How to Use Gemini 3.5 Flash in OpenClaw
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 OpenClaw
Copy an example into OpenClaw, or ask in your own words.
Use Gemini 3.5 Flash each morning to classify the supplied support messages as billing, bug, feature request, or other. Return counts and a review queue for ambiguous messages.
Use Gemini 3.5 Flash each week to compare the supplied old and new policy text. Report changed requirements with quotations and omit wording changes that preserve meaning.
Use Gemini 3.5 Flash each afternoon to extract owners, deadlines, and blockers from the supplied project updates. Mark missing owners or dates explicitly.
Use Gemini 3.5 Flash with low reasoning effort to categorize each supplied product feedback message. Return a JSON record containing its identifier, category, and supporting phrase.
Use Gemini 3.5 Flash each month to organize the supplied financial summaries. List reported amounts, conflicting statements, and missing details with source passages for review.
How to set up Gemini 3.5 Flash 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 3.5 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: OpenClaw 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.
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.
Settings you can ask for
Ask OpenClaw for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Max tokens | 1 to 65536 | The most output tokens to generate. | |
| Presence penalty | a number from -2 | ||
| Reasoning effort | minimal, low, medium, or high | medium | How much the model reasons. |
| Frequency penalty | a 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 OpenClaw?
Gemini 3.5 Flash can turn recurring batches of text into categorized queues and review summaries. Define the categories, evidence requirements, and stopping point for each run.
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.
More on Gemini 3.5 Flash and OpenClaw
Gemini 3.5 Flash in other agents
Questions about Gemini 3.5 Flash in OpenClaw
Can OpenClaw use Gemini 3.5 Flash?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Gemini 3.5 Flash like any built-in tool.
How much does Gemini 3.5 Flash cost in OpenClaw?
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 OpenClaw plan is separate.
Do I need a Vertex AI account to use Gemini 3.5 Flash in OpenClaw?
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 OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while Gemini 3.5 Flash runs?
Gemini 3.5 Flash runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.
What is Gemini 3.5 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.
Start using Gemini 3.5 Flash 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


