How to Use GPT-6 Sol Pro in Codex
GPT-6 Sol Pro is for difficult coding and analysis that warrant additional model work. It uses the same underlying model as GPT-6 Sol with pro reasoning enabled.
Prompts to try with GPT-6 Sol Pro in Codex
Copy an example into Codex, or ask in your own words.
Use GPT-6 Sol Pro with high reasoning effort to review this project's database migration. Identify data loss risks, compatibility problems, and rollback gaps before proposing changes.
Use GPT-6 Sol Pro to compare the two architecture proposals in this repository against the documented requirements. Return a recommendation, the strongest objection to it, and unresolved technical questions.
Ask GPT-6 Sol Pro 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 Sol Pro on this function, then tell me what the call cost.
Summarize these release notes with GPT-6 Sol Pro in five bullet points.
How to set up GPT-6 Sol Pro in Codex
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
codex mcp add spiral --url https://api.spiral.ai/mcp
- Sign in
Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.
codex mcp login spiral
Use the Spiral skill
- Send Codex 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 Sol Pro
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": "openai/gpt-6-sol-pro", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Codex finds GPT-6 Sol Pro on Spiral, shows the price and runs it.
GPT-6 Sol Pro providers and prices
Spiral runs GPT-6 Sol Pro through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.053339 per run at the default inputs. $2.60 per 1M input tokens, $13.00 per 1M output tokens.
Settings you can ask for
Ask Codex for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Max tokens | 1 to 128000 | The most output tokens to generate. | |
| Reasoning effort | none, low, medium, high, xhigh, or max | medium | How much the model reasons. |
Every API field of OpenAI: GPT-6 Sol Pro is on its tool page: open its card above.
What can you do with GPT-6 Sol Pro in Codex?
GPT-6 Sol can turn a bug report or feature brief into code changes and a reviewable explanation. Give the agent relevant project context, clear acceptance criteria, and a defined scope for verification.
Debug a recurring software failure
Trace a failure from its reproduction steps and logs, propose a focused fix, and identify the checks that would demonstrate it works.
Review a database migration
Examine a migration plan for data loss, compatibility problems, and rollback gaps. Ask for failure scenarios and the evidence needed before proceeding.
Turn requirements into an implementation plan
Convert a product brief into engineering tasks, dependencies, acceptance criteria, and questions that block implementation.
Compare technical proposals
Evaluate competing designs against stated requirements. Request a recommendation with tradeoffs and references to the supplied proposals.
Explain unfamiliar code
Map the responsibilities and data flow in supplied code, then identify the places a proposed change would affect.
Review an incident timeline
Compare logs, observations, and a response timeline to separate established facts from possible causes. Produce follow-up investigations with clear evidence requirements.
Check a specification for contradictions
Review a detailed specification for conflicting requirements, missing cases, and ambiguous behavior. Return concrete questions and proposed acceptance criteria.
More on GPT-6 Sol Pro and Codex
Overview
GPT-6 Sol Pro in other agents
Questions about GPT-6 Sol Pro in Codex
Can Codex use GPT-6 Sol Pro?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run GPT-6 Sol Pro like any built-in tool.
How much does GPT-6 Sol Pro cost in Codex?
Up to $0.053339 per run at the default inputs. $2.60 per 1M input 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 Codex plan is separate.
Do I need an OpenRouter account to use GPT-6 Sol Pro in Codex?
No. Spiral runs GPT-6 Sol Pro on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up GPT-6 Sol Pro in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while GPT-6 Sol Pro runs?
GPT-6 Sol Pro runs in the background. Codex starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-6 Sol useful for?
GPT-6 Sol is designed for complex coding and agent workflows. Practical tasks include debugging, comparing technical proposals, and turning a detailed brief into an implementation plan.
How does GPT-6 Sol Pro differ from GPT-6 Sol?
GPT-6 Sol Pro uses the same underlying model with pro reasoning enabled. Start with GPT-6 Sol for routine work; consider GPT-6 Sol Pro for difficult analysis or coding that warrants additional model work.
How much context and output can GPT-6 Sol handle?
The underlying model has a 1,050,000-token context window and a maximum output allowance of 128,000 tokens. Internal reasoning shares the output allowance, so the readable response can be shorter.
Does GPT-6 Sol know about recent events?
Its knowledge cutoff is April 20, 2026. Supply current source material when a task depends on later events, product changes, or new documentation.
How should I prompt GPT-6 Sol?
Give a clear task, the relevant evidence, explicit constraints, and the response format you want. For example, ask for a recommendation under 300 words that cites the supplied evidence and lists unresolved questions.
Start using GPT-6 Sol Pro in Codex
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Codex:
set up https://spiral.ai/SKILL.md


