---
title: "GPT-6.1 Terra — API access"
description: "GPT-6.1 Terra through Codex: a fast, efficient model for visual reasoning, computer use and natural writing, 872K maximum context and reasoning from none to max. Official $1/$5 per 1M input/output tokens; $0.50/$2.50 with the flat 50% discount."
url: "https://apitoken.sale/models/gpt-6-1-terra"
language: "en"
---
# GPT-6.1 Terra

GPT-6.1 Terra is the newest GPT model: fast and efficient for visual reasoning, computer use and natural writing, at half the GPT-6.1 Sol price, on the OpenAI-compatible endpoint. Choose reasoning effort from none to max, send images, and use structured outputs or function tools.

- **Model ID:** `gpt-6.1-terra`
- **Tier:** Balanced
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $1 input / $5 output
- **Your price (per 1M):** input $0.5, output $2.5 (flat 50% off)
- **Base URL:** `https://router.apitoken.sale/v1` · **Endpoints:** `POST /v1/responses`, `POST /v1/chat/completions` (Authorization: Bearer)

## Best for

- Image understanding and visual reasoning at a low price.
- Natural writing, everyday coding and agent steps with explicit effort control.
- Long sessions with repeated context: cached input is $0.05 per 1M.

## Notes

- This service uses GPT-6.1 Terra's Codex subscription limits: 872K maximum context. The larger direct OpenAI API window does not apply here.
- Discovery reports 872K total context, 128K output and 744K conservative input.
- Cached input bills at 5% of input, like GPT-6.1 Sol.
- Above 272K input tokens, the whole request uses 2× input/cache rates and 1.5× output rates. Fast (priority) uses 2× the applicable API rates.
- Codex-specific ultra delegation is not advertised.

## Call it

```bash
curl https://router.apitoken.sale/v1/responses \
  -H "Authorization: Bearer $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-6.1-terra", "input": "Reply with exactly: connected"}'
```

## FAQ

**What does GPT-6.1 Terra cost?**

Official rates per 1M tokens are $1 input, $0.05 cached input, $1.25 cache write and $5 output. With the normal 50% B2C discount, these are $0.50, $0.025, $0.625 and $2.50. OpenKeys uses the official rates.

**How is GPT-6.1 Terra different from GPT-6.1 Sol?**

GPT-6.1 Terra is a separate model with its own ID. OpenAI positions it as the fast, efficient choice for visual reasoning, computer use and natural writing; GPT-6.1 Sol targets complex coding and professional work. Every Terra rate is half the Sol rate, and Terra also accepts reasoning none. Both stay available; choose by model ID.

**How do I select GPT-6.1 Terra?**

Set model to gpt-6.1-terra on https://router.apitoken.sale/v1. Supported reasoning levels are none, low, medium, high, xhigh and max. Use service_tier priority for Fast.

---
API reference: https://apitoken.sale/md/docs · All models: https://apitoken.sale/md/models
