How to Use Gemma 3 12B in ChatGPT
Gemma 3 12B is an instruction-tuned model for document summaries, multilingual drafts, and code explanations. Its 128K-token context supports questions across long source texts.
Prompts to try with Gemma 3 12B in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Gemma 3 12B to summarize the research text in this conversation in 250 words. Include three findings, a supporting passage for each, and two questions the text leaves unanswered.
Use Gemma 3 12B to compare the two policy passages in this conversation. Make a table of changed requirements, unchanged requirements, and unclear wording, quoting the relevant passages.
Use Gemma 3 12B to draft a Spanish reply to the customer message in this conversation using only the supplied return policy. Keep it under 150 words and identify any question the policy does not answer.
Use Gemma 3 12B to correct the French paragraph in this conversation. Show the corrected paragraph, explain the three most useful corrections in English, and give me one practice question.
Use Gemma 3 12B to turn the meeting transcript in this conversation into decisions and action items. Include owners and deadlines only when explicitly stated, and finish with unresolved questions.
How to set up Gemma 3 12B in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- 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
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- 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
- Send ChatGPT this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- 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
- Create an API key
In the console, under API keys.
- Run Gemma 3 12B
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": "openrouter", "model": "google/gemma-3-12b-it", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: ChatGPT finds Gemma 3 12B on Spiral, shows the price and runs it.
Gemma 3 12B providers and prices
Spiral runs Gemma 3 12B through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.000803 per run at the default inputs. $0.065 per 1M input tokens, $0.195 per 1M output tokens.
Settings you can ask for
Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 16384 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Google: Gemma 3 12B is on its tool page: open its card above.
What can you do with Gemma 3 12B in ChatGPT?
Turn supplied text into summaries, multilingual drafts, and answers grounded in reference material with Gemma 3 12B. Specify the audience and desired length, and request supporting passages for factual answers.
Research brief summaries
Turn supplied research text into a short brief with findings, supporting passages, and unanswered questions.
Policy comparison
Compare two policy texts and list changed requirements, exceptions, and passages that need clarification.
Multilingual support drafts
Draft replies in the customer's language using a supplied policy and terminology guide.
Code explanations
Explain supplied functions, trace their inputs and outputs, and identify assumptions worth testing.
Structured request extraction
Convert written requests into structured records, using explicit rules for missing information.
Meeting recaps
Summarize meeting transcripts into decisions, action items, owners, and unresolved questions.
Writing practice
Review a learner's paragraph, explain corrections, and suggest a short follow-up exercise.
Release note drafts
Turn supplied change descriptions into reader-facing release notes, keeping confirmed changes separate from open questions.
More on Gemma 3 12B and ChatGPT
Overview
Gemma 3 12B in other agents
Questions about Gemma 3 12B in ChatGPT
Can ChatGPT use Gemma 3 12B?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Gemma 3 12B like any built-in tool.
How much does Gemma 3 12B cost in ChatGPT?
Up to $0.000803 per run at the default inputs. $0.065 per 1M input tokens, $0.195 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 an OpenRouter account to use Gemma 3 12B in ChatGPT?
No. Spiral runs Gemma 3 12B on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Gemma 3 12B in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while Gemma 3 12B runs?
Gemma 3 12B runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.
What is Gemma 3 12B useful for?
Use it to summarize long text, answer questions about supplied material, explain code, and draft multilingual content. Give each request a clear deliverable, such as a comparison table or a short explanation.
How much text can Gemma 3 12B work with?
It supports a 128K-token context. Google's current documentation says input tokens reduce the space available for output, so leave room for the response and request long drafts section by section.
Does Gemma 3 12B support languages besides English?
Google reports support for more than 140 languages. Specify the target language, audience, and terms that should stay untranslated.
Can Gemma 3 12B produce structured text?
Yes, Google lists structured outputs among its capabilities. Describe the exact structure, include a completed example, and check the result before using it in another process.
Where does Gemma 3 12B need extra checking?
It can state incorrect or outdated information, and highly complex or open-ended tasks can be challenging. Supply reference material, ask it to flag missing evidence, and verify factual claims against the source.
Start using Gemma 3 12B in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


