Chat Completions API

获取 API Key

前往 API 密钥页面创建你的 API 密钥。

API Base URL

https://tokenoff.com/api

OpenAI 系列模型支持 /v1/chat/completions 接口，兼容 OpenAI Chat Completions API。

curl

阻塞调用

curl https://tokenoff.com/api/v1/chat/completions \
  -H "Authorization: Bearer your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "gpt-5.4",
      "messages": [
          {"role": "user", "content": "Hello"}
      ]
  }'

输出内容如下:

{"id":"resp_07cc003c4736c70b0069e0c1e41c2c8196952f2f53524e1891","object":"chat.completion","created":1776337380,"model":"gpt-4.1","choices":[{"index":0,"message":{"role":"assistant","content":"Hello! How can I help you today?"},"finish_reason":"stop"}],"usage":{"prompt_tokens":7,"completion_tokens":13,"total_tokens":20}}

流式响应

curl https://tokenoff.com/api/v1/chat/completions \
  -H "Authorization: Bearer your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "gpt-5.4",
      "messages": [
          {"role": "user", "content": "Hello"}
      ],
      "stream": true
  }'

输出内容如下:

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":" How"},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":" can"},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":" I"},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":" help"},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":" you"},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":" today"},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{"content":"?"},"finish_reason":null}]}

data: {"id":"resp_01570884e7e6265a0069e0c260ed9c8194bd120e896b171efb","object":"chat.completion.chunk","created":1776337504,"model":"gpt-4.1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":7,"completion_tokens":13,"total_tokens":20}}

data: [DONE]

Python

pip install openai

阻塞调用

from openai import OpenAI

client = OpenAI(
  api_key="your_api_key_here",
  base_url="https://tokenoff.com/api/v1",
)

response = client.chat.completions.create(
  model="gpt-5.4",
  messages=[
      {"role": "user", "content": "Hello"}
  ],
)

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

输出内容如下:

Hello! How can I help?

流式响应

from openai import OpenAI

client = OpenAI(
  api_key="your_api_key_here",
  base_url="https://tokenoff.com/api/v1",
)

response = client.chat.completions.create(
  model="gpt-5.4",
  messages=[
      {"role": "user", "content": "Hello"}
  ],
  stream=True,
)

for event in response:
  print(event)

输出内容如下:

ChatCompletionChunk(id='resp_02f00b38518533fd0069e0c3f104fc819484590784cd3b0aa7', choices=[Choice(delta=ChoiceDelta(content='', function_call=None, refusal=None, role='assistant', tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776337905, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_02f00b38518533fd0069e0c3f104fc819484590784cd3b0aa7', choices=[Choice(delta=ChoiceDelta(content='Hello', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776337905, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_02f00b38518533fd0069e0c3f104fc819484590784cd3b0aa7', choices=[Choice(delta=ChoiceDelta(content='!', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776337905, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_02f00b38518533fd0069e0c3f104fc819484590784cd3b0aa7', choices=[Choice(delta=ChoiceDelta(content=' How', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776337905, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_02f00b38518533fd0069e0c3f104fc819484590784cd3b0aa7', choices=[Choice(delta=ChoiceDelta(content=' can', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776337905, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_02f00b38518533fd0069e0c3f104fc819484590784cd3b0aa7', choices=[Choice(delta=ChoiceDelta(content=' I', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776337905, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_02f00b38518533fd0069e0c3f104fc819484590784cd3b0aa7', choices=[Choice(delta=ChoiceDelta(content=' help', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776337905, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_02f00b38518533fd0069e0c3f104fc819484590784cd3b0aa7', choices=[Choice(delta=ChoiceDelta(content='?', function_call=None, refusal=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1776337905, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='resp_02f00b38518533fd0069e0c3f104fc819484590784cd3b0aa7', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role=None, tool_calls=None), finish_reason='stop', index=0, logprobs=None)], created=1776337905, model='gpt-4.1', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=11, prompt_tokens=7, total_tokens=18, completion_tokens_details=None, prompt_tokens_details=None))

TypeScript

npm install openai

阻塞调用

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your_api_key_here",
  baseURL: "https://tokenoff.com/api/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [
      { role: "user", content: "Hello" },
  ],
});

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

输出内容如下:

Hello! How can I help you today?

流式响应

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your_api_key_here",
  baseURL: "https://tokenoff.com/api/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [
      { role: "user", content: "Hello" },
  ],
  stream: true,
});

for await (const event of response) {
console.log(event);
}

输出内容如下:

{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: [Object], finish_reason: null } ]
}
{
  id: 'resp_09288c4e32022db60069e0c4918cec819699f22a80c5900655',
  object: 'chat.completion.chunk',
  created: 1776338065,
  model: 'gpt-4.1',
  choices: [ { index: 0, delta: {}, finish_reason: 'stop' } ],
  usage: { prompt_tokens: 7, completion_tokens: 13, total_tokens: 20 }
}

支持的模型

联系我们

如果在使用 TokenOff 过程中遇到任何问题：

通过邮箱support@tokenoff.com等官方渠道联系我们的技术支持团队
在我们的Github仓库提交 Issue

TokenOff

Chat Completions API

获取 API Key

API Base URL

curl

阻塞调用

流式响应

Python

阻塞调用

流式响应

TypeScript

阻塞调用

流式响应

支持的模型

gpt-5.4

gpt-5.4-mini

gpt-5.4-nano

gpt-5.2

gpt-5.1

gpt-5

gpt-5-mini

gpt-5-nano

gpt-4.1

gpt-4.1-mini

gpt-4.1-nano

gpt-4o

gpt-4o-mini

o4-mini

o3

o3-mini

o3-pro

gpt-5.3-codex

gpt-5.3-codex-spark

gpt-5.2-codex

gpt-5.1-codex-max

gpt-5.1-codex

gpt-5-codex

gpt-5.1-codex-mini

联系我们

目录