# GPT-6.1 Terra vs GPT-6.1 Sol: price, specs and which to pick

Canonical: https://theagenticweekly.com/compare/gpt-6-1-terra-vs-gpt-6-1-sol · Last verified: 2026-10-26 · Published: 2026-10-26 · Author: Agentic Weekly (operated independently from Texas, US) · Evidence: Evidence: Reported. Every fact is read from the vendor pages listed under Sources on 2026-10-26 (America/Chicago). We have not run these models for this page.

> GPT-6.1 Terra is OpenAI's cheaper, faster model at $1 per million input tokens and $5 per million output tokens, half of GPT-6.1 Sol's $2 and $10, with the same 1,050,000-token context window. OpenAI says to keep Sol for the most complex coding work and use Terra for writing, visual work, computer use and scoped code fixes. Last verified 2026-10-26 (America/Chicago).

## GPT-6.1 Terra vs GPT-6.1 Sol at a glance

Both models are in OpenAI's GPT-6.1 line, take text and images, return text, and share a 1,050,000-token context window and 128,000-token output limit. The differences are price, release date, knowledge cutoff, which reasoning-effort levels exist, and where each is offered. Full facts: [GPT-6.1 Terra](https://theagenticweekly.com/models/gpt-6-1-terra) and [GPT-6.1 Sol](https://theagenticweekly.com/models/gpt-6-1-sol).

Table: GPT-6.1 Terra and GPT-6.1 Sol, read from OpenAI's model pages and changelog on 2026-10-26

|  | GPT-6.1 Terra | GPT-6.1 Sol |
|---|---|---|
| Released (API changelog) | 2026-10-26 | 2026-09-29 |
| API model id | `gpt-6.1-terra` | `gpt-6.1-sol` |
| Input price, per 1M tokens | $1 | $2 |
| Cached input, per 1M tokens | $0.05 | $0.10 |
| Cache writes, per 1M tokens | $1.25 (30-minute retention) | $2.50 |
| Output price, per 1M tokens | $5 | $10 |
| Prompts over 272K input tokens | 2x input and cache rates, 1.5x output, for the full request | Same rule |
| Batch and Flex | 50% lower than Standard | 50% lower than Standard |
| Fast mode | 2x Standard | 2x Standard |
| Ultrafast mode | Not listed on its model page | 6x Standard |
| Context window / max input / max output | 1,050,000 / 922,000 / 128,000 tokens | 1,050,000 / 922,000 / 128,000 tokens |
| Modalities | Text and image in, text out | Text and image in, text out |
| Knowledge cutoff | Jun 01, 2026 | Apr 30, 2026 |
| Reasoning effort levels | none, low, medium (default), high, xhigh, max | low, medium (default), high, xhigh, max |
| OpenAI's one-line pitch | "A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing." | "Near-Astra performance for complex work at a lower cost." |

Sources for the table: OpenAI's [Terra model page](https://developers.openai.com/api/docs/models/gpt-6.1-terra), [Sol model page](https://developers.openai.com/api/docs/models/gpt-6.1-sol) and [API changelog](https://developers.openai.com/api/docs/changelog). Prices are standard processing in US dollars.

## Cost per task, not cost per token

Terra's list price is exactly half of Sol's on every token type. That does not make every job half the price, because a model that needs more tokens, retries or a higher reasoning effort can erase the gap. The arithmetic below is illustrative: it assumes both models use the same number of tokens, which OpenAI does not claim.

Table: Illustrative list-price cost of one job: 200,000 uncached input tokens and 20,000 output tokens, same token counts for every model (our arithmetic, not a measurement)

| Model | Input cost | Output cost | Job total |
|---|---|---|---|
| GPT-6.1 Terra | $0.20 | $0.10 | $0.30 |
| GPT-6.1 Sol | $0.40 | $0.20 | $0.60 |
| Claude Opus 5.5 (for reference, [compared here](https://theagenticweekly.com/compare/gpt-6-1-terra-vs-claude-opus-5-5)) | $0.80 | $0.40 | $1.20 |

Reported by one user, not verified by us: an X post on 2026-10-26 by [EnvolDev](https://x.com/EnvolDev/status/2114834080122761701) gives one run of the same prompt as Opus 5.5 at $31.85 and 2h 45m, Sol at $3.62 and 43m, and Terra at $4.90 and 43m. The post states no reasoning-effort settings or task description beyond a prompt name, it is a single run, and it shows Sol cheaper than Terra on that run. Treat it as a reminder to measure your own task, not as a result.

Formula to use: cost per completed task = (input tokens x input price + output tokens x output price) per attempt, times the average number of attempts needed to pass your own check. Anthropic's [cost and intelligence guide](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence) makes the same point about measuring completed tasks.

## What OpenAI says about the difference

These are OpenAI's own claims from its launch post (read through the Internet Archive because openai.com blocks scripted fetches), its model-selection guide and its Codex models page. We have not reproduced any of them.

- Speed: the launch post says Terra completes tasks over three times faster than both GPT-6 Astra and GPT-6.1 Sol.
- Price: the launch post says Terra's standard API prices are 50% lower than GPT-5.6 Terra's and GPT-6.1 Sol's.
- Coding: the launch post gives Terra 50.3% on Terminal-Bench 4.0 at maximum reasoning effort, and says "For the most complex coding tasks, GPT-6.1 Sol and GPT-6 Astra remain the better choice." We did not find a Sol figure for the same benchmark in the post's text.
- Science agents: on Terminal-Bench-Science 0.1 at max reasoning, the post says Terra surpasses Sol at lower cost.
- Where to start: OpenAI's [model-selection guide](https://developers.openai.com/api/docs/guides/model-selection) suggests Terra for concise writing from supplied material, computer-use tasks with a defined outcome and scoped code fixes, and Sol for complex projects where cost matters, such as a board presentation from financial results or a website from a product brief. It tells you to compare Terra with Sol on the same inputs and reasoning effort.

Details for Terra are in our [GPT-6.1 Terra news brief](https://theagenticweekly.com/news/openai-gpt-6-1-terra-computer-use).

## Where each model is available

Table: Availability from OpenAI's Codex models page and GitHub's changelog, read 2026-10-26

| Surface | GPT-6.1 Terra | GPT-6.1 Sol |
|---|---|---|
| OpenAI API | Yes, `gpt-6.1-terra` | Yes, `gpt-6.1-sol` |
| ChatGPT Work and Codex (plans) | OpenAI says Plus, Pro, Enterprise and Edu users from launch | OpenAI's Codex page names it as the GPT-5.5 replacement on Plus, Pro, Business, Enterprise and Edu plans when available |
| Codex CLI | Yes, needs Codex CLI 0.159.0 or later (`codex -m gpt-6.1-terra`) | Yes (`codex -m gpt-6.1-sol`) |
| Codex IDE extension | Not listed for Terra on OpenAI's page | Listed |
| GitHub Copilot | Generally available to Pro, Pro+, Max, Business and Enterprise, gradual rollout | Listed as generally available in GitHub's supported-models table |

OpenAI's launch post also says that in ChatGPT Work and Codex the same usage allowance covers more tasks with Terra than with Sol or Astra. For a full tool-by-tool matrix see [which coding agents can use GPT-6.1 Terra](https://theagenticweekly.com/guides/gpt-6-1-terra-in-coding-agents).

## Which should you pick?

These are our editorial rules of thumb built on OpenAI's guidance, not test results.

- Start with Terra when the task is scoped, has a way to verify the result (tests, a saved record, a checklist), and you run it often enough that half the per-token price matters.
- Start with Sol when the task is long, ambiguous or multi-file, when a wrong attempt is expensive, or when OpenAI's own guidance says to keep Sol, such as the most complex coding work.
- Escalate rather than guess: run the same inputs on Terra first at the same reasoning effort, and move up to Sol only on the tasks that fail your check.
- Check the 272K-token line: above 272,000 input tokens both models bill the whole request at 2x input and 1.5x output, so the 2:1 price ratio holds but both cost more per request.
- If you also consider Anthropic's models, see [GPT-6.1 Terra vs Claude Opus 5.5](https://theagenticweekly.com/compare/gpt-6-1-terra-vs-claude-opus-5-5) and our [best LLM for coding](https://theagenticweekly.com/best/llm-for-coding) page.

## What we have not tested

We have not run either model for this page. No speed, quality, token-efficiency or cost-per-task number here is ours. Benchmark names and scores are OpenAI's, from its own post, and OpenAI's charts are not copied because their values are not in the page text.

## FAQ

### Is GPT-6.1 Terra cheaper than GPT-6.1 Sol?

Yes per token: Terra is $1 input, $0.05 cached input and $5 output per million tokens, against $2, $0.10 and $10 for Sol, from OpenAI's model pages on 2026-10-26. Cost per finished task depends on how many tokens and attempts each model needs, which we have not measured.

### Is GPT-6.1 Terra as good as GPT-6.1 Sol?

OpenAI says Sol remains the better choice for the most complex coding tasks and that Terra surpasses Sol on one science-agent benchmark at lower cost. We have not run either, so we cannot say which is better for your task; compare them on your own inputs at the same reasoning effort.

### Do Terra and Sol have the same context window?

Yes. OpenAI lists 1,050,000 tokens of context, 922,000 maximum input tokens and 128,000 maximum output tokens for both.

### Can I use GPT-6.1 Terra in GitHub Copilot?

GitHub says Terra is generally available in Copilot for Pro, Pro+, Max, Business and Enterprise users, with a gradual rollout. Details are in our [coding-agent availability guide](https://theagenticweekly.com/guides/gpt-6-1-terra-in-coding-agents).

### Which model is newer?

Terra, released 2026-10-26 per OpenAI's API changelog. Sol was released 2026-09-29. Terra also has the later knowledge cutoff: Jun 01, 2026 against Apr 30, 2026.

## Sources

- [OpenAI API: GPT-6.1 Terra model page](https://developers.openai.com/api/docs/models/gpt-6.1-terra) (fetched 2026-10-26)
- [OpenAI API: GPT-6.1 Sol model page](https://developers.openai.com/api/docs/models/gpt-6.1-sol) (fetched 2026-10-26)
- [OpenAI API changelog](https://developers.openai.com/api/docs/changelog) (fetched 2026-10-26)
- [OpenAI: model selection guide](https://developers.openai.com/api/docs/guides/model-selection) (fetched 2026-10-26)
- [OpenAI: Introducing GPT-6.1 Terra (Internet Archive capture; openai.com blocks scripted fetches)](https://web.archive.org/web/20261026180514/https://openai.com/index/introducing-gpt-6-1-terra/) (fetched 2026-10-26)
- [OpenAI: Codex and ChatGPT Work models](https://developers.openai.com/codex/models) (fetched 2026-10-26)
- [GitHub changelog: GPT-6.1 Terra in GitHub Copilot](https://github.blog/changelog/2026-10-26-gpt-6-1-terra-in-github-copilot/) (fetched 2026-10-26)
- [GitHub Docs: supported AI models in Copilot](https://docs.github.com/en/copilot/reference/ai-models/supported-models) (fetched 2026-10-26)
- [Anthropic: optimizing for cost and intelligence](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence) (fetched 2026-10-26)
- [EnvolDev on X: Opus 5.5 vs Sol vs Terra (one user's unverified run)](https://x.com/EnvolDev/status/2114834080122761701) (fetched 2026-10-26)

## Related

- [GPT-6.1 Terra: facts and sources](https://theagenticweekly.com/models/gpt-6-1-terra)
- [GPT-6.1 Sol: facts and sources](https://theagenticweekly.com/models/gpt-6-1-sol)
- [GPT-6.1 Terra vs Claude Opus 5.5](https://theagenticweekly.com/compare/gpt-6-1-terra-vs-claude-opus-5-5)
- [Which coding agents can use GPT-6.1 Terra](https://theagenticweekly.com/guides/gpt-6-1-terra-in-coding-agents)
- [Best LLM for coding](https://theagenticweekly.com/best/llm-for-coding)
- [Codex CLI](https://theagenticweekly.com/tools/codex-cli)

## Changelog

- 2026-10-26: First published. OpenAI model pages, API changelog, Codex models page and GitHub's Copilot changelog read on this date; nothing was run.

## How to cite

Agentic Weekly, "GPT-6.1 Terra vs GPT-6.1 Sol: price, specs and which to pick", last updated 2026-10-26, https://theagenticweekly.com/compare/gpt-6-1-terra-vs-gpt-6-1-sol