[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [Gemini 3 Flash Preview](https://spiral.ai/integrations/chatgpt/gemini-3-flash-preview)

# How to Use Gemini 3 Flash Preview in ChatGPT

Gemini 3 Flash Preview suits everyday coding, document analysis, and planning when response speed matters. Built on Gemini 3 Pro’s reasoning foundation, it lets you trade reasoning depth for faster responses.

|  |  |
| --- | --- |
| Model | Gemini 3 Flash Preview |
| Available through | Vertex AI |
| Category | LLM |
| Price | Up to $0.01602 per run at the default inputs. $0.65 per 1M input tokens, $0.065 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $1.30 per 1M audio input tokens, $3.90 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Gemini 3 Flash Preview in ChatGPT

- Use Gemini 3 Flash Preview to summarize the meeting notes above in under 250 words. Separate decisions, action items, and open questions; mark missing owners and dates as unknown.
- Use Gemini 3 Flash Preview to compare the two policy texts above. Return a table of changed obligations, deadlines, and exceptions, with a supporting passage for each change.
- Use Gemini 3 Flash Preview with high thinking to turn the requirements above into a launch plan. Order the work by dependency and list the evidence needed to finish each step.
- Use Gemini 3 Flash Preview with minimal thinking to sort the customer messages above into bug, feature request, billing question, or other. Include one supporting excerpt per message.
- Use Gemini 3 Flash Preview to answer my questions using only the reference text above. Quote the supporting passage for each answer and say when the text does not provide an answer.

## How to set up Gemini 3 Flash Preview in ChatGPT

Pick the way that suits you. Each takes about two minutes.

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Gemini 3 Flash Preview**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "vertex",
    "model": "google/gemini-3-flash-preview",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds Gemini 3 Flash Preview on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/chatgpt

## Gemini 3 Flash Preview tools and prices

- [Gemini 3 Flash Preview](https://spiral.ai/tools/vertex/google/gemini-3-flash-preview) (Vertex AI): Up to $0.01602 per run at the default inputs. $0.65 per 1M input tokens, $0.065 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $1.30 per 1M audio input tokens, $3.90 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 65536 | — | The most output tokens to generate. |

## What can you do with Gemini 3 Flash Preview in ChatGPT?

Turn pasted notes, reference text, and requirements into comparisons, answers, and practical plans with Gemini 3 Flash Preview. Ask for supporting passages and a defined response length to make the result easier to check.

### Debug a failing test

Give Gemini 3 Flash Preview the failure output and relevant code. Ask for a reproducible cause, a focused patch, and a regression test.

### Review a code change

Ask Gemini 3 Flash Preview to inspect a diff for behavioral bugs and explain each finding with the triggering input and affected code.

### Compare long documents

Provide two policy texts and ask Gemini 3 Flash Preview to identify changed obligations, deadlines, and exceptions with supporting passages.

### Extract action items

Turn meeting notes into a record of decisions, owners, and due dates. Ask Gemini 3 Flash Preview to mark any unstated owner or deadline as unknown.

### Sort support requests

Give Gemini 3 Flash Preview defined categories and request one category plus a supporting excerpt for each request.

### Plan a software migration

Use Gemini 3 Flash Preview to turn requirements and constraints into an ordered migration plan with dependencies, checks, and rollback conditions.

### Answer questions from reference text

Supply product documentation and ask Gemini 3 Flash Preview to answer with supporting passages and identify questions the text does not resolve.

### Build a playable prototype

Ask Gemini 3 Flash Preview to turn explicit game rules into a small browser prototype with a clear win condition and keyboard controls.

## Overview

- [Google Vertex AI](https://spiral.ai/providers/vertex)
- [All ChatGPT guides](https://spiral.ai/integrations/chatgpt)

## Gemini 3 Flash Preview in other agents

- [Amp](https://spiral.ai/integrations/amp/gemini-3-flash-preview)
- [Claude](https://spiral.ai/integrations/claude-desktop/gemini-3-flash-preview)
- [Claude Code](https://spiral.ai/integrations/claude-code/gemini-3-flash-preview)
- [Cline](https://spiral.ai/integrations/cline/gemini-3-flash-preview)
- [Codex](https://spiral.ai/integrations/codex/gemini-3-flash-preview)
- [Cursor](https://spiral.ai/integrations/cursor/gemini-3-flash-preview)
- [Devin](https://spiral.ai/integrations/devin/gemini-3-flash-preview)
- [dots](https://spiral.ai/integrations/dots/gemini-3-flash-preview)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gemini-3-flash-preview)
- [Gemini](https://spiral.ai/integrations/gemini/gemini-3-flash-preview)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gemini-3-flash-preview)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gemini-3-flash-preview)
- [goose](https://spiral.ai/integrations/goose/gemini-3-flash-preview)
- [Grok](https://spiral.ai/integrations/grok/gemini-3-flash-preview)
- [Grok Build](https://spiral.ai/integrations/grok-build/gemini-3-flash-preview)
- [Hermes](https://spiral.ai/integrations/hermes/gemini-3-flash-preview)
- [Instinct](https://spiral.ai/integrations/instinct/gemini-3-flash-preview)
- [Manus](https://spiral.ai/integrations/manus/gemini-3-flash-preview)
- [Muse](https://spiral.ai/integrations/muse/gemini-3-flash-preview)
- [Muse Code](https://spiral.ai/integrations/muse-code/gemini-3-flash-preview)
- [n8n](https://spiral.ai/integrations/n8n/gemini-3-flash-preview)
- [Notion](https://spiral.ai/integrations/notion/gemini-3-flash-preview)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gemini-3-flash-preview)
- [opencode](https://spiral.ai/integrations/opencode/gemini-3-flash-preview)
- [Perplexity](https://spiral.ai/integrations/perplexity/gemini-3-flash-preview)
- [Raycast](https://spiral.ai/integrations/raycast/gemini-3-flash-preview)
- [VS Code](https://spiral.ai/integrations/vscode/gemini-3-flash-preview)
- [Windsurf](https://spiral.ai/integrations/windsurf/gemini-3-flash-preview)
- [Zapier](https://spiral.ai/integrations/zapier/gemini-3-flash-preview)

## More ChatGPT guides

- [GPT-oss-120B](https://spiral.ai/integrations/chatgpt/gpt-oss-120b)
- [Gemini 3.1 Flash-Lite](https://spiral.ai/integrations/chatgpt/gemini-3-1-flash-lite)
- [GPT-oss Safeguard 20B](https://spiral.ai/integrations/chatgpt/gpt-oss-safeguard-20b)
- [Gemini 3.1 Pro Custom Tools](https://spiral.ai/integrations/chatgpt/gemini-3-1-pro-custom-tools)
- [GPT-6.2 Sol Pro](https://spiral.ai/integrations/chatgpt/gpt-6-2-sol-pro)
- [Gemini 3.1 Pro Preview](https://spiral.ai/integrations/chatgpt/gemini-3-1-pro-preview)

## Questions about Gemini 3 Flash Preview in ChatGPT

**Can ChatGPT use Gemini 3 Flash Preview?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Gemini 3 Flash Preview like any built-in tool.

**How much does Gemini 3 Flash Preview cost in ChatGPT?**

Up to $0.01602 per run at the default inputs. $0.65 per 1M input tokens, $0.065 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $1.30 per 1M audio input tokens, $3.90 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.

**Do I need a Vertex AI account to use Gemini 3 Flash Preview in ChatGPT?**

No. Spiral runs Gemini 3 Flash Preview on its own Vertex AI account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Gemini 3 Flash Preview in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while Gemini 3 Flash Preview runs?**

Gemini 3 Flash Preview runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.

**What is Gemini 3 Flash good at?**

Google lists everyday coding, reasoning, planning, and multimodal analysis as intended uses. Practical tasks include debugging a function, comparing long documents, and turning a brief into an ordered work plan.

**How much context can Gemini 3 Flash handle?**

Gemini 3 Flash Preview has a 1,048,576-token context window and supports up to 65,536 output tokens. For a long document or codebase, put the source material first and the specific question afterward.

**When should I use less thinking?**

Try minimal thinking for straightforward extraction or classification. Reserve higher thinking for debugging, reasoning, and plans with dependencies, then compare results on examples from your actual workload.

**Should I lower the temperature for more accurate answers?**

Start at 1.0, which Google recommends for Gemini 3. Define the evidence the answer must use and the format you need instead of treating a lower temperature as an accuracy guarantee.

**How should I prompt Gemini 3 Flash?**

Give it a clear task, the relevant source material, and a concrete deliverable. For example, request a comparison table with supporting passages rather than a general review.

