Spiral gives your agent every tool with one account. Browse the tools →

ChatGPT · LLMReleased 2026-05-19

How to Use Gemini 3.5 Flash in ChatGPT

Gemini 3.5 Flash suits code changes, document analysis, and tasks with several steps. Gemini 3.6 Flash improves on it with fewer unwanted edits and debugging loops.

Prompts to try with Gemini 3.5 Flash in ChatGPT

Copy an example into ChatGPT, or ask in your own words.

Use Gemini 3.5 Flash to compare the two policy texts above. List changed requirements, quote the supporting passages, and distinguish changes from wording edits.

Gemini 3.5 FlashChatGPT
Try asking
  • Use Gemini 3.5 Flash to extract every deadline and responsible person from the conversation above. Return a table and mark anything that is not explicitly stated.

  • Use Gemini 3.5 Flash with high reasoning effort to check the mathematical argument above. Identify the first unsupported step and provide a corrected argument.

  • Use Gemini 3.5 Flash to classify the customer messages above as billing, bug, feature request, or other. Give one supporting phrase for each classification.

  • Use Gemini 3.5 Flash to turn the product requirements above into acceptance criteria. Include normal behavior, error cases, and unresolved questions.

How to set up Gemini 3.5 Flash 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.

    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.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Gemini 3.5 Flash

    One request; the result comes back by polling or a webhook.

    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-3.5-flash",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: ChatGPT finds Gemini 3.5 Flash on Spiral, shows the price and runs it.

Gemini 3.5 Flash providers and prices

Spiral runs Gemini 3.5 Flash through Vertex AI. Open a card for today's price, with every fee included.

Vertex AILLM
Gemini 3.5 Flash
google/gemini-3.5-flash

Settings you can ask for

Ask ChatGPT for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number
Max tokens1 to 65536

The most output tokens to generate.

Presence penaltya number from -2
Reasoning effortminimal, low, medium, or highmedium

How much the model reasons.

Frequency penaltya number from -2

Every API field of Gemini 3.5 Flash is on its tool page: open its card above.

What can you do with Gemini 3.5 Flash in ChatGPT?

Gemini 3.5 Flash can compare supplied text, extract records, and work through difficult questions in conversation. Put long source material before the question and specify the answer format.

Fix a reproducible bug

Use Gemini 3.5 Flash to trace a failing test, propose a focused patch, and explain which behavior the patch changes.

Plan a codebase migration

Have Gemini 3.5 Flash map dependencies, divide a migration into reviewable changes, and identify checks for each stage.

Build an application prototype

Ask Gemini 3.5 Flash to turn a written specification into application code, then revise it against concrete acceptance criteria.

Compare long documents

Give Gemini 3.5 Flash the source text and ask for conflicting requirements, changed obligations, and supporting passages.

Extract records from text

Use Gemini 3.5 Flash to extract names, dates, amounts, and source passages into JSON for validation.

Sort incoming requests

Have Gemini 3.5 Flash classify support requests against defined categories and flag ambiguous cases for review.

Prepare a financial document review

Ask Gemini 3.5 Flash to organize supplied financial text into a checklist of reported amounts, missing details, and questions for the reviewer.

Questions about Gemini 3.5 Flash in ChatGPT

Can ChatGPT use Gemini 3.5 Flash?

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Gemini 3.5 Flash like any built-in tool.

How much does Gemini 3.5 Flash cost in ChatGPT?

Up to $0.04806 per run at the default inputs. $1.95 per 1M input tokens, $0.195 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $3.90 per 1M audio input tokens, $11.70 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 3.5 Flash in ChatGPT?

No. Spiral runs Gemini 3.5 Flash 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 3.5 Flash 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 3.5 Flash runs?

Gemini 3.5 Flash runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.

What is Gemini 3.5 Flash good at?

Code generation, codebase maintenance, and workflows that require several steps are documented uses. It can also turn supplied documents into summaries or extracted records.

How much context can Gemini 3.5 Flash handle?

Google lists a context window of 1,048,576 tokens and a maximum output of 65,536 tokens. For long documents, put the source material before the final question.

Can Gemini 3.5 Flash generate images or video?

Its output is text. It can write code for a visual interface, but it does not directly return generated image, audio, or video files.

When should I increase reasoning effort?

Use high effort for hard math, complex reasoning, or difficult coding problems. Try low effort when faster responses matter, and compare the results on your actual task.

Can I trust every value in its JSON?

Validate the values before using them. Correct JSON syntax does not establish that a date, amount, or extracted name matches the source.

Get started

Start using Gemini 3.5 Flash in ChatGPT

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into ChatGPT:

Set up ChatGPT

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options