GPT-6.1 Terra
GPT-6.1 Terra is a large language model made by OpenAI, added to the catalog on 26 Oct 2026. It has a context window of 1,050,000 tokens and costs $1.00 per 1M input tokens and $5.00 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: drafting and revising text, working through coding requests and understanding screenshots.
Price checked ยท source: OpenRouter
What GPT-6.1 Terra is
OpenAI GPT-6.1 Terra is a multimodal model for everyday writing, coding, and agentic work. It accepts text, images, and files, and produces text. Its description specifically highlights screenshot understanding, making visual inputs relevant to tasks involving screenshots. The model can take supplied material together with a text prompt, then return a text response. The facts do not specify particular file types or image-processing limits.
Terra has a context window of 1,050,000 tokens and a maximum output of 128,000 tokens. This capacity suits prompts containing lengthy source material or tasks that require a long response, within the stated limits. It supports reasoning, tools, structured outputs, and response-format controls. These capabilities can support workflows where a request is accompanied by source material and a response must follow a specified structure, or where tools are part of the workflow.
The stated work areas are everyday agentic tasks, coding, and writing. Terra is relevant to drafting and revising text, working through programming requests, and handling tasks that may use tools. Image input and screenshot understanding add a visual dimension to these text-focused uses, while file input provides another way to supply material. The available facts do not name specific tools, programming languages, or structured formats, so those should not be inferred from the feature list.
Key features
- Accepts text, images, and files; produces text
- Has a context window of 1,050,000 tokens
- Supports reasoning and tool use
- Supports structured outputs and response-format controls
- The model description highlights screenshot understanding
Typical uses
- Drafting and revising text
- Working through coding requests
- Understanding screenshots
- Agentic workflows involving tools
- Preparing structured text responses
GPT-6.1 Terra pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $1.00 | $0.50 |
| Output, per 1M tokens | $5.00 | $2.50 |
| Cached input read, per 1M tokens | $0.05 | $0.025 |
| Cache write, per 1M tokens | $1.25 | $0.625 |
| Web search, per search | $0.01 | $0.01 |
| Input above 272,000 prompt tokens, per 1M | $2.00 | $1.00 |
| Output above 272,000 prompt tokens, per 1M | $7.50 | $3.75 |
| Variant | Model id |
|---|---|
| Batch | openai/gpt-6.1-terra:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 26 Oct 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0020 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.029 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.040 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.158 |
GPT-6.1 Terra specifications
| Model id | openai/gpt-6.1-terra |
|---|---|
| Version | gpt-6.1-terra-20261026 |
| Context window | 1,050,000 tokensAbout 787,500 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 26 Oct 2026 |
| Input types | file, image, text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for GPT-6.1 Terra yet.
Compare GPT-6.1 Terra
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.