How to Use Gemini 3.1 Flash-Lite in OpenClaw
Gemini 3.1 Flash-Lite suits repeated translation, classification, and data extraction tasks. It also generates UI code, with adjustable reasoning for more involved requests.
Prompts to try with Gemini 3.1 Flash-Lite in OpenClaw
Copy an example into OpenClaw, or ask in your own words.
Every morning, use Gemini 3.1 Flash-Lite with minimal reasoning to classify newly received support messages as billing, technical, account, or other. Produce a review list with message IDs and supporting excerpts.
Each weekday, use Gemini 3.1 Flash-Lite to summarize newly collected customer feedback in 300 words. Group it by usability, reliability, and feature requests, and retain the source message IDs.
Every hour, use Gemini 3.1 Flash-Lite to extract order IDs, promised dates, and explicit requests from new customer messages. Return a structured list and leave unstated values empty.
Each evening, use Gemini 3.1 Flash-Lite to review new community submissions against the moderation policy supplied to this task. Return policy labels, supporting excerpts, and uncertain cases for review.
Every Monday, use Gemini 3.1 Flash-Lite to draft Spanish translations of newly approved English help articles supplied to this task. Preserve product terminology and flag passages that need human review.
How to set up Gemini 3.1 Flash-Lite in OpenClaw
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send OpenClaw 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 Spiral's MCP server
- Add the server
On the machine that runs OpenClaw's Gateway:
openclaw mcp add spiral \ --url https://api.spiral.ai/mcp \ --transport streamable-http \ --auth oauth
- Sign in
In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.
openclaw mcp login spiral
- Reload and check
A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.
openclaw mcp reload openclaw mcp doctor spiral --probe
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 Gemini 3.1 Flash-Lite
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-3.1-flash-lite", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: OpenClaw finds Gemini 3.1 Flash-Lite on Spiral, shows the price and runs it.
Gemini 3.1 Flash-Lite providers and prices
Spiral runs Gemini 3.1 Flash-Lite through Vertex AI. Open a card for today's price, with every fee included.
Up to $0.008011 per run at the default inputs. $0.325 per 1M input tokens, $0.0325 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $0.65 per 1M audio input tokens, $1.95 per 1M output tokens.
Settings you can ask for
Ask OpenClaw for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 65536 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | a number from -2 | ||
| Reasoning effort | minimal, low, medium, or high | minimal | How much the model reasons. |
| Frequency penalty | a number from -2 |
Every API field of Gemini 3.1 Flash Lite is on its tool page: open its card above.
What can you do with Gemini 3.1 Flash-Lite in OpenClaw?
Process recurring batches of messages into consistent labels, summaries, and extracted records with Gemini 3.1 Flash-Lite. Define the categories and missing-information rules once so each run produces comparable results.
Translate support replies
Translate repeated customer replies while preserving product names, order numbers, and a supplied terminology list.
Classify incoming requests
Assign support messages to defined categories, with examples that distinguish billing questions, technical issues, and account requests.
Extract records from text
Turn order confirmations or business messages into structured records. Require explicit evidence for each value and leave missing information empty.
Review content against a policy
Label submitted text against a supplied moderation policy and flag uncertain cases for review.
Summarize lengthy documents
Condense supplied documents into decisions, open questions, and supporting passages so a reviewer can check the summary.
Build a dashboard prototype
Generate UI code from a defined layout, sample data, and interaction requirements, then test filtering, sorting, and empty states.
Label customer feedback
Sort feedback into a fixed list of themes and return a short supporting excerpt for each label.
More on Gemini 3.1 Flash-Lite and OpenClaw
Gemini 3.1 Flash-Lite in other agents
Questions about Gemini 3.1 Flash-Lite in OpenClaw
Can OpenClaw use Gemini 3.1 Flash-Lite?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Gemini 3.1 Flash-Lite like any built-in tool.
How much does Gemini 3.1 Flash-Lite cost in OpenClaw?
Up to $0.008011 per run at the default inputs. $0.325 per 1M input tokens, $0.0325 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $0.65 per 1M audio input tokens, $1.95 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.
Do I need a Vertex AI account to use Gemini 3.1 Flash-Lite in OpenClaw?
No. Spiral runs Gemini 3.1 Flash-Lite 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 3.1 Flash-Lite in OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while Gemini 3.1 Flash-Lite runs?
Gemini 3.1 Flash-Lite runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.
What is Gemini 3.1 Flash-Lite good at?
It is designed for repeated translation, classification, and simple data extraction. Other documented uses include content moderation, document summaries, and generating UI code.
How much text can Gemini 3.1 Flash-Lite handle?
Google lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. These are token limits, so avoid treating them as fixed word or page counts.
When should I increase the reasoning level?
Start with minimal reasoning for straightforward extraction and labeling. Try higher reasoning for requests with interacting constraints, such as generating a dashboard with filtering and validation.
Can Gemini 3.1 Flash-Lite write code?
Yes. Google specifically identifies user interfaces, dashboards, and simulations as supported coding uses; give it a concrete specification and test the resulting behavior.
How should I write prompts for Gemini 3.1 Flash-Lite?
State the task, constraints, and required output directly. Separate the source material from instructions, and include examples when labels or formatting could be ambiguous.
Start using Gemini 3.1 Flash-Lite in OpenClaw
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into OpenClaw:
set up https://spiral.ai/SKILL.md


