How to Use GPT-6.2 Sol in Amp
GPT-6.2 Sol handles everyday coding, writing, and multistep tasks. Choose it for routine work; GPT-6.2 Sol Pro uses the same underlying model with additional reasoning for harder problems.
Prompts to try with GPT-6.2 Sol in Amp
Copy an example into Amp, or ask in your own words.
Use GPT-6.2 Sol to review the current branch against main. Report actionable bugs with file locations, triggering conditions, and suggested checks.
Use GPT-6.2 Sol to apply the review comments recorded in this project. Follow existing conventions, run the affected tests, and report any unresolved comments.
Use GPT-6.2 Sol to update the README from the current implementation. Verify each example against the code and flag behavior you cannot confirm.
Ask GPT-6.2 Sol through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
Get a second opinion from GPT-6.2 Sol on this function, then tell me what the call cost.
How to set up GPT-6.2 Sol in Amp
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
No header and no client ID or secret: Amp registers itself with Spiral.
amp mcp add spiral https://api.spiral.ai/mcp
- Sign in
Start amp. Amp opens Spiral's sign-in page in your browser: sign in, pick the organization and click Authorize. No API key.
- Check it
amp mcp doctor
Use the Spiral skill
- Send Amp 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 GPT-6.2 Sol
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": "openai", "model": "openai/gpt-6.2-sol", "input": { "messages": [ { "role": "user", "content": "Hello!" } ] } }'
Then paste one of the prompts above: Amp finds GPT-6.2 Sol on Spiral, shows the price and runs it.
GPT-6.2 Sol providers and prices
Spiral runs GPT-6.2 Sol through OpenAI. Open a card for today's price, with every fee included.
Up to $0.053363 per run at the default inputs. $2.60 per 1M input tokens, $0.13 per 1M cached input tokens, $3.25 per 1M cache write tokens, $13.00 per 1M output tokens.
Settings you can ask for
Ask Amp for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Max tokens | 16 to 128000 | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). | |
| Reasoning effort | low, medium, high, or xhigh | How much the model reasons. | |
| Parallel tool calls | on or off |
Every API field of GPT-6.2 Sol is on its tool page: open its card above.
What can you do with GPT-6.2 Sol in Amp?
Turn code review feedback into focused changes with GPT-6.2 Sol. Give the agent the relevant project files, expected behavior, and checks that define completion.
Review a pull request
Check a proposed change for bugs and missed edge cases. Request findings tied to specific code, with an explanation of how each issue could occur.
Apply code review feedback
Turn reviewer comments into focused edits and relevant checks. Provide the intended behavior and project conventions so the changes have a clear target.
Review a database migration
Examine a migration plan for failure modes, recovery gaps, and missing validation. Use the pro reasoning option when the plan needs additional analysis.
Turn meeting notes into a brief
Organize notes into decisions, next steps, owners, and unresolved questions. Ask for missing owners or dates to be marked explicitly.
Draft technical documentation
Turn supplied implementation details into a guide for a defined audience. Request examples and explanations grounded in the supplied material.
Prepare recurring operations summaries
Compare the latest status updates with the previous report. Request changed commitments, unresolved blockers, and questions that need an owner.
Extract structured action items
Convert supplied notes or messages into structured records for downstream processing. Define the required information and how unknown values should be represented.
More on GPT-6.2 Sol and Amp
Overview
GPT-6.2 Sol in other agents
Questions about GPT-6.2 Sol in Amp
Can Amp use GPT-6.2 Sol?
Yes. Add Spiral to Amp as an MCP server, and Amp can find and run GPT-6.2 Sol like any built-in tool.
How much does GPT-6.2 Sol cost in Amp?
Up to $0.053363 per run at the default inputs. $2.60 per 1M input tokens, $0.13 per 1M cached input tokens, $3.25 per 1M cache write tokens, $13.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Amp plan is separate.
Do I need an OpenAI account to use GPT-6.2 Sol in Amp?
No. Spiral runs GPT-6.2 Sol on its own OpenAI account. You sign in to Spiral once and never paste a key.
How long does it take to set up GPT-6.2 Sol in Amp?
About two minutes: add the server, then sign in, then check it.
Does Amp wait while GPT-6.2 Sol runs?
GPT-6.2 Sol runs in the background. Amp starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-6.2 Sol good at?
Everyday coding, writing, and work that requires several steps. Useful starting points include reviewing a code change, drafting technical explanations, and turning notes into an actionable brief.
How does GPT-6.2 Sol Pro differ from GPT-6.2 Sol?
GPT-6.2 Sol Pro uses the same underlying model with pro reasoning. Choose it when a task warrants additional analysis, such as examining a migration plan for failure modes.
How much text can GPT-6.2 Sol handle?
The underlying model has a 1,050,000-token context window, with up to 922,000 input tokens and 128,000 output tokens. Treat the output ceiling as a budget for reasoning and the visible answer, rather than a guaranteed answer length.
Does GPT-6.2 Sol know recent events?
Its listed knowledge cutoff is June 1, 2026. Supply current sources when asking about later events, releases, or changing information.
Should I ask GPT-6.2 Sol to think step by step?
Use a direct task description instead. State the desired result, relevant constraints, and what the final answer should contain; OpenAI says step-by-step prompting may hinder reasoning models.
Start using GPT-6.2 Sol in Amp
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Amp:
set up https://spiral.ai/SKILL.md


