Responses API

NUWA 兼容 OpenAI 的 Responses API，保持与官方一致的参数与返回格式。只需替换 api_key 与 base_url 即可在国内直连，获得多模态、推理、搜索等完整能力。

能力概览

Text / Image input：支持文本或图文混合输入
Streaming：支持流式增量返回
Web search & Deep research：实时搜索与深度研究
Reasoning 深度：minimal / low / medium / high，minimal 仅 gpt-5 系列支持
Verbosity 控制：gpt-5 系列支持 low / medium / high
工具：函数调用、image_generation、code_interpreter、mcp、Computer Use

快速开始

与官方 OpenAI SDK 的调用方式相同，只需替换 api_key 与 base_url。

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",  # 换成你在 NUWA 生成的密钥
    base_url="https://api.nuwaapi.com/v1"
)

response = client.responses.create(
    model="gpt-4o-mini",
    input="Hello NUWA"
)

print(response)

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-4o-mini",
    input: "Hello NUWA"
  })
});

const data = await response.json();
console.log(JSON.stringify(data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-4o-mini",
    input: "Hello NUWA"
  });

  console.log(JSON.stringify(response, null, 2));
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-4o-mini",
    "input": "Hello NUWA"
  }'

提示

关于模型摘要：默认关闭，可按 disabled > auto > None 配置，auto 为兼顾成本与效果的选项。
gpt-5-chat 若未传入 reasoning_effort，等同于不启用推理，可获得更快响应。
深度研究模型建议使用 o1-deep-research、o1-mini-deep-research，仅支持 responses 端口。
gpt-5 系列默认锁定过程一致性输出，不再使用传统 temperature、top_p 干预。
o 系列 / gpt-5 系列不再使用 max_tokens，请在 responses 端使用 max_output_tokens 控制上限。

功能示例

gpt-5 系列

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1"
)

response = client.responses.create(
    model="gpt-5",  # gpt-5, gpt-5-chat-latest, gpt-5-mini, gpt-5-nano
    input="塔罗占卜为何有效，背后的原理和可迁移的方法是什么？Output format: Markdown",
    reasoning={"effort": "minimal"},
    text={"verbosity": "low"},
    stream=True
)

for event in response:
    print(event)

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-5",
    input: "塔罗占卜为何有效，背后的原理和可迁移的方法是什么？Output format: Markdown",
    reasoning: { effort: "minimal" },
    text: { verbosity: "low" }
  })
});

const data = await response.json();
console.log(JSON.stringify(data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-5",
    input: "塔罗占卜为何有效，背后的原理和可迁移的方法是什么？Output format: Markdown",
    reasoning: { effort: "minimal" },
    text: { verbosity: "low" },
    stream: true
  });

  for await (const event of response) {
    console.log(JSON.stringify(event, null, 2));
  }
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-5",
    "input": "塔罗占卜为何有效，背后的原理和可迁移的方法是什么？Output format: Markdown",
    "reasoning": {"effort": "minimal"},
    "text": {"verbosity": "low"},
    "stream": true
  }'

文本

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1"
)

response = client.responses.create(
    model="gpt-4o-mini",  # codex-mini-latest 也可用
    input="Tell me a three sentence bedtime story about a unicorn."
)

print(response)

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-4o-mini",
    input: "Tell me a three sentence bedtime story about a unicorn."
  })
});

const data = await response.json();
console.log(JSON.stringify(data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-4o-mini",
    input: "Tell me a three sentence bedtime story about a unicorn."
  });

  console.log(JSON.stringify(response, null, 2));
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-4o-mini",
    "input": "Tell me a three sentence bedtime story about a unicorn."
  }'

图文

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1"
)

response = client.responses.create(
    model="gpt-4o-mini",
    input=[
        {
            "role": "user",
            "content": [
                {"type": "input_text", "text": "what is in this image?"},
                {"type": "input_image", "image_url": "https://picsum.photos/400/300"}
            ]
        }
    ]
)

print(response)

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-4o-mini",
    input: [
      {
        role: "user",
        content: [
          { type: "input_text", text: "what is in this image?" },
          { type: "input_image", image_url: "https://picsum.photos/400/300" }
        ]
      }
    ]
  })
});

const data = await response.json();
console.log(JSON.stringify(data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-4o-mini",
    input: [
      {
        role: "user",
        content: [
          { type: "input_text", text: "what is in this image?" },
          { type: "input_image", image_url: "https://picsum.photos/400/300" }
        ]
      }
    ]
  });

  console.log(JSON.stringify(response, null, 2));
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-4o-mini",
    "input": [
      {
        "role": "user",
        "content": [
          {"type": "input_text", "text": "what is in this image?"},
          {"type": "input_image", "image_url": "https://picsum.photos/400/300"}
        ]
      }
    ]
  }'

流式

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1"
)

response = client.responses.create(
    model="gpt-4o-mini",
    instructions="You are a helpful assistant.",
    input="Hello!",
    stream=True
)

for event in response:
    print(event)

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-4o-mini",
    instructions: "You are a helpful assistant.",
    input: "Hello!",
    stream: true
  })
});

const text = await response.text();
console.log(text);

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-4o-mini",
    instructions: "You are a helpful assistant.",
    input: "Hello!",
    stream: true
  });

  for await (const event of response) {
    console.log(JSON.stringify(event, null, 2));
  }
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-4o-mini",
    "instructions": "You are a helpful assistant.",
    "input": "Hello!",
    "stream": true
  }'

搜索

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1"
)

response = client.responses.create(
    model="gpt-4o-mini",  # codex-mini-latest 不支持搜索
    tools=[{"type": "web_search_preview"}],
    input="What was a positive news story from today?"
)

print(response)

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-4o-mini",
    tools: [{ type: "web_search_preview" }],
    input: "What was a positive news story from today?"
  })
});

const data = await response.json();
console.log(JSON.stringify(data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-4o-mini",
    tools: [{ type: "web_search_preview" }] as any,
    input: "What was a positive news story from today?"
  });

  console.log(JSON.stringify(response, null, 2));
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-4o-mini",
    "tools": [{"type": "web_search_preview"}],
    "input": "What was a positive news story from today?"
  }'

Deep Research

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1",
    timeout=3600,
)

input_text = """
Research the economic impact of semaglutide on global healthcare systems.
Do:
- Include specific figures, trends, statistics, and measurable outcomes.
- Prioritize reliable, up-to-date sources: peer-reviewed research, health
  organizations (e.g., WHO, CDC), regulatory agencies, or pharmaceutical
  earnings reports.
- Include inline citations and return all source metadata.

Be analytical, avoid generalities, and ensure that each section supports
data-backed reasoning that could inform healthcare policy or financial modeling.
"""

response = client.responses.create(
    model="o1-deep-research",
    input=input_text,
    tools=[
        {"type": "web_search_preview"},
        {"type": "code_interpreter", "container": {"type": "auto"}},
    ],
)

print(response.output_text)

const inputText = `
Research the economic impact of semaglutide on global healthcare systems.
Do:
- Include specific figures, trends, statistics, and measurable outcomes.
- Prioritize reliable, up-to-date sources: peer-reviewed research, health
  organizations (e.g., WHO, CDC), regulatory agencies, or pharmaceutical
  earnings reports.
- Include inline citations and return all source metadata.

Be analytical, avoid generalities, and ensure that each section supports
data-backed reasoning that could inform healthcare policy or financial modeling.
`;

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "o1-deep-research",
    input: inputText,
    tools: [
      { type: "web_search_preview" },
      { type: "code_interpreter", container: { type: "auto" } }
    ]
  }),
  signal: AbortSignal.timeout(3600000)
});

const data = await response.json();
console.log(data.output_text ?? JSON.stringify(data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1",
  timeout: 3600000
});

const inputText = `
Research the economic impact of semaglutide on global healthcare systems.
Do:
- Include specific figures, trends, statistics, and measurable outcomes.
- Prioritize reliable, up-to-date sources: peer-reviewed research, health
  organizations (e.g., WHO, CDC), regulatory agencies, or pharmaceutical
  earnings reports.
- Include inline citations and return all source metadata.

Be analytical, avoid generalities, and ensure that each section supports
data-backed reasoning that could inform healthcare policy or financial modeling.
`;

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "o1-deep-research",
    input: inputText,
    tools: [
      { type: "web_search_preview" },
      { type: "code_interpreter", container: { type: "auto" } }
    ] as any
  });

  console.log((response as any).output_text);
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "o1-deep-research",
    "input": "Research the economic impact of semaglutide on global healthcare systems.\nDo:\n- Include specific figures, trends, statistics, and measurable outcomes.\n- Prioritize reliable, up-to-date sources: peer-reviewed research, health organizations (e.g., WHO, CDC), regulatory agencies, or pharmaceutical earnings reports.\n- Include inline citations and return all source metadata.\n\nBe analytical, avoid generalities, and ensure that each section supports data-backed reasoning that could inform healthcare policy or financial modeling.",
    "tools": [
      {"type": "web_search_preview"},
      {"type": "code_interpreter", "container": {"type": "auto"}}
    ]
  }'

推理

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1",
)

response = client.responses.create(
    model="o4-mini",  # 支持 codex-mini-latest, o4-mini, o3-mini, o3, o1
    input="How much wood would a woodchuck chuck?",
    reasoning={
        "effort": "medium",  # low / medium / high
        "summary": "auto",
    },
)

print(response)

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "o4-mini",
    input: "How much wood would a woodchuck chuck?",
    reasoning: {
      effort: "medium",
      summary: "auto"
    }
  })
});

const data = await response.json();
console.log(JSON.stringify(data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "o4-mini",
    input: "How much wood would a woodchuck chuck?",
    reasoning: {
      effort: "medium",
      summary: "auto"
    } as any
  });

  console.log(JSON.stringify(response, null, 2));
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "o4-mini",
    "input": "How much wood would a woodchuck chuck?",
    "reasoning": {
      "effort": "medium",
      "summary": "auto"
    }
  }'

函数调用

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1",
)

tools = [
    {
        "type": "function",
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                },
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location", "unit"],
        },
    }
]

response = client.responses.create(
    model="gpt-4o-mini",
    tools=tools,
    input="What is the weather like in Boston today?",
    tool_choice="auto",
)

print(response)

const tools = [{
  type: "function",
  name: "get_current_weather",
  description: "Get the current weather in a given location",
  parameters: {
    type: "object",
    properties: {
      location: { type: "string", description: "The city and state, e.g. San Francisco, CA" },
      unit: { type: "string", enum: ["celsius", "fahrenheit"] }
    },
    required: ["location", "unit"]
  }
}];

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-4o-mini",
    input: "What is the weather like in Boston today?",
    tool_choice: "auto",
    tools
  })
});

const data = await response.json();
console.log(JSON.stringify(data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

const tools = [{
  type: "function",
  name: "get_current_weather",
  description: "Get the current weather in a given location",
  parameters: {
    type: "object",
    properties: {
      location: { type: "string", description: "The city and state, e.g. San Francisco, CA" },
      unit: { type: "string", enum: ["celsius", "fahrenheit"] }
    },
    required: ["location", "unit"]
  }
}];

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-4o-mini",
    input: "What is the weather like in Boston today?",
    tool_choice: "auto",
    tools: tools as any
  });

  console.log(JSON.stringify(response, null, 2));
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-4o-mini",
    "input": "What is the weather like in Boston today?",
    "tool_choice": "auto",
    "tools": [{
      "type": "function",
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"},
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
        },
        "required": ["location", "unit"]
      }
    }]
  }'

图像生成工具

Python
JavaScript
TypeScript
Curl

from openai import OpenAI
import base64

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1",
)

response = client.responses.create(
    model="gpt-4.1-mini",
    input="Generate an image of gray tabby cat hugging an otter with an orange scarf",
    tools=[
        {
            "type": "image_generation",
            "background": "opaque",
            "quality": "high",
        }
    ],
)

image_data = [
    output.result
    for output in response.output
    if output.type == "image_generation_call"
]

if image_data:
    with open("cat_and_otter.png", "wb") as f:
        f.write(base64.b64decode(image_data[0]))

const fs = require("fs");

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-4.1-mini",
    input: "Generate an image of gray tabby cat hugging an otter with an orange scarf",
    tools: [
      {
        type: "image_generation",
        background: "opaque",
        quality: "high"
      }
    ]
  })
});

const data = await response.json();
const call = (data.output ?? []).find(item => item.type === "image_generation_call");
if (call?.result) {
  fs.writeFileSync("cat_and_otter.png", Buffer.from(call.result, "base64"));
  console.log("✅ 图片已保存为 cat_and_otter.png");
} else {
  console.log(JSON.stringify(data, null, 2));
}

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-4.1-mini",
    input: "Generate an image of gray tabby cat hugging an otter with an orange scarf",
    tools: [
      {
        type: "image_generation",
        background: "opaque",
        quality: "high"
      }
    ] as any
  });

  const output = (response as any).output ?? [];
  const call = output.find((item: any) => item.type === "image_generation_call");
  if (call?.result) {
    fs.writeFileSync("cat_and_otter.png", Buffer.from(call.result, "base64"));
    console.log("✅ 图片已保存为 cat_and_otter.png");
  } else {
    console.log(JSON.stringify(response, null, 2));
  }
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-4.1-mini",
    "input": "Generate an image of gray tabby cat hugging an otter with an orange scarf",
    "tools": [{
      "type": "image_generation",
      "background": "opaque",
      "quality": "high"
    }]
  }' -o response.json

python -c "
import json, base64
with open('response.json', 'r', encoding='utf-8') as f:
    data = json.load(f)
items = data.get('output', [])
call = next((x for x in items if x.get('type') == 'image_generation_call'), None)
if call and call.get('result'):
    with open('cat_and_otter.png', 'wb') as out:
        out.write(base64.b64decode(call['result']))
    print('✅ 图片已保存为 cat_and_otter.png')
else:
    print(json.dumps(data, ensure_ascii=False, indent=2))
"

代码解析器

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1",
)

instructions = """
You are a personal math tutor. When asked a math question,
write and run code using the python tool to answer the question.
"""

response = client.responses.create(
    model="gpt-4.1",
    tools=[
        {
            "type": "code_interpreter",
            "container": {"type": "auto"}
        }
    ],
    instructions=instructions,
    input="I need to solve the equation 3x + 11 = 14. Can you help me?",
)

print(response.output)

const instructions = `
You are a personal math tutor. When asked a math question,
write and run code using the python tool to answer the question.
`;

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-4.1",
    tools: [{ type: "code_interpreter", container: { type: "auto" } }],
    instructions,
    input: "I need to solve the equation 3x + 11 = 14. Can you help me?"
  })
});

const data = await response.json();
console.log(JSON.stringify(data.output ?? data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

const instructions = `
You are a personal math tutor. When asked a math question,
write and run code using the python tool to answer the question.
`;

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-4.1",
    tools: [{ type: "code_interpreter", container: { type: "auto" } }] as any,
    instructions,
    input: "I need to solve the equation 3x + 11 = 14. Can you help me?"
  });

  console.log(JSON.stringify((response as any).output, null, 2));
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-4.1",
    "instructions": "You are a personal math tutor. When asked a math question, write and run code using the python tool to answer the question.",
    "input": "I need to solve the equation 3x + 11 = 14. Can you help me?",
    "tools": [{
      "type": "code_interpreter",
      "container": {"type": "auto"}
    }]
  }'

MCP 调用

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1",
)

response = client.responses.create(
    model="gpt-4.1",
    tools=[{
        "type": "mcp",
        "server_label": "deepwiki",
        "server_url": "https://mcp.deepwiki.com/mcp",
        "require_approval": "never",
        "allowed_tools": ["ask_question"],
    }],
    input="What transport protocols does the 2025-03-26 version of the MCP spec (modelcontextprotocol/modelcontextprotocol) support?",
)

print(response.output_text)

const response = await fetch("https://api.nuwaapi.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "sk-***"
  },
  body: JSON.stringify({
    model: "gpt-4.1",
    input: "What transport protocols does the 2025-03-26 version of the MCP spec (modelcontextprotocol/modelcontextprotocol) support?",
    tools: [{
      type: "mcp",
      server_label: "deepwiki",
      server_url: "https://mcp.deepwiki.com/mcp",
      require_approval: "never",
      allowed_tools: ["ask_question"]
    }]
  })
});

const data = await response.json();
console.log(data.output_text ?? JSON.stringify(data, null, 2));

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.responses.create({
    model: "gpt-4.1",
    tools: [{
      type: "mcp",
      server_label: "deepwiki",
      server_url: "https://mcp.deepwiki.com/mcp",
      require_approval: "never",
      allowed_tools: ["ask_question"]
    }] as any,
    input: "What transport protocols does the 2025-03-26 version of the MCP spec (modelcontextprotocol/modelcontextprotocol) support?"
  });

  console.log((response as any).output_text);
}

main().catch(console.error);

curl https://api.nuwaapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: sk-***" \
  -d '{
    "model": "gpt-4.1",
    "input": "What transport protocols does the 2025-03-26 version of the MCP spec (modelcontextprotocol/modelcontextprotocol) support?",
    "tools": [{
      "type": "mcp",
      "server_label": "deepwiki",
      "server_url": "https://mcp.deepwiki.com/mcp",
      "require_approval": "never",
      "allowed_tools": ["ask_question"]
    }]
  }'

已知限制

codex-mir-latest 不支持搜索
Computer Use 需要配合 Playwright，参考官方仓库
截图任务耗时较长时成功率会降低
CAPTCHA / Cloudflare 验证可能触发循环校验

能力概览​

快速开始​

功能示例​

gpt-5 系列​

文本​

图文​

流式​

搜索​

Deep Research​

推理​

函数调用​

图像生成工具​

代码解析器​

MCP 调用​

已知限制​

能力概览

快速开始

功能示例

gpt-5 系列

文本

图文

流式

搜索

Deep Research

推理

函数调用

图像生成工具

代码解析器

MCP 调用

已知限制