バリアント · Google / Gemini

Gemini gemini-3-flash-preview 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/gemini -g

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

Or paste this prompt to your AI agent:

Install the Gemini skill for me:

1. Clone https://github.com/runapi-ai/gemini
2. Copy the skills/gemini/ 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

gemini-2.5-flash gemini-2.5-pro gemini-3-pro-preview gemini-3.1-pro-preview gemini-3.5-flash

概要

Gemini gemini-3-flash-preview 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

Chat completion

Input $0.25 / 1M tokens

Output $1.50 / 1M tokens

Generate content stream

Input $0.25 / 1M tokens

Output $1.50 / 1M tokens

仕様

Model ID	gemini-3-flash-preview
プロバイダー	Google
モダリティ	text
Task type	synchronous
課金	1K tokens
Endpoint	/v1/chat/completions
Commercial	Yes
Status	Operational

クイックスタート

Quickstart — gemini-3-flash-preview

runapi.ai

curl -X POST https://runapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-3-flash-preview",
  "messages": [
    {
      "role": "user",
      "content": "Analyze this codebase and suggest three performance improvements with before/after examples."
    }
  ]
}'

import { GeminiClient } from "@runapi.ai/gemini";

const client = new GeminiClient();
const result = await client.chatCompletion.run({
    model: "gemini-3-flash-preview",
    messages: [{"role":"user","content":"Analyze this codebase and suggest three performance improvements with before/after examples."}],
});

require "runapi/gemini"

client = RunApi::Gemini::Client.new
result = client.chat_completion.run(
    model: "gemini-3-flash-preview",
    messages: [{role: "user", content: "Analyze this codebase and suggest three performance improvements with before/after examples."}]
)

@runapi.ai/gemini v1

仕組み