MonkeyAI API 脚本：文本、视觉与图片

准备密钥与运行环境

在 注册 或 登录 后，前往 密钥管理 创建适合接口的分组密钥。将密钥放在运行脚本的环境变量中；不要写进代码、浏览器或提交记录。运行脚本会产生请求与潜在费用。

Python 3 安装 python3 -m pip install openai anthropic；Node.js 使用支持当前 SDK 的 LTS 版本，安装 npm install openai @anthropic-ai/sdk。请使用官方 SDK 软件包。

bash
export MONKEYAI_API_KEY="YOUR_API_KEY"
powershell
$env:MONKEYAI_API_KEY="YOUR_API_KEY"

协议与分组选择

协议稳定路径本文模型
ResponsesPOST /v1/responsesgpt-6.1-sol
Chat CompletionsPOST /v1/chat/completionsgpt-6.1-sol
MessagesPOST /v1/messagesclaude-opus-4-8

OpenAI SDK 的 base 是 https://monkeytheme.com/v1；Anthropic SDK 的 base 是 https://monkeytheme.com，由 SDK 拼接 /v1/messages。不要重复拼接 /v1。

模型列表列有上述模型。外接脚本选择 Codex Pro（外接版）、GPT 官方直连或允许外接的 Claude 分组；“仅限Codex”“仅限CC”分组不能按通用脚本使用。模型出现在广场不等于任意密钥都可访问，也不能据此认定所有视觉、工具或协议特性均已验证。Gemini 原生路由为 /v1beta/，不能仅靠更换模型名把原生请求改成这三种格式。

Python：三种协议的文本、视觉与流式

保存为 api_demo.py。三个参数依次选择协议、输入和传输方式，例如 python3 api_demo.py responses text plain。把 text 改为 vision 时，先在当前目录放置自己的静态 input.png；把 plain 改为 stream 使用流式处理。三个协议均有文本和视觉分支。它们展示协议结构，所选分组的视觉兼容性仍需实际验证。

python
import base64
import os
import sys
from pathlib import Path
from openai import OpenAI, APIError
from anthropic import Anthropic, APIError as AnthropicError

# python api_demo.py responses|chat|messages text|vision plain|stream
protocol, mode, delivery = sys.argv[1:]
if protocol not in {"responses", "chat", "messages"}:
    raise ValueError("Unknown protocol")
if mode not in {"text", "vision"} or delivery not in {"plain", "stream"}:
    raise ValueError("Invalid mode or delivery")
streaming = delivery == "stream"
key = os.environ["MONKEYAI_API_KEY"]
image = None
if mode == "vision":
    image = base64.b64encode(Path("input.png").read_bytes()).decode("ascii")
try:
    if protocol == "messages":
        client = Anthropic(api_key=key, base_url="https://monkeytheme.com",
                           timeout=120.0, max_retries=0)
        content = [{"type": "text", "text": "Describe the visible evidence."}]
        if image:
            content.append({"type": "image", "source": {"type": "base64",
                "media_type": "image/png", "data": image}})
        args = dict(model="claude-opus-4-8", max_tokens=600,
                    messages=[{"role": "user", "content": content}])
        if streaming:
            with client.messages.stream(**args) as events:
                for text in events.text_stream:
                    print(text, end="", flush=True)
                final = events.get_final_message()
                print("\nusage:", final.usage)
        else:
            result = client.messages.create(**args)
            for block in result.content:
                if block.type == "text":
                    print(block.text)
            print("usage:", result.usage)
    else:
        client = OpenAI(api_key=key, base_url="https://monkeytheme.com/v1",
                        timeout=120.0, max_retries=0)
        if protocol == "responses":
            content = [{"type": "input_text", "text": "Describe the visible evidence."}]
            if image:
                content.append({"type": "input_image",
                    "image_url": "data:image/png;base64," + image})
            result = client.responses.create(model="gpt-6.1-sol",
                input=[{"role": "user", "content": content}], stream=streaming)
            if streaming:
                with result as events:
                    for event in events:
                        if event.type == "response.output_text.delta":
                            print(event.delta, end="", flush=True)
                        elif event.type in {"error", "response.failed", "response.incomplete"}:
                            raise RuntimeError(str(event))
                        elif event.type == "response.completed":
                            print("\nusage:", event.response.usage)
            else:
                print(result.output_text)
                print("usage:", result.usage)
        else:
            content = [{"type": "text", "text": "Describe the visible evidence."}]
            if image:
                content.append({"type": "image_url", "image_url": {
                    "url": "data:image/png;base64," + image}})
            result = client.chat.completions.create(model="gpt-6.1-sol",
                messages=[{"role": "user", "content": content}], stream=streaming)
            if streaming:
                with result as chunks:
                    for chunk in chunks:
                        if chunk.choices:
                            print(chunk.choices[0].delta.content or "", end="", flush=True)
            else:
                print(result.choices[0].message.content)
                print("usage:", result.usage)
except (APIError, AnthropicError, OSError, RuntimeError) as error:
    print("Request failed:", error, file=sys.stderr)
    sys.exit(1)

Node.js：同样的六类输入与两种传输

保存为 api_demo.mjs，运行方式如 node api_demo.mjs messages vision stream。不要将 SSE 当成一个完整 JSON 文档解析。SDK 负责事件边界，应用只拼接文本增量。

javascript
import fs from "node:fs/promises";
import OpenAI from "openai";
import Anthropic from "@anthropic-ai/sdk";

// node api_demo.mjs responses|chat|messages text|vision plain|stream
try {
  const [protocol, mode, delivery] = process.argv.slice(2);
  if (!["responses", "chat", "messages"].includes(protocol) ||
      !["text", "vision"].includes(mode) || !["plain", "stream"].includes(delivery)) {
    throw new Error("Invalid protocol, mode or delivery");
  }
  const apiKey = process.env.MONKEYAI_API_KEY;
  if (!apiKey) throw new Error("Set MONKEYAI_API_KEY");
  const stream = delivery === "stream";
  const image = mode === "vision" ? (await fs.readFile("input.png")).toString("base64") : null;
  if (protocol === "messages") {
    const client = new Anthropic({apiKey, baseURL: "https://monkeytheme.com",
      timeout: 120000, maxRetries: 0});
    const content = [{type: "text", text: "Describe the visible evidence."}];
    if (image) content.push({type: "image", source: {
      type: "base64", media_type: "image/png", data: image}});
    const args = {model: "claude-opus-4-8", max_tokens: 600,
      messages: [{role: "user", content}]};
    if (stream) {
      const events = client.messages.stream(args);
      for await (const event of events) {
        if (event.type === "content_block_delta" && event.delta.type === "text_delta")
          process.stdout.write(event.delta.text);
      }
      console.log("\nusage:", (await events.finalMessage()).usage);
    } else {
      const result = await client.messages.create(args);
      for (const block of result.content) if (block.type === "text") console.log(block.text);
      console.log("usage:", result.usage);
    }
  } else {
    const client = new OpenAI({apiKey, baseURL: "https://monkeytheme.com/v1",
      timeout: 120000, maxRetries: 0});
    if (protocol === "responses") {
      const content = [{type: "input_text", text: "Describe the visible evidence."}];
      if (image) content.push({type: "input_image", image_url: `data:image/png;base64,${image}`});
      const result = await client.responses.create({model: "gpt-6.1-sol",
        input: [{role: "user", content}], stream});
      if (stream) {
        for await (const event of result) {
          if (event.type === "response.output_text.delta") process.stdout.write(event.delta);
          if (["error", "response.failed", "response.incomplete"].includes(event.type))
            throw new Error(JSON.stringify(event));
          if (event.type === "response.completed") console.log("\nusage:", event.response.usage);
        }
      } else { console.log(result.output_text); console.log("usage:", result.usage); }
    } else {
      const content = [{type: "text", text: "Describe the visible evidence."}];
      if (image) content.push({type: "image_url", image_url: {url: `data:image/png;base64,${image}`}});
      const result = await client.chat.completions.create({model: "gpt-6.1-sol",
        messages: [{role: "user", content}], stream});
      if (stream) {
        for await (const chunk of result) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
      } else { console.log(result.choices[0].message.content); console.log("usage:", result.usage); }
    }
  }
} catch (error) {
  console.error("Request failed:", error.status ?? "", error.message);
  process.exitCode = 1;
}

流式完成与用量

Responses 只读取 response.output_text.delta 文本；完成事件可提供 usage，失败或不完整事件必须保留为失败状态。Messages 只拼接文本块，结束后读取最终消息。Chat 的首个块或 usage 块可能没有 choices，delta 也可能为空；上例已跳过空值。Chat 流不保证提供 usage；确认分组支持后可请求 stream_options: {include_usage: true} 并读取最终 usage 块，否则以后台用量记录对账。

连接中断后的部分文本不能当作完整成功结果。生产程序应记录完成状态、停止原因和可用请求 ID；需要提前停止时关闭流。示例没有调用工具；若启用工具调用，还需累积并校验工具参数，不能把它们当作普通文本。不要对已经生成部分内容的请求盲目重试，重复调用可能重复收费。

图片生成与编辑

模型列表列有 gpt-image-2，Codex Pro（外接版）与 ChatGPT 生图分组包含它；Codex Lite 不在该生图列表中。下面分别使用稳定路径 /v1/images/generations 和 /v1/images/edits，编辑由 SDK 发送 multipart 文件。模型列名不是编辑、遮罩、尺寸或返回格式已在当前渠道验证的证据；这些兼容性待验证。示例要求 Base64 返回，遇到仅 URL 返回会明确报错，不自动下载未知地址。

Python 保存为 image_demo.py，Node.js 保存为 image_demo.mjs，参数为 generate 或 edit。编辑需自备 input.png。输出会覆盖当前目录的 output.png，请先保留已有文件。这里没有视频示例：当前证据不能保证 MonkeyAI 视频生成可用。

python
import base64
import os
import sys
from pathlib import Path
from openai import OpenAI, APIError

# python image_demo.py generate|edit
try:
    client = OpenAI(api_key=os.environ["MONKEYAI_API_KEY"],
        base_url="https://monkeytheme.com/v1", timeout=180.0, max_retries=0)
    mode = sys.argv[1]
    if mode == "generate":
        result = client.images.generate(model="gpt-image-2",
            prompt="A paper sculpture of a mountain, plain background", n=1)
    elif mode == "edit":
        with open("input.png", "rb") as image:
            result = client.images.edit(model="gpt-image-2", image=image,
                prompt="Change the background to pale blue; preserve the subject", n=1)
    else:
        raise ValueError("Use generate or edit")
    if not result.data or not result.data[0].b64_json:
        raise RuntimeError("No Base64 image returned; inspect the response format safely")
    Path("output.png").write_bytes(base64.b64decode(result.data[0].b64_json, validate=True))
    print("Saved output.png")
except (APIError, OSError, ValueError, RuntimeError) as error:
    print("Image request failed:", error, file=sys.stderr)
    sys.exit(1)
javascript
import fs from "node:fs";
import OpenAI from "openai";

try {
  if (!process.env.MONKEYAI_API_KEY) throw new Error("Set MONKEYAI_API_KEY");
  const client = new OpenAI({apiKey: process.env.MONKEYAI_API_KEY,
    baseURL: "https://monkeytheme.com/v1", timeout: 180000, maxRetries: 0});
  const mode = process.argv[2];
  let result;
  if (mode === "generate") {
    result = await client.images.generate({model: "gpt-image-2",
      prompt: "A paper sculpture of a mountain, plain background", n: 1});
  } else if (mode === "edit") {
    result = await client.images.edit({model: "gpt-image-2", image: fs.createReadStream("input.png"),
      prompt: "Change the background to pale blue; preserve the subject", n: 1});
  } else throw new Error("Use generate or edit");
  if (!result.data?.[0]?.b64_json) throw new Error("No Base64 image returned; inspect response format safely");
  fs.writeFileSync("output.png", Buffer.from(result.data[0].b64_json, "base64"));
  console.log("Saved output.png");
} catch (error) {
  console.error("Image request failed:", error.status ?? "", error.message);
  process.exitCode = 1;
}

大文件输入

模型不会自动读取本地路径。先在本地提取 PDF/办公文件中的文字；扫描件需要 OCR。Python 用 Path("document.txt").read_text(encoding="utf-8")，Node.js 用 await fs.readFile("document.txt", "utf8") 取得正文，再替换示例文本块中的 text。不要把整个二进制文件放进 text。文件上传、file ID、远程 URL 自动抓取与 PDF 原生输入在这些分组上尚未验证，不能假定 /v1/files 可用。按段落拆分超长输入，保留段落 ID，再汇总分段结果；图片 Base64 增大会同时影响请求体与输入预算。本站确切文件、图片和上下文限制需按模型/渠道确认。

费用与排错

以 实时价格 和账户用量为准。文本输入、输出、缓存及图片的计费方式可能不同，分组倍率和长上下文规则也可能影响费用。不要将每图价格当成文本单价，或把无 usage 的流式响应当成免费。

现象处理
401 / 403检查环境变量、密钥有效性、余额及分组客户端限制；不要打印 Authorization
404 / model_not_found核对完整模型 ID、协议路径和密钥分组；不要随意追加 /v1
400 / 422检查协议专用内容块、图片 MIME 类型及可选参数；逐项减少不兼容选项
413 / 上下文超限缩小图片、提取文本、分段；字符数不是 Token 数
429 / 503降低并发，尊重 Retry-After，设置有上限的指数退避
超时 / 中断检查代理与网络，标记部分结果；确认计费状态再决定是否重试
图片输出为空核对生图分组、返回格式和权限；不要伪造图片或成功结果

错误可能包含用户输入，记录前应脱敏。示例禁用 SDK 自动重试，避免教程隐式多次请求；HTTP 错误、网络异常及流内错误都需要处理。确切 SDK 版本兼容、实时通道和端到端视觉/编辑效果需按所选渠道确认。