Seedance 2.0 | Special Offer ✦ 10% OFF NOW
openai
openai/gpt-5.4

openai/gpt-5.4

1,050,000 context · $2.50/M input tokens · $15.00/M output tokens

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.

定价

按量付费

无需预付费用,仅按实际使用量付费

输入
272K $2.50 / M Tokens
> 272K $5.00 / M Tokens
输出
272K $15.00 / M Tokens
> 272K $22.50 / M Tokens

API 使用

使用以下代码示例接入我们的 API:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

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

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

模型介绍

Openai gpt-5.4

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input,

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.


Why It Looks Great

  • Large Language Model architecture for efficient processing
  • 1050000 context window for long document handling
  • Competitive pricing at $2.5/$15.0 per million tokens

Key Features

  • Context Window: 1050000 tokens
  • Max Output: 128000 tokens
  • Vision: Supported
  • Function Calling: Supported

Specifications

SpecificationValue
ProviderOpenai
Model TypeLarge Language Model (LLM)
ArchitectureN/A
Context Window1050000 tokens
Max Output128000 tokens
InputText
OutputText
VisionSupported
Function CallingSupported

Pricing

Token TypeCost per Million Tokens
Input$2.5
Output$15.0

How to Use

  1. Write your prompt — describe the task, provide context, and specify desired output format.
  2. Submit — the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: openai/gpt-5.4


API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

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

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

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

  • Model: openai/gpt-5.4
  • Provider: Openai

信息

提供商openai
类型llm

支持功能

输入
文本图像
输出
文本
上下文1,050,000
最大输出128,000
视觉✓ 支持
函数调用✓ 支持

API 访问指南

Base URLhttps://llm.wavespeed.ai/v1
API 端点chat/completions
Model IDopenai/gpt-5.4

GPT 5.4 API

openai/gpt-5.4

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.

输入

$2.5 /M

输出

$15 /M

上下文

1050K

最大输出

128K

Vision

支持

工具调用

支持

在 WaveSpeedAI 试用 GPT 5.4

通过我们的统一 API 接入 GPT 5.4 — 兼容 OpenAI、无冷启动、透明计费。

打开 Playground

关于 GPT 5.4 的常见问题

GPT 5.4 API 多少钱?+

WaveSpeedAI 定价:输入每百万 token $2.50,输出每百万 token $15.00。Prompt 缓存和批处理单独计费,可显著降低长上下文、高重复任务的实际成本。

GPT 5.4 的上下文窗口是多大?+

GPT 5.4 单次请求最多支持 1050K 上下文 token,输出最多 128K token。

GPT 5.4 是否兼容 OpenAI?+

是的。WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容端点提供 GPT 5.4。把官方 OpenAI SDK 的 base URL 指向该地址,使用 WaveSpeedAI 的 API Key 即可,无需任何其他代码改动。

如何开始使用 GPT 5.4?+

登录 WaveSpeedAI,在 Access Keys 中生成 API Key,使用上方显示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 发送请求。新账户可获得免费额度,用于试用 GPT 5.4。

相关 LLM API