GPT-6.1 Terra — Specs, Pricing & Limits
In Codex with ChatGPT sign-in it needs Codex CLI 0.159.0 or later and is offered on Plus, Pro, Business, Enterprise and Edu, not in ChatGPT's Chat. With an API key it follows your API access.
Specs
| Status | Priced |
|---|---|
| Released (API changelog) | 2026-10-26 |
| Context window | 1,050,000 tokens |
| Max output | 128,000 tokens |
| Knowledge cutoff | Jun 01, 2026 |
| Reasoning effort levels | none, low, medium (default), high, xhigh, max |
| Long-context rule | >272,000 input tokens: 2x input and cache rates, 1.5x output (full request) |
| Cache writes | Billed at the cache-write rate instead of the input rate |
| ChatGPT credit rate (per 1M) | 25 in · 1.25 cached · 125 out |
Pricing per 1M tokens, every published service tier
| Standard — short context | in $1.00 · cached $0.05 · writes $1.25 · out $5.00 |
|---|---|
| Standard — long context | in $2.00 · cached $0.10 · writes $2.50 · out $7.50 |
| Batch — short context | in $0.50 · cached $0.025 · writes $0.625 · out $2.50 |
| Batch — long context | in $1.00 · cached $0.05 · writes $1.25 · out $3.75 |
| Flex — short context | in $0.50 · cached $0.025 · writes $0.625 · out $2.50 |
| Flex — long context | in $1.00 · cached $0.05 · writes $1.25 · out $3.75 |
| Fast — short context | in $2.00 · cached $0.10 · writes $2.50 · out $10.00 |
| Fast — long context | in $4.00 · cached $0.20 · writes $5.00 · out $15.00 |
| Cache writes, 12-hour lifetime | $2.50 Standard short · $5.00 long — 2.5× the tier's input rate, instead of 1.25× for the default 30-minute lifetime (Responses API) |
Rate limits by usage tier
| Free | Not supported |
|---|---|
| Build | 5,000 RPM · 1,000,000 TPM · 3,000,000 batch queue |
| Launch | 10,000 RPM · 4,000,000 TPM · 200,000,000 batch queue |
| Grow | 15,000 RPM · 40,000,000 TPM · 15,000,000,000 batch queue |
GPT-6.1 Terra arrived on October 26, 2026 as the second GPT-6.1 model, and OpenAI pitches it at a different job from GPT-6.1 Sol: fast, efficient work on images, screens and prose — matching photos to catalog entries, reading technical drawings, acting in an application's interface, drafting and revising text. On price it sits between GPT-6 Luna and GPT-6.1 Sol, below Sol on every Standard price cell and well above Luna.
It keeps the GPT-6.1 cache discount. A cached read bills at 0.05x its input rate, the deep discount it shares only with GPT-6.1 Sol, against 0.1x on most other models. Cache writes follow the GPT-5.6-and-later rule, at their own rate rather than on top of input, and the 12-hour lifetime is available too.
Two things set it apart from its sibling. It accepts every effort level from none to max, with medium as the default — GPT-6.1 Sol starts at low — and its knowledge cutoff is the newest of any model this site prices. It has no Ultrafast row. Tool calling needs the Responses API, though plain requests work through Chat Completions too. Its rate-limit table is the one OpenAI's guide shares across Astra, Sol and Terra, batch-queue column included, and it supports only US and EU data residency, with Fast mode available under EU residency.
In Codex it's offered on Plus, Pro, Business, Enterprise and Edu — in Work and Codex, not ChatGPT's Chat — and needs CLI 0.159.0 or later: run codex -m gpt-6.1-terra. OpenAI's five-hour usage estimates for Plus put it between GPT-6.1 Sol and GPT-6 Luna. GPT-6.1 Sol vs GPT-6.1 Terra and GPT-6.1 Terra vs GPT-6 Luna compare it with its neighbors, and the GPT-5.6 Terra migration covers moving from the older Terra.
The tables above are computed from this site's facts module: every published service tier with both context bands, the effort levels, and the rate-limit table.
Verified 2026-10-28 against https://developers.openai.com/api/docs/models/gpt-6.1-terra.
Could not confirm: No Ultrafast price or limit is published for GPT-6.1 Terra. Codex's model page lists the desktop app, ChatGPT Work on the web, the CLI, credits and API access for it but not the IDE extension, while its pricing page's feature matrix says only that Terra is available on each plan — so IDE-extension support is not claimed here either way.
Checked: https://developers.openai.com/api/docs/models/gpt-6.1-terra · https://developers.openai.com/api/docs/pricing · https://developers.openai.com/api/docs/changelog · https://developers.openai.com/api/docs/guides/latest-model · https://learn.chatgpt.com/docs/models · https://learn.chatgpt.com/docs/pricing