Model · GPT
GPT-6.1 Terra: price, limits and messages on every plan
OpenAI's GPT-6.1 Terra in llmwise: how many GPT-6.1 Terra messages each plan gives, what counts against them, what GPT-6.1 Terra reads, where your messages go, and what it costs at OpenAI's API prices.
Prices and limits checked against OpenRouter's GPT-6.1 Terra page. Updated .
Short answer
GPT-6.1 Terra is in the 2-day free trial of Plus or Pro. A paid plan gives up to 125 GPT-6.1 Terra messages a month on Plus ($10), 250 on Pro ($20), 800 on Max ($50), 1,800 on Ultra ($100) and 4,000 on Studio ($200). Each GPT-6.1 Terra message's price is shown before you send it.
In the news: GPT-6.1 Terra is out: what changed, and what it costs you ().
What OpenAI announced, sourced on its launch page:
- OpenAI calls Terra a significant step up from its previous Terra model, for the communication and computer-based work that fills a workday, from drafting proposals and interpreting technical drawings to filling out forms and editing videos.
- Its standard API prices are $1 per million input tokens, $0.05 per million cached input tokens and $5 per million output tokens, 50% lower than GPT-6.1 Sol's and the previous Terra's.
- Cached input costs 5% of the input price; cache writes cost $1.25 per million tokens for 30-minute retention and $2.50 for 12-hour retention.
GPT-6.1 Terra on every plan
What GPT-6.1 Terra costs in llmwise is a count, not a token bill: up to 250 a month on Pro, and it's in the 2-day free trial of Plus or Pro.
| Plan | Price | GPT-6.1 Terra messages | Each, if all go to GPT-6.1 Terra |
|---|---|---|---|
| Plus | $10 a month | Up to 125 a month | $0.08 |
| Pro | $20 a month | Up to 250 a month | $0.08 |
| Max | $50 a month | Up to 800 a month | $0.06 |
| Ultra | $100 a month | Up to 1,800 a month | $0.06 |
| Studio | $200 a month | Up to 4,000 a month | $0.05 |
Prices don't include tax, which is added where it applies and shown before you pay. A paid plan's month is one allowance every model shares, so each GPT-6.1 Terra count is the most you get if all of it goes to GPT-6.1 Terra, and "each" is the plan's price divided by that count. How pricing works.
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Plus $3.75, Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.
GPT-6.1 Terra usage limits, explained
Every limit on GPT-6.1 Terra in llmwise is published. Here's each one, in GPT-6.1 Terra messages.
GPT-6.1 Terra draws on the monthly allowance every model shares: 250 GPT-6.1 Terra messages on Pro if nothing else uses it. Each message on a smaller model leaves fewer GPT-6.1 Terra messages, each GPT-6.1 Terra message leaves fewer for them, and unused GPT-6.1 Terra messages don't carry over when the billing period renews.
Long GPT-6.1 Terra chats count more, because each GPT-6.1 Terra reply resends the whole conversation. Past 64k tokens a GPT-6.1 Terra reply counts as 2 messages, so Pro's 250 GPT-6.1 Terra messages become up to 125 such replies; past 128k it counts as 4 (up to 62 GPT-6.1 Terra replies); past 200k the GPT-6.1 Terra chat is full.
GPT-6.1 Terra's native context window is 1.05M tokens; llmwise stops a GPT-6.1 Terra chat at 200k tokens, so a GPT-6.1 Terra chat uses at most 200k of its 1.05M tokens.
A GPT-6.1 Terra reply can run to 8,000 tokens on Plus and Pro and 16,000 on Max, Ultra, and Studio, at the same GPT-6.1 Terra price however long it runs.
On a paid plan each web search or link read in a GPT-6.1 Terra reply counts as 1 more GPT-6.1 Terra message.
A $10 top-up adds up to 200 more GPT-6.1 Terra messages, valid 12 months, spent once the plan's own GPT-6.1 Terra count is gone.
GPT-6.1 Terra replies share every plan's soft cap of 100 replies an hour with the other models.
What GPT-6.1 Terra reads and does
| Made by | OpenAI |
|---|---|
| Model at OpenRouter | openai/gpt-6.1-terra |
| Context window | 1.05M tokens |
| Longest chat in llmwise | 200k tokens |
| Images you attach | Reads them |
| PDFs you attach | Reads the whole file, charts and layout included |
| Tools (search, documents, code, apps) | Yes |
| Reasoning | On, at medium effort |
| API price, per million tokens | $1.00 in, $5.00 out |
| A typical message at API prices | $0.0075 |
| On Pro | Up to 250 a month |
Where your GPT-6.1 Terra messages go
A GPT-6.1 Terra message goes to OpenAI directly when llmwise can reach OpenAI, or through OpenRouter when it can't.
If OpenAI fails before a GPT-6.1 Terra reply starts (an overload, a server error, a dropped connection), llmwise resends the GPT-6.1 Terra request through OpenRouter, to endpoints that, according to OpenRouter, don't store prompts for their own use or train on them.
The Privacy Policy lists every company a GPT-6.1 Terra message can reach.
GPT-6.1 Terra's API price, and what a message costs
GPT-6.1 Terra's API price is $1.00 per million tokens in and $5.00 out: OpenAI's list price. At that price a typical GPT-6.1 Terra message (4,000 tokens in, 700 out) costs about $0.0075.
In llmwise a GPT-6.1 Terra message isn't billed by the token: it's one of up to 250 GPT-6.1 Terra messages a month on Pro, however long the GPT-6.1 Terra reply runs.
What GPT-6.1 Terra's replies cost in our test runs, job by job, and GPT-6.1 Terra beside the rest of its family: GPT-6.1 Terra pricing: API price, cost per message and plans.
When to use GPT-6.1 Terra, and when a cheaper model will do
llmwise's catalog describes GPT-6.1 Terra as “Fast, efficient GPT for images, computer use and writing”. No benchmark scores here: ask GPT-6.1 Terra your own question, then switch the picker to another model in the same chat, which sees GPT-6.1 Terra's answer too.
When a question doesn't need GPT-6.1 Terra, these read the same attachments, whole PDFs included, and leave more of the month for GPT-6.1 Terra:
GPT-6 Luna (OpenAI): 60 a day on Pro, against GPT-6.1 Terra's 250.
Claude Haiku 5.5 (Anthropic): 60 a day on Pro, against GPT-6.1 Terra's 250.
Same count as GPT-6.1 Terra on every plan: Claude Haiku 4.5, Gemini 3.8 Flash, DeepSeek V4 Pro, Grok 4.7, GLM 5.3 and Mistral Large 4.
GPT-6.1 Terra in our test runs
GPT-6.1 Terra passed 48 of our 50 test prompts, sent through llmwise's own pipeline and checked the same way for every model.
- Coding5 of 5 passed
- Writing5 of 5 passed
- Math5 of 5 passed
- Summarization5 of 5 passed
- Data analysis5 of 5 passed
- Customer support3 of 5 passed
- Translation5 of 5 passed
- SQL5 of 5 passed
- RAG and answering from documents5 of 5 passed
- Agents and tool use5 of 5 passed
How GPT-6.1 Terra began its reply to our first writing prompt, “Write a LinkedIn post of 100 to 150 words announcing that our small bakery, Crumb & Co., opens a second shop in Leeds on 14 November. Mention the free coffee…”:
We’re excited to share that Crumb & Co. is opening a second shop in Leeds on 14 November. What started as a small bakery has grown thanks to everyone who has bought a loaf, stopped in for a treat, or recommended us to a friend. We’re grateful for your support, and we can’t wait to welcome more of you through our doors. To celebrate, we’ll be serving free coffee on opening day. Whether you’ve been with us from the beginning or are discovering Crumb & Co. for the first time, we’d love to see you. Thank you for helping us reach this milestone. Here’s to the next chapter, and to many more good things shared over coffee and fresh bakes.
Questions
Is GPT-6.1 Terra free in llmwise?
For 2 days: GPT-6.1 Terra is in the 2-day free trial of Plus or Pro. Add a card at checkout; cancel before the trial ends and you pay nothing. One free trial per person. After the trial, Pro ($20 a month) gets up to 250 GPT-6.1 Terra messages a month.
What are GPT-6.1 Terra's usage limits in llmwise?
GPT-6.1 Terra has a published monthly count on each paid plan (up to 250 GPT-6.1 Terra messages a month on Pro), shared with the other models. A long GPT-6.1 Terra chat counts each reply as 2 GPT-6.1 Terra messages past 64k tokens and 4 past 128k.
What happens when my GPT-6.1 Terra messages run out?
Your GPT-6.1 Terra count resets when your billing period renews. Until then, the everyday models keep answering on their own daily count, and a $10 top-up adds up to 200 more GPT-6.1 Terra messages.
How much context does GPT-6.1 Terra have in llmwise?
1.05M tokens is GPT-6.1 Terra's native context window. A GPT-6.1 Terra chat in llmwise stops at 200k tokens, and past 64k each GPT-6.1 Terra reply counts as more than one message, so a new GPT-6.1 Terra chat for each new task goes further.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.
See what a message costs before you send it. Every plan starts with a 2-day free trial. Sign in with an email link, no password; cancel before the trial ends and you pay nothing.