Spiral gives your agent every tool with one account. Browse the tools →

ChatGPT · LLMReleased 2026-09-08

How to Use Nex-N2.5-Pro in ChatGPT

Nex-N2.5-Pro suits complex coding and tasks that require repeated testing and correction. It targets advanced software engineering, while Nex-N2.5-Mini targets fast instruction following and tool execution.

Prompts to try with Nex-N2.5-Pro in ChatGPT

Copy an example into ChatGPT, or ask in your own words.

Use Nex-N2.5-Pro with adaptive thinking to investigate the error message I pasted. Ask for missing evidence before recommending a fix.

Nex-N2.5-ProChatGPT
Try asking
  • Use Nex-N2.5-Pro to compare SQLite and PostgreSQL for an offline desktop app. Consult official documentation and link support for each recommendation.

  • Use Nex-N2.5-Pro with thinking always enabled to check this calculation. State assumptions, recompute the result, and identify inconsistencies.

  • Use Nex-N2.5-Pro to turn the checkout requirements above into a browser test checklist with an expected result for every step.

  • Use Nex-N2.5-Pro to investigate the conflicting technical claims in this conversation. Find primary evidence and list what remains unresolved.

How to set up Nex-N2.5-Pro in ChatGPT

Pick the way that suits you. Each takes about two minutes.

Use the ChatGPT connector

  1. Add a custom MCP server

    In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

    https://api.spiral.ai/mcp
  2. Click Connect

    ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

  3. Sign in to Spiral and approve

    Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

Use the Spiral skill

  1. Send ChatGPT this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run Nex-N2.5-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": "nex-agi/nex-n2.5-pro",
        "input": {
          "messages": [
            {
              "role": "system"
            }
          ]
        }
      }'

Then paste one of the prompts above: ChatGPT finds Nex-N2.5-Pro on Spiral, shows the price and runs it.

Nex-N2.5-Pro providers and prices

Spiral runs Nex-N2.5-Pro through OpenRouter. Open a card for today's price, with every fee included.

OpenRouterLLM
Nex AGI: Nex-N2.5-Pro
nex-agi/nex-n2.5-pro

Settings you can ask for

Ask ChatGPT for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Top ka whole number from 0
Top p0 to 1
Logprobson or off
Max tokens1 to 235929

The most output tokens to generate.

Temperature0 to 2
Top logprobs0 to 20
Reasoning effortnone, medium, or highhigh

How much the model reasons.

Every API field of Nex AGI: Nex-N2.5-Pro is on its tool page: open its card above.

What can you do with Nex-N2.5-Pro in ChatGPT?

Work through technical investigations and research questions with Nex-N2.5-Pro. Ask it to separate supported findings from assumptions and explain how to verify the result.

Fix bugs across several files

Trace a failure through the application, patch the affected code, and rerun the reproduction.

Verify a frontend change

Implement a requested interaction, exercise it in the browser, and correct observed failures.

Run browser regression checks

Follow a concrete checklist and report failing steps with expected and observed behavior.

Investigate terminal failures

Inspect command output, identify the cause, apply a fix, and repeat the failing command.

Research a technical question

Compare primary sources, resolve conflicting claims, and produce a brief with supporting links.

Check a scientific calculation

Translate assumptions into a calculation, execute it, and investigate inconsistent results.

Questions about Nex-N2.5-Pro in ChatGPT

Can ChatGPT use Nex-N2.5-Pro?

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Nex-N2.5-Pro like any built-in tool.

How much does Nex-N2.5-Pro cost in ChatGPT?

Up to $0.001336 per run at the default inputs. $0.0975 per 1M input tokens, $0.325 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.

Do I need an OpenRouter account to use Nex-N2.5-Pro in ChatGPT?

No. Spiral runs Nex-N2.5-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 Nex-N2.5-Pro in ChatGPT?

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

Does ChatGPT wait while Nex-N2.5-Pro runs?

Nex-N2.5-Pro runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.

What is Nex-N2.5-Pro best suited for?

Complex software changes and tasks that require a cycle of action, testing, and correction. Its documented applications also include browser testing, research, and scientific workflows.

How does Nex-N2.5-Pro differ from Nex-N2.5-Mini?

Nex AGI positions Pro for complex reasoning and advanced software engineering. Mini targets fast instruction following and real-time tool execution.

How much context can Nex-N2.5-Pro handle?

Its documented context window is 262,144 tokens. Keep a long task focused by carrying forward the goal, verified findings, and unresolved questions.

When should I use each thinking mode?

As a starting point, use adaptive thinking for mixed tasks and always-enabled thinking for difficult debugging. Direct responses skip the reasoning trace and suit straightforward requests.

Which sampling settings should I start with?

The maker recommends temperature 0.7, top-p 0.95, and top-k 40. Use that combination as a baseline when evaluating your own tasks.

Get started

Start using Nex-N2.5-Pro in ChatGPT

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into ChatGPT:

Set up ChatGPT

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options