バリアント · OpenAI / GPT

GPT gpt-5.3-codex-spark API

A model variant exposed through RunAPI's unified AI API.

Operational · text · Commercial use supported

# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/gpt -g

The -g flag installs globally so every project picks it up.

Or paste this prompt to your AI agent:

Install the GPT skill for me:

1. Clone https://github.com/runapi-ai/gpt
2. Copy the skills/gpt/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.

Switch variant

codex-auto-review gpt-5.2 gpt-5.2-pro gpt-5.3-codex gpt-5.4 gpt-5.4-mini gpt-5.4-nano gpt-5.4-pro gpt-5.5 gpt-5.5-pro

概要

GPT gpt-5.3-codex-spark is available through the same RunAPI auth, SDKs, and agent skill workflow.

Unified endpoint
SDK snippets
Agent install path
失敗した生成は課金されません

料金

失敗した生成は課金されません

Responses API

Input $0.38 / 1M tokens

Output $2.25 / 1M tokens

Cache read $0.04

Chat completion

Input $0.38 / 1M tokens

Output $2.25 / 1M tokens

Cache read $0.04

仕様

Model ID	gpt-5.3-codex-spark
プロバイダー	OpenAI
モダリティ	text
Task type	synchronous
課金	1K tokens
Endpoint	/v1/responses
Commercial	Yes
Status	Operational

クイックスタート

Quickstart — gpt-5.3-codex-spark

runapi.ai

curl -X POST https://runapi.ai/v1/responses \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-5.3-codex-spark",
  "messages": [
    {
      "role": "user",
      "content": "Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."
    }
  ]
}'

import { GptClient } from "@runapi.ai/gpt";

const client = new GptClient();
const result = await client.response.run({
    model: "gpt-5.3-codex-spark",
    messages: [{"role":"user","content":"Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."}],
});

require "runapi/gpt"

client = RunApi::Gpt::Client.new
result = client.response.run(
    model: "gpt-5.3-codex-spark",
    messages: [{role: "user", content: "Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."}]
)

@runapi.ai/gpt v1

仕組み