变体 · Google / Gemini

Gemini gemini-3.5-flash API

同一套 API，同一个 SDK — 切换变体只需改一个参数。

运行中 · text · 可商用

# 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.

切换变体

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

概览

gemini-3.5-flash 在 Gemini 家族中处于质量与成本的最佳平衡点。

USD 按次定价
失败不计费
模型支持时流式
Schema 校验后的工具调用

定价

失败的生成不计费

Generate content stream

Input $0.75 / 1M tokens

Output $4.50 / 1M tokens

规格

技术细节

模型 ID	gemini-3.5-flash
提供方	Google
模态	text
任务类型	synchronous
计费单位	1K tokens
API 端点	/v1beta/models/gemini-3.5-flash:streamGenerateContent
商用许可	允许商用
状态	运行中

快速开始

Quickstart — gemini-3.5-flash

runapi.ai

curl -X POST https://runapi.ai/v1beta/models/gemini-3.5-flash:streamGenerateContent \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-3.5-flash",
  "contents": [
    {
      "parts": [
        {
          "text": "分析这段代码库，给出三项性能优化建议，包含优化前后的对比示例。"
        }
      ]
    }
  ]
}'

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

const client = new GeminiClient();
const result = await client.streamGenerateContent.run({
    model: "gemini-3.5-flash",
    contents: [{"parts":[{"text":"分析这段代码库，给出三项性能优化建议，包含优化前后的对比示例。"}]}],
});

require "runapi/gemini"

client = RunApi::Gemini::Client.new
result = client.stream_generate_content.run(
    model: "gemini-3.5-flash",
    contents: [{parts: [{text: "分析这段代码库，给出三项性能优化建议，包含优化前后的对比示例。"}]}]
)

@runapi.ai/gemini v1

工作流程