GPT Terra Latest
GPT Terra Latest is a large language model made by OpenAI, added to the catalog on 11 Sep 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: reviewing long documents, answering questions about supplied images and summarising files and text.
Price checked ยท source: OpenRouter
What GPT Terra Latest is
OpenAI: GPT Terra Latest is an endpoint that always redirects to the latest model in the GPT Terra family. It accepts text, images, and files, and produces text. The catalog lists support for reasoning, tools, structured outputs, and response formats. These capabilities suit requests that combine supplied material with a need for a reasoned answer, a tool-enabled workflow, or a response arranged in a specified structure. Because the endpoint follows the latest model in its family, it does not point to one fixed GPT Terra version.
The model has a context window of 1,050,000 tokens and can produce up to 128,000 output tokens. That context size suits work involving long source material or multiple supplied items in one interaction, while the output limit allows room for extended responses. Its image and file inputs can be used alongside text, making it relevant to tasks such as reviewing documents, answering questions about provided images, and bringing information from supplied materials into a written response. Text output can be requested as prose or, with structured-output and response-format support, in an organized form. Tool support is listed, although the catalog does not specify particular tools or workflows. The available facts identify the input types, output type, context capacity, and supported features, but do not name a specific version because the endpoint redirects within the family. It is therefore suited to flexible text tasks that rely on mixed inputs and substantial context.
Key features
- Accepts text, images, and files
- Produces text
- Has a 1,050,000-token context window
- Supports reasoning, tools, and structured outputs
- Allows up to 128,000 output tokens
Typical uses
- Reviewing long documents
- Answering questions about supplied images
- Summarising files and text
- Producing structured text responses
GPT Terra Latest pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $1.00 |
| Output, per 1M tokens | $5.00 |
| Cached input read, per 1M tokens | $0.05 |
| Cache write, per 1M tokens | $1.25 |
| Web search, per search | $0.01 |
| Input above 272,000 prompt tokens, per 1M | $2.00 |
| Output above 272,000 prompt tokens, per 1M | $7.50 |
No price change since it was added on 11 Sep 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 Terra Latest specifications
| Model id | ~openai/gpt-terra-latest |
|---|---|
| Version | gpt-terra-latest |
| Context window | 1,050,000 tokensAbout 787,500 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 11 Sep 2026 |
| Input types | file, image, text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not 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 Terra Latest yet.
Compare GPT Terra Latest
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.