GPT-5.4 MiniAPI
OpenAI GPT-5.4 Mini — fast, cost-efficient reasoning.
输入价格
$0.225
per 1M tokens
输出价格
$1.35
per 1M tokens
Prompt 缓存
给稳定 prefix 加 cache_control，命中按 input 价的一小部分计费。cache_write 按 input 原价计费。
按 input × 0.2 自动派生
参数
- 模型 ID
gpt-5-4-mini- 端点
POST /v1/chat/completions- 类别
- Text
- 供应商
- OpenAI
- 能力
- functionstreamingthinking
无缝兼容 OpenAI SDK
把 OpenAI SDK 的 base_url 指向 api.kunavo.com/v1，换 model id 即可。流式、工具调用、SDK 行为完全一致。
查看文档GPT API 定价指南立即试用
在 /app/keys 创建 API key，复制为 KUNAVO_API_KEY，然后任选下面一段代码运行。
curl https://api.kunavo.com/v1/chat/completions \
-H "Authorization: Bearer $KUNAVO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5-4-mini",
"messages": [
{"role": "user", "content": "Hello, GPT-5.4 Mini"}
],
"stream": false
}'FAQ
How much does GPT-5.4 Mini cost?
On Kunavo, GPT-5.4 Mini is $0.225 per 1M input tokens and $1.35 per 1M output tokens — about 70% under OpenAI's official price. Failed requests are never billed, and it's pay-as-you-go — you only pay for successful calls.
Can I call GPT-5.4 Mini with the OpenAI SDK?
Yes. Set base_url to https://api.kunavo.com/v1, pass your Kunavo key, and set model to "gpt-5-4-mini". Requests and responses are OpenAI-compatible.
What endpoint does GPT-5.4 Mini use?
GPT-5.4 Mini is called via POST /v1/chat/completions on Kunavo's OpenAI-compatible API.
What is GPT-5.4 Mini good for?
GPT-5.4 Mini is a text model from OpenAI, with support for function, streaming, thinking.