How to Use Gemini 3.7 Flash in Gemini CLI
Gemini 3.7 Flash suits debugging, web development, and document-heavy tasks that take several steps. Google reports improvements over Gemini 3.6 Flash in software engineering, knowledge work, and web development.
Prompts to try with Gemini 3.7 Flash in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use Gemini 3.7 Flash to investigate the failing tests in this project. Trace the failure to the relevant code, make the smallest justified fix, and run the affected tests.
Use Gemini 3.7 Flash to build a searchable table using this project's existing components. Include empty results, keyboard access, and a clear search reset; verify each behavior.
Use Gemini 3.7 Flash to review the current diff for behavior changes. Report each finding with its file, triggering conditions, and a concrete verification step.
Use Gemini 3.7 Flash to compare this project's README with its implementation. Fix instructions contradicted by the code and flag anything you cannot verify.
Use Gemini 3.7 Flash with high reasoning effort to investigate duplicate job execution in this project. Inspect retries and state transitions, propose a focused correction, and test the duplicate-delivery case.
How to set up Gemini 3.7 Flash in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI 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 Gemini 3.7 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-3.7-flash", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Gemini CLI finds Gemini 3.7 Flash on Spiral, shows the price and runs it.
Gemini 3.7 Flash providers and prices
Spiral runs Gemini 3.7 Flash through Vertex AI. Open a card for today's price, with every fee included.
Up to $0.040005 per run at the default inputs. $1.95 per 1M input tokens, $0.195 per 1M cached input tokens, $0.054166668 per 1M cache write tokens, $9.75 per 1M output tokens.
Settings you can ask for
Ask Gemini CLI 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. | |
| Reasoning effort | low, medium, or high | medium | How much the model reasons. |
Every API field of Gemini 3.7 Flash is on its tool page: open its card above.
What can you do with Gemini 3.7 Flash in Gemini CLI?
Turn bug reports and feature briefs into code changes with Gemini 3.7 Flash. Have your coding agent inspect the relevant project files, make focused edits, and verify the requested behavior.
Investigate a failing feature
Ask Gemini 3.7 Flash to connect an error report with the relevant code, propose a focused fix, and identify how to verify it.
Build a web feature
Give Gemini 3.7 Flash a concrete feature brief with interaction rules and acceptance criteria. Ask for working code and a checklist of behaviors to test.
Compare lengthy reports
Have Gemini 3.7 Flash compare supplied reports, trace changed claims to their sources, and separate documented differences from interpretation.
Extract business records
Ask Gemini 3.7 Flash to turn supplied document text into structured records, using explicit rules for missing values and ambiguous entries.
Prepare an operations brief
Use Gemini 3.7 Flash to summarize supplied status updates into unresolved issues, dependencies, and proposed next actions with supporting evidence.
Review a training video
Ask Gemini 3.7 Flash to identify demonstrated steps and unclear instructions in a training recording. Keep video with audio under the approximate 45-minute limit.
More on Gemini 3.7 Flash and Gemini CLI
Gemini 3.7 Flash in other agents
Questions about Gemini 3.7 Flash in Gemini CLI
Can Gemini CLI use Gemini 3.7 Flash?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Gemini 3.7 Flash like any built-in tool.
How much does Gemini 3.7 Flash cost in Gemini CLI?
Up to $0.040005 per run at the default inputs. $1.95 per 1M input tokens, $0.195 per 1M cached input tokens, $0.054166668 per 1M cache write tokens, $9.75 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.
Do I need a Vertex AI account to use Gemini 3.7 Flash in Gemini CLI?
No. Spiral runs Gemini 3.7 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 3.7 Flash in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while Gemini 3.7 Flash runs?
Gemini 3.7 Flash runs in the background. Gemini CLI starts the run, checks on it and gives you the text, json when it's ready.
What is Gemini 3.7 Flash good at?
Coding, web development, and knowledge work are its main documented strengths. Use it for tasks such as investigating bugs, building web features, and comparing dense documents.
How much text can Gemini 3.7 Flash handle?
Google lists a 1,048,576-token context window and a maximum output of 65,536 tokens. Treat the output limit as a ceiling when planning long reports.
Can Gemini 3.7 Flash analyze long videos?
Yes. Google lists approximate limits of 45 minutes for video with audio and one hour for video without audio.
How should I prompt Gemini 3.7 Flash?
State the task, constraints, and required result directly. Include an example when you need a particular format, classification rule, or writing style.
Can Gemini 3.7 Flash return structured data?
Yes, it supports structured output with a response schema. This fits extraction and classification tasks where the result needs a predictable structure.
Start using Gemini 3.7 Flash in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


