CLAWDROUTER_API_KEY"));

var json = """
{
  "model": "gpt-4o",
  "messages": [
    {"role": "user", "content": "写一篇关于人工智能的短文"}
  ],
  "stream": true
}
""";

using var request = new HttpRequestMessage(HttpMethod.Post, "__DOCS_API_ORIGIN__/v1/chat/completions") {
    Content = new StringContent(json, Encoding.UTF8, "application/json")
};

using var response = await client.SendAsync(request, HttpCompletionOption.ResponseHeadersRead);
await using var stream = await response.Content.ReadAsStreamAsync();
using var reader = new StreamReader(stream);

while (!reader.EndOfStream) {
    Console.WriteLine(await reader.ReadLineAsync());
}

调用 Veo 视频生成

视频生成是异步任务。提交成功后会返回 task_id，请到控制台任务中心下载生成结果。

cURL

curl __DOCS_API_ORIGIN__/v1/video/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CLAWDROUTER_API_KEY" \
  -d '{
    "model": "veo-3.1-fast-generate-001",
    "prompt": "A cute small bird dancing on a tree branch, moving rhythmically to cheerful music. The bird gently sways its body, lightly flaps its wings, and playfully tilts its head. Bright forest background with soft sunlight and subtle shadows. Semi-realistic, slightly cartoon style, vivid but not over-saturated colors. Static camera, centered subject, smooth motion, medium detail. 720p resolution, clear and stable output.",
    "duration": 4,
    "metadata": {
      "durationSeconds": 4,
      "aspectRatio": "16:9",
      "resolution": "720p",
      "negativePrompt": "low quality, blurry, distorted",
      "personGeneration": "allow_adult",
      "generateAudio": true
    }
  }'

Python

import os
import requests

response = requests.post(
    "__DOCS_API_ORIGIN__/v1/video/generations",
    headers={
        "Authorization": f"Bearer {os.environ['CLAWDROUTER_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "model": "veo-3.1-fast-generate-001",
        "prompt": "A cute small bird dancing on a tree branch, moving rhythmically to cheerful music. The bird gently sways its body, lightly flaps its wings, and playfully tilts its head. Bright forest background with soft sunlight and subtle shadows. Semi-realistic, slightly cartoon style, vivid but not over-saturated colors. Static camera, centered subject, smooth motion, medium detail. 720p resolution, clear and stable output.",
        "duration": 4,
        "metadata": {
            "durationSeconds": 4,
            "aspectRatio": "16:9",
            "resolution": "720p",
            "negativePrompt": "low quality, blurry, distorted",
            "personGeneration": "allow_adult",
            "generateAudio": True,
        },
    },
)

print(response.json())

Node.js

const response = await fetch("__DOCS_API_ORIGIN__/v1/video/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.CLAWDROUTER_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "veo-3.1-fast-generate-001",
    prompt:
      "A cute small bird dancing on a tree branch, moving rhythmically to cheerful music. The bird gently sways its body, lightly flaps its wings, and playfully tilts its head. Bright forest background with soft sunlight and subtle shadows. Semi-realistic, slightly cartoon style, vivid but not over-saturated colors. Static camera, centered subject, smooth motion, medium detail. 720p resolution, clear and stable output.",
    duration: 4,
    metadata: {
      durationSeconds: 4,
      aspectRatio: "16:9",
      resolution: "720p",
      negativePrompt: "low quality, blurry, distorted",
      personGeneration: "allow_adult",
      generateAudio: true,
    },
  }),
});

console.log(await response.json());

Go

package main

import (
	"bytes"
	"fmt"
	"io"
	"net/http"
	"os"
)

func main() {
	body := []byte(`{
	  "model": "veo-3.1-fast-generate-001",
	  "prompt": "A cute small bird dancing on a tree branch, moving rhythmically to cheerful music. The bird gently sways its body, lightly flaps its wings, and playfully tilts its head. Bright forest background with soft sunlight and subtle shadows. Semi-realistic, slightly cartoon style, vivid but not over-saturated colors. Static camera, centered subject, smooth motion, medium detail. 720p resolution, clear and stable output.",
	  "duration": 4,
	  "metadata": {
	    "durationSeconds": 4,
	    "aspectRatio": "16:9",
	    "resolution": "720p",
	    "negativePrompt": "low quality, blurry, distorted",
	    "personGeneration": "allow_adult",
	    "generateAudio": true
	  }
	}`)

	req, _ := http.NewRequest(
		"POST",
		"__DOCS_API_ORIGIN__/v1/video/generations",
		bytes.NewReader(body),
	)
	req.Header.Set("Content-Type", "application/json")
	req.Header.Set("Authorization", "Bearer "+os.Getenv("CLAWDROUTER_API_KEY"))

	resp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()

	data, _ := io.ReadAll(resp.Body)
	fmt.Println(string(data))
}

Java

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
  public static void main(String[] args) throws Exception {
    String body = """
      {
        "model": "veo-3.1-fast-generate-001",
        "prompt": "A cute small bird dancing on a tree branch, moving rhythmically to cheerful music. The bird gently sways its body, lightly flaps its wings, and playfully tilts its head. Bright forest background with soft sunlight and subtle shadows. Semi-realistic, slightly cartoon style, vivid but not over-saturated colors. Static camera, centered subject, smooth motion, medium detail. 720p resolution, clear and stable output.",
        "duration": 4,
        "metadata": {
          "durationSeconds": 4,
          "aspectRatio": "16:9",
          "resolution": "720p",
          "negativePrompt": "low quality, blurry, distorted",
          "personGeneration": "allow_adult",
          "generateAudio": true
        }
      }
      """;

    HttpRequest request = HttpRequest.newBuilder()
        .uri(URI.create("__DOCS_API_ORIGIN__/v1/video/generations"))
        .header("Content-Type", "application/json")
        .header("Authorization", "Bearer " + System.getenv("CLAWDROUTER_API_KEY"))
        .POST(HttpRequest.BodyPublishers.ofString(body))
        .build();

    HttpResponse<String> response = HttpClient.newHttpClient()
        .send(request, HttpResponse.BodyHandlers.ofString());

    System.out.println(response.body());
  }
}

PHP

<?php
$payload = [
    "model" => "veo-3.1-fast-generate-001",
    "prompt" => "A cute small bird dancing on a tree branch, moving rhythmically to cheerful music. The bird gently sways its body, lightly flaps its wings, and playfully tilts its head. Bright forest background with soft sunlight and subtle shadows. Semi-realistic, slightly cartoon style, vivid but not over-saturated colors. Static camera, centered subject, smooth motion, medium detail. 720p resolution, clear and stable output.",
    "duration" => 4,
    "metadata" => [
        "durationSeconds" => 4,
        "aspectRatio" => "16:9",
        "resolution" => "720p",
        "negativePrompt" => "low quality, blurry, distorted",
        "personGeneration" => "allow_adult",
        "generateAudio" => true,
    ],
];

$ch = curl_init("__DOCS_API_ORIGIN__/v1/video/generations");
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        "Content-Type: application/json",
        "Authorization: Bearer " . getenv("CLAWDROUTER_API_KEY"),
    ],
    CURLOPT_POSTFIELDS => json_encode($payload, JSON_UNESCAPED_UNICODE),
]);

$response = curl_exec($ch);
curl_close($ch);

echo $response . PHP_EOL;

Ruby

require "json"
require "net/http"
require "uri"

uri = URI("__DOCS_API_ORIGIN__/v1/video/generations")
request = Net::HTTP::Post.new(uri)
request["Content-Type"] = "application/json"
request["Authorization"] = "Bearer #{ENV.fetch('CLAWDROUTER_API_KEY')}"
request.body = {
  model: "veo-3.1-fast-generate-001",
  prompt: "A cute small bird dancing on a tree branch, moving rhythmically to cheerful music. The bird gently sways its body, lightly flaps its wings, and playfully tilts its head. Bright forest background with soft sunlight and subtle shadows. Semi-realistic, slightly cartoon style, vivid but not over-saturated colors. Static camera, centered subject, smooth motion, medium detail. 720p resolution, clear and stable output.",
  duration: 4,
  metadata: {
    durationSeconds: 4,
    aspectRatio: "16:9",
    resolution: "720p",
    negativePrompt: "low quality, blurry, distorted",
    personGeneration: "allow_adult",
    generateAudio: true,
  },
}.to_json

response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
  http.request(request)
end

puts response.body

C#

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

using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization =
    new AuthenticationHeaderValue("Bearer", Environment.GetEnvironmentVariable("CLAWDROUTER_API_KEY"));

var json = """
{
  "model": "veo-3.1-fast-generate-001",
  "prompt": "A cute small bird dancing on a tree branch, moving rhythmically to cheerful music. The bird gently sways its body, lightly flaps its wings, and playfully tilts its head. Bright forest background with soft sunlight and subtle shadows. Semi-realistic, slightly cartoon style, vivid but not over-saturated colors. Static camera, centered subject, smooth motion, medium detail. 720p resolution, clear and stable output.",
  "duration": 4,
  "metadata": {
    "durationSeconds": 4,
    "aspectRatio": "16:9",
    "resolution": "720p",
    "negativePrompt": "low quality, blurry, distorted",
    "personGeneration": "allow_adult",
    "generateAudio": true
  }
}
""";

var response = await client.PostAsync(
    "__DOCS_API_ORIGIN__/v1/video/generations",
    new StringContent(json, Encoding.UTF8, "application/json")
);

Console.WriteLine(await response.Content.ReadAsStringAsync());

典型受理响应：

{
  "id": "task_MrvezeP3uOim5bWo8texognLwHHHVgpB",
  "task_id": "task_MrvezeP3uOim5bWo8texognLwHHHVgpB",
  "object": "video",
  "model": "veo-3.1-fast-generate-001",
  "status": "queued",
  "progress": 0,
  "created_at": 1779265222
}

调用 Anthropic 原生协议

如果你需要直接使用 Anthropic Messages 协议，请调用 /v1/messages。该协议使用 x-api-key 认证头，而不是 Authorization: Bearer。

cURL

curl __DOCS_API_ORIGIN__/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $CLAWDROUTER_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "用简单的话解释什么是机器学习"}
    ]
  }'

Python

import os
import anthropic

client = anthropic.Anthropic(
    api_key=os.environ["CLAWDROUTER_API_KEY"],
    base_url="__DOCS_API_ORIGIN__",
)

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "用简单的话解释什么是机器学习"},
    ],
)

print(message.content[0].text)

Node.js

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

const client = new Anthropic({
  apiKey: process.env.CLAWDROUTER_API_KEY,
  baseURL: "__DOCS_API_ORIGIN__",
});

const message = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 1024,
  messages: [
    { role: "user", content: "用简单的话解释什么是机器学习" },
  ],
});

console.log(message.content[0].text);

Go

package main

import (
	"bytes"
	"fmt"
	"io"
	"net/http"
	"os"
)

func main() {
	body := []byte(`{
	  "model": "claude-sonnet-4-6",
	  "max_tokens": 1024,
	  "messages": [
	    {"role": "user", "content": "用简单的话解释什么是机器学习"}
	  ]
	}`)

	req, _ := http.NewRequest(
		"POST",
		"__DOCS_API_ORIGIN__/v1/messages",
		bytes.NewReader(body),
	)
	req.Header.Set("Content-Type", "application/json")
	req.Header.Set("x-api-key", os.Getenv("CLAWDROUTER_API_KEY"))
	req.Header.Set("anthropic-version", "2023-06-01")

	resp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()

	data, _ := io.ReadAll(resp.Body)
	fmt.Println(string(data))
}

Java

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
  public static void main(String[] args) throws Exception {
    String body = """
      {
        "model": "claude-sonnet-4-6",
        "max_tokens": 1024,
        "messages": [
          {"role": "user", "content": "用简单的话解释什么是机器学习"}
        ]
      }
      """;

    HttpRequest request = HttpRequest.newBuilder()
        .uri(URI.create("__DOCS_API_ORIGIN__/v1/messages"))
        .header("Content-Type", "application/json")
        .header("x-api-key", System.getenv("CLAWDROUTER_API_KEY"))
        .header("anthropic-version", "2023-06-01")
        .POST(HttpRequest.BodyPublishers.ofString(body))
        .build();

    HttpResponse<String> response = HttpClient.newHttpClient()
        .send(request, HttpResponse.BodyHandlers.ofString());

    System.out.println(response.body());
  }
}

PHP

<?php
$payload = [
    "model" => "claude-sonnet-4-6",
    "max_tokens" => 1024,
    "messages" => [
        ["role" => "user", "content" => "用简单的话解释什么是机器学习"],
    ],
];

$ch = curl_init("__DOCS_API_ORIGIN__/v1/messages");
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        "Content-Type: application/json",
        "x-api-key: " . getenv("CLAWDROUTER_API_KEY"),
        "anthropic-version: 2023-06-01",
    ],
    CURLOPT_POSTFIELDS => json_encode($payload, JSON_UNESCAPED_UNICODE),
]);

$response = curl_exec($ch);
curl_close($ch);

echo $response . PHP_EOL;

Ruby

require "json"
require "net/http"
require "uri"

uri = URI("__DOCS_API_ORIGIN__/v1/messages")
request = Net::HTTP::Post.new(uri)
request["Content-Type"] = "application/json"
request["x-api-key"] = ENV.fetch("CLAWDROUTER_API_KEY")
request["anthropic-version"] = "2023-06-01"
request.body = {
  model: "claude-sonnet-4-6",
  max_tokens: 1024,
  messages: [
    { role: "user", content: "用简单的话解释什么是机器学习" },
  ],
}.to_json

response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
  http.request(request)
end

puts response.body

C#

using System.Text;

using var client = new HttpClient();
client.DefaultRequestHeaders.Add("x-api-key", Environment.GetEnvironmentVariable("CLAWDROUTER_API_KEY"));
client.DefaultRequestHeaders.Add("anthropic-version", "2023-06-01");

var json = """
{
  "model": "claude-sonnet-4-6",
  "max_tokens": 1024,
  "messages": [
    {"role": "user", "content": "用简单的话解释什么是机器学习"}
  ]
}
""";

var response = await client.PostAsync(
    "__DOCS_API_ORIGIN__/v1/messages",
    new StringContent(json, Encoding.UTF8, "application/json")
);

Console.WriteLine(await response.Content.ReadAsStringAsync());

常见配置

配置	推荐值	说明
OpenAI-compatible Base URL	__DOCS_API_ORIGIN__/v1	OpenAI SDK、Chat Completions、Responses、Images API 使用
Anthropic Base URL	__DOCS_API_ORIGIN__	Anthropic SDK 和 Messages API 使用
认证头	Authorization: Bearer YOUR_API_KEY	OpenAI-compatible 接口使用
Anthropic 认证头	x-api-key: YOUR_API_KEY	Anthropic 原生协议使用
Content-Type	application/json	所有 JSON 请求都需要
Request-Id	自定义唯一字符串	可选，用于业务侧幂等和排查

错误处理建议

• 401 通常表示 API Key 无效、缺失或被禁用。
• 429 通常表示请求频率或额度达到限制，可以稍后重试或调整并发。
• 5xx 通常表示平台或上游模型服务异常，建议保留 request_id 后重试或提交工单。
• 视频生成返回 queued 只代表任务已受理，不代表视频已经完成。

下一步

• 快速开始 - 查看完整接入流程
• 认证鉴权 - 了解 API Key 和请求头
• OpenAI 聊天补全 - 查看完整参数说明
• Veo 视频生成 - 查看视频生成字段和使用技巧