GPT API
OpenAI's flagship LLM for chat, code generation, and multi-step reasoning tasks.
# Base URL
https://runapi.ai
# Endpoints
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages
POST /v1beta/models/{model}:generateContent
POST /v1beta/models/{model}:streamGenerateContent
curl https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-terra",
"messages": [
{
"role": "user",
"content": "Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."
}
]
}'
from openai import OpenAI
client = OpenAI(
base_url="https://runapi.ai/v1",
api_key="your-runapi-key"
)
response = client.chat.completions.create(
model="gpt-5.6-terra",
messages=[{"role": "user", "content": "Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."}]
)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://runapi.ai/v1",
apiKey: "your-runapi-key"
});
const response = await client.chat.completions.create({
model: "gpt-5.6-terra",
messages: [{ role: "user", content: "Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations." }]
});
GPT is OpenAI's flagship large language model series, with the GPT-5 family delivering state-of-the-art performance in chat, code generation, and multi-step reasoning. Available in multiple capability tiers.
- 多個變體,對應不同速度/品質層級
- Model skill 包含文件、schema 與 setup 備註
- 支援 app-focused coding workflows
- 生成失敗不收費
比較所有 API 變體
| Variant | Billing | From | |
|---|---|---|---|
| codex-auto-review | 1K tokens | $0.150 | 查看 → |
| gpt-5.2 | 1K tokens | $0.070 | 查看 → |
| gpt-5.2-pro | 1K tokens | $0.840 | 查看 → |
| gpt-5.3-codex | 1K tokens | $0.070 | 查看 → |
| gpt-5.3-codex-spark | 1K tokens | $0.070 | 查看 → |
| gpt-5.4 | 1K tokens | $0.120 | 查看 → |
| gpt-5.4-mini | 1K tokens | $0.030 | 查看 → |
| gpt-5.4-nano | 1K tokens | $0.010 | 查看 → |
| gpt-5.4-pro | 1K tokens | $1.35 | 查看 → |
| gpt-5.5 | 1K tokens | $0.230 | 查看 → |
| gpt-5.5-pro | 1K tokens | $1.35 | 查看 → |
| gpt-5.6-luna | 1K tokens | $0.050 | 查看 → |
| gpt-5.6-sol | 1K tokens | $0.230 | 查看 → |
| gpt-5.6-terra | 1K tokens | $0.120 | 查看 → |
GPT API 端點
使用 OpenAI 或 Anthropic SDK 搭配 RunAPI key 呼叫,不需額外 SDK。
| Endpoint | Protocol |
|---|---|
| /v1/chat/completions | OpenAI compatible |
| /v1/responses | OpenAI Responses |
| /v1/messages | Anthropic compatible |
| /v1beta/models/{model}:generateContent | Gemini generateContent |
| /v1beta/models/{model}:streamGenerateContent | Gemini streamGenerateContent |
從 model skill 到第一次結果,只需四步
選擇模型
挑選符合輸出類型、品質門檻與延遲目標的模型與變體。
設定
設定 RunAPI key,並在 coding workspace 安裝 model skill。
開發
使用 skill 指引,在你的 app 內加入模型功能。
接收
透過 task ID 查詢、在支援時串流,或處理 webhook callback。
GPT API 是甚麼?
GPT is OpenAI's frontier LLM family, spanning standard and mini variants for different cost-performance trade-offs. Through RunAPI, all GPT models share the same API shape and billing.
為何透過 RunAPI 使用 GPT API
一個驗證,對應所有 provider
一組 RunAPI key 即可解鎖整個 catalog。無需分開帳戶,亦無需為每個整合輪換密鑰。
統一定價與計費
按次以 USD 收費,每月結算。失敗的生成不會收費。
內含 schema 的 skill
型別化 schema 與 setup 備註打包在 model skill 內,讓實作從正確契約開始。
常見問題
Which GPT variant should I choose?
GPT-5.6 — the sol, terra, and luna tiers — is the current flagship generation. GPT-5.4 remains a strong choice for coding and agentic workflows, GPT-5.5 for long-horizon autonomous tasks, and GPT-5.4-mini is the cost-effective option for simpler tasks.
Does GPT support tool use and function calling?
Yes — all GPT-5 variants support structured function calling with JSON schemas, enabling agentic tool-use workflows.
What is Thinking mode?
Thinking mode lets GPT reason step-by-step before responding. Available on GPT-5.2 and above, it improves accuracy on complex reasoning tasks.
What is the context window size?
Context windows vary by variant. GPT-5.4 and above support large context windows suitable for multi-file code analysis and long documents.
What is GPT-5.3 Codex optimized for?
Codex is specialized for multi-file code generation, editing, and analysis — purpose-built for developer workflows and CI/CD integration.
我應該先用邊個版本?
先選最平而且符合你質素要求的版本。大多數團隊會先用快速版本,之後再升級到 pro 用於正式生產。
有免費方案嗎?
新帳戶可獲得每個模型的首次呼叫免費。之後按次收費。
你哋支援串流結果嗎?
如有提供串流,RunAPI 會端到端串流。
失敗會點樣收費?
生成失敗不會收費。
輸出有快取嗎?
已生成輸出會儲存,並可按任務 ID 取回。輸入內容不會快取。
可以商業使用嗎?
可以——除非模型授權明確限制,否則每個版本都包括商業使用。相關限制會在版本頁面列明。
限流點樣計?
每個密鑰的限流會跟使用等級而提升。最新限制請參考定價頁。
可以在邊度報告問題?
可以在公開 GitHub repo 開 issue,或者電郵支援。