[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [GPT-5.6 Terra Pro](https://spiral.ai/integrations/codex/gpt-5-6-terra-pro)

# How to Use GPT-5.6 Terra Pro in Codex

GPT-5.6 Terra Pro targets complex analysis where answer quality matters. It uses the same underlying model as Terra, served with Pro reasoning mode.

|  |  |
| --- | --- |
| Model | GPT-5.6 Terra Pro |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.063989 per run at the default inputs. $2.60 per 1M input tokens, $15.60 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-5.6 Terra Pro in Codex

- Use GPT-5.6 Terra Pro to review this database migration plan against the schema and application code. Identify data-loss risks, rollback gaps, and assumptions requiring verification.
- Ask GPT-5.6 Terra 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-5.6 Terra Pro on this function, then tell me what the call cost.
- Summarize these release notes with GPT-5.6 Terra Pro in five bullet points.
- Ask GPT-5.6 Terra Pro to write unit tests for the file I have open and explain each case.

## How to set up GPT-5.6 Terra Pro in Codex

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

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex 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.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run GPT-5.6 Terra Pro**: One request; the result comes back by polling or a webhook.

```bash
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-5.6-terra-pro",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Codex finds GPT-5.6 Terra Pro on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/codex

## GPT-5.6 Terra Pro tools and prices

- [OpenAI: GPT-5.6 Terra Pro](https://spiral.ai/tools/openrouter/openai/gpt-5.6-terra-pro) (OpenRouter): Up to $0.063989 per run at the default inputs. $2.60 per 1M input tokens, $15.60 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 128000 | — | The most output tokens to generate. |
| tool_choice |  | — |  |
| response_format |  | — |  |

## What can you do with GPT-5.6 Terra Pro in Codex?

Turn project requirements into scoped patches, tests, and code reviews. Use Terra for everyday implementation and Terra Pro for difficult analysis.

### Scoped code changes

Give Terra a concrete bug or implementation request. Ask for the relevant patch and validation results.

### Document comparisons

Compare supplied material against explicit criteria. Request supporting passages for each finding and mark missing evidence.

### Customer conversation classification

Group conversations into defined categories, summarize recurring issues, and separate ambiguous cases for review.

### Difficult analytical reviews

Use Terra Pro to examine a complex proposal, identify conflicting assumptions, and produce a recommendation with supporting evidence.

### Repeatable extraction

Turn supplied text into consistent records with explicit rules for missing values and conflicting information.

### Implementation planning

Ask Terra to turn a bounded engineering requirement into a plan with acceptance criteria and relevant checks.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Codex guides](https://spiral.ai/integrations/codex)

## GPT-5.6 Terra Pro in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-5-6-terra-pro)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-5-6-terra-pro)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-5-6-terra-pro)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-5-6-terra-pro)
- [Cline](https://spiral.ai/integrations/cline/gpt-5-6-terra-pro)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-5-6-terra-pro)
- [Devin](https://spiral.ai/integrations/devin/gpt-5-6-terra-pro)
- [dots](https://spiral.ai/integrations/dots/gpt-5-6-terra-pro)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-5-6-terra-pro)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-5-6-terra-pro)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-5-6-terra-pro)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-5-6-terra-pro)
- [goose](https://spiral.ai/integrations/goose/gpt-5-6-terra-pro)
- [Grok](https://spiral.ai/integrations/grok/gpt-5-6-terra-pro)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-5-6-terra-pro)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-5-6-terra-pro)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-5-6-terra-pro)
- [Manus](https://spiral.ai/integrations/manus/gpt-5-6-terra-pro)
- [Muse](https://spiral.ai/integrations/muse/gpt-5-6-terra-pro)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-5-6-terra-pro)
- [n8n](https://spiral.ai/integrations/n8n/gpt-5-6-terra-pro)
- [Notion](https://spiral.ai/integrations/notion/gpt-5-6-terra-pro)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-5-6-terra-pro)
- [opencode](https://spiral.ai/integrations/opencode/gpt-5-6-terra-pro)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-5-6-terra-pro)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-5-6-terra-pro)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-5-6-terra-pro)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-5-6-terra-pro)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-5-6-terra-pro)

## More Codex guides

- [GPT-5.6 Terra](https://spiral.ai/integrations/codex/gpt-5-6-terra)
- [GPT-6 Astra](https://spiral.ai/integrations/codex/gpt-6-astra)
- [GPT-5.6 Sol Pro](https://spiral.ai/integrations/codex/gpt-5-6-sol-pro)
- [GPT-6 Astra Pro](https://spiral.ai/integrations/codex/gpt-6-astra-pro)
- [GPT-5.6 Sol](https://spiral.ai/integrations/codex/gpt-5-6-sol)
- [GPT-6 Luna](https://spiral.ai/integrations/codex/gpt-6-luna)

## Questions about GPT-5.6 Terra Pro in Codex

**Can Codex use GPT-5.6 Terra Pro?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run GPT-5.6 Terra Pro like any built-in tool.

**How much does GPT-5.6 Terra Pro cost in Codex?**

Up to $0.063989 per run at the default inputs. $2.60 per 1M input tokens, $15.60 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-5.6 Terra Pro in Codex?**

No. Spiral runs GPT-5.6 Terra 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-5.6 Terra Pro in Codex?**

About two minutes: add the hosted server, then sign in.

**Does Codex wait while GPT-5.6 Terra Pro runs?**

GPT-5.6 Terra 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-5.6 Terra good at?**

Use it for everyday implementation, document analysis, and classifying customer conversations. Keep requests scoped around a clear deliverable, such as a patch, comparison table, or categorized summary.

**How does Terra Pro differ from Terra?**

Terra Pro uses the same underlying model with Pro reasoning mode for complex tasks. Choose it for difficult analysis where additional model work may improve the answer.

**How much material can Terra handle?**

Terra has a 1,050,000-token context window and a maximum output allowance of 128,000 tokens. Internal reasoning also consumes the generation allowance, so visible answers can be shorter than that ceiling.

**Can Terra analyze images, audio, or video?**

Terra accepts images for analysis. Audio and video are not natively supported.

**Which reasoning setting should I start with?**

Start with medium reasoning. Try low for straightforward tasks where response time matters, then compare results on examples from your actual workload.

