[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [GPT Terra Latest](https://spiral.ai/integrations/instinct/gpt-terra-latest)

# How to Use GPT Terra Latest in Instinct

GPT Terra Latest suits product photo matching, technical drawing analysis, and everyday writing. It currently points to GPT-6.1 Terra and follows future Terra updates, whereas GPT-6.1 Terra names a specific release.

|  |  |
| --- | --- |
| Model | GPT Terra Latest |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.026682 per run at the default inputs. $1.30 per 1M input tokens, $0.065 per 1M cached input tokens, $1.625 per 1M cache write tokens, $6.50 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with GPT Terra Latest in Instinct

- Every morning, use GPT Terra Latest to compare the product photos supplied for this run with the current catalog entries. Report proposed matches, visible supporting details, and uncertain cases.
- Each weekday, use GPT Terra Latest to review the application screenshots supplied for this run. Describe each screen's state and list visible error messages with their exact wording.
- Each Friday, use GPT Terra Latest to turn the progress notes supplied for this run into a weekly update. Cover completed work, blockers, and next steps in no more than 300 words.
- For each new technical drawing supplied to this task, use GPT Terra Latest to write a component summary. Include visible labels and relationships, and identify unreadable annotations.
- Each Monday, use GPT Terra Latest to draft a proposal from the approved brief supplied for this run. Include scope, deliverables, assumptions, and open questions in under 600 words.

## How to set up GPT Terra Latest in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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 Spiral's MCP server

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### 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 Terra Latest**: 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": "openai",
    "model": "~openai/gpt-terra-latest",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds GPT Terra Latest on Spiral, shows the price and runs it.

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

## GPT Terra Latest tools and prices

- [GPT Terra Latest](https://spiral.ai/tools/openai/~openai/gpt-terra-latest) (OpenAI): Up to $0.026682 per run at the default inputs. $1.30 per 1M input tokens, $0.065 per 1M cached input tokens, $1.625 per 1M cache write tokens, $6.50 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| tools |  | — |  |
| top_p | … to 1 | — | Taken only with reasoning effort "none". |
| logprobs |  | — | Taken only with reasoning effort "none". |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 16 to 128000 | — | The most output tokens to generate. |

## What can you do with GPT Terra Latest in Instinct?

GPT Terra can produce recurring catalog comparisons, screen reviews, and written progress updates from supplied material. Give each recurring task a defined result and response structure so its reports address the same questions each time.

### Match product photos to catalog entries

Compare a product image with candidate catalog entries. Ask for the closest match, the visible details supporting it, and any differences that need review.

### Explain technical drawings

Turn a technical drawing into a written description of its components, labels, and relationships. Ask it to identify unreadable annotations separately.

### Interpret application screens

Read an application screenshot and describe the visible controls, current state, and next action for a defined task.

### Investigate webpage layout shifts

Use screenshots and relevant frontend code to investigate elements that move during page loading. Request a focused fix and a way to check the result.

### Draft proposals from a brief

Turn supplied requirements into a proposal with scope, deliverables, assumptions, and open questions. Specify the audience and desired length.

### Revise business writing

Rewrite an existing draft for a specific reader. Ask it to preserve the facts while improving clarity, organization, and tone.

### Prepare recurring written updates

Turn supplied progress notes into a consistent weekly update covering completed work, blockers, and next steps. Define the structure and word limit in the prompt.

## Overview

- [OpenAI](https://spiral.ai/providers/openai)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## GPT Terra Latest in other agents

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

## More Instinct guides

- [GPT Sol Latest](https://spiral.ai/integrations/instinct/gpt-sol-latest)
- [GPT-3.5 Turbo 0613](https://spiral.ai/integrations/instinct/gpt-3-5-turbo-0613)
- [GPT Mini Latest](https://spiral.ai/integrations/instinct/gpt-mini-latest)
- [GPT-4.1](https://spiral.ai/integrations/instinct/gpt-4-1)
- [GPT Luna Latest](https://spiral.ai/integrations/instinct/gpt-luna-latest)
- [GPT-4.1 mini](https://spiral.ai/integrations/instinct/gpt-4-1-mini)

## Questions about GPT Terra Latest in Instinct

**Can Instinct use GPT Terra Latest?**

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

**How much does GPT Terra Latest cost in Instinct?**

Up to $0.026682 per run at the default inputs. $1.30 per 1M input tokens, $0.065 per 1M cached input tokens, $1.625 per 1M cache write tokens, $6.50 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need an OpenAI account to use GPT Terra Latest in Instinct?**

You need no OpenAI account. Instinct uses one Spiral API key for every tool, and Spiral runs GPT Terra Latest on its own OpenAI account.

**How long does it take to set up GPT Terra Latest in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while GPT Terra Latest runs?**

GPT Terra Latest runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**Does GPT Terra Latest always use the same release?**

No. It follows the newest Terra release and currently points to GPT-6.1 Terra, so its behavior can change when that target changes.

**What is GPT Terra good at?**

The current release, GPT-6.1 Terra, is designed for product photo matching, technical drawing interpretation, application screen tasks, and writing. These are useful starting points for testing it on everyday work.

**How much material can GPT Terra handle?**

The current GPT-6.1 Terra target has a 1,050,000-token context window and can generate up to 128,000 output tokens. Those are separate limits, and future Terra updates may change them.

**Is GPT Terra suitable for difficult coding work?**

GPT-6.1 Terra can handle coding tasks such as investigating webpage layout shifts. OpenAI recommends GPT-6.1 Sol or GPT-6 Astra for the most complex coding tasks.

**Can GPT Terra analyze pictures?**

Yes. GPT Terra Latest accepts images and returns text, which supports tasks such as explaining a drawing or comparing a product photo with catalog descriptions.

