GPT 6.1 Terra
Neural Network
OpenAI's GPT 6.1 Terra is a mid-sized model for daily agent scenarios, programming, and text tasks.
Specifications
- Input
- text, images, documents
- Output
- text
- Context size
- 1 050 000 tokens
- Max answer length
- 128 000 tokens
- Reasoning effort
- none, low, medium, high, extra high, max
- Capabilities
- reasoning, function calling
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
import OpenAI from 'openai';
const openai = new OpenAI({
apiKey: '<your bothub access token>',
baseURL: 'https://openai.bothub.chat/v1'
});
// Sync - Text generation
async function main() {
const chatCompletion = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'gpt-6.1-terra:batch',
});
}
// Async - Text generation
async function main() {
const stream = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'gpt-6.1-terra:batch',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works GPT 6.1 Terra?
GPT 6.1 Terra is a mid-sized model in the OpenAI GPT 6.1 series. It excels at daily agent scenarios, programming, and text processing, with particularly strong screenshot analysis capabilities: interfaces, tables, charts, and on-screen errors. In BotHub, the model is accessible without a VPN or foreign card, payment is in rubles based on actual usage, and tokens do not expire. Over 250 models are available in one window, making it easy to compare responses and switch without rewriting integrations. Developers benefit from a unified OpenAI-compatible API, while teams get contracts, invoices, electronic document management, an admin panel, and limits. Data is protected by AES-GCM encryption and is not stored. Terra is great for writing and refactoring code, debugging via error screenshots, building agents, automating routine tasks, drafting business letters and articles, analyzing tables and interface layouts, and verifying data from images against reports.Frequently asked questions about GPT 6.1 Terra
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
The model is designed for long and voluminous tasks: a context of up to 1,050,000 tokens allows loading an entire document or codebase. It accepts images and documents, can reason, and call functions. The batch format is convenient for streaming processing of large sets of similar requests.
In a single response, the model outputs up to 128,000 tokens—a large volume sufficient for detailed analysis, a long document, or a significant code fragment. If more is needed, it is better to break the task into parts and submit them sequentially to maintain coherence.
Yes, reasoning mode is a confirmed capability of the model. Before the final answer, it works through solution steps, which is useful for math, logic, data analysis, and complex code analysis. It is not necessary for simple queries, but it usually improves accuracy.
Yes, both features are supported: the model supports function calling and structured JSON output. This means it can be embedded into an application where it accesses external tools and returns results in a machine-readable format—convenient for integrations, parsing, and process automation.
You can input images and documents—this is confirmed by our data. Audio and video are not listed among the input formats, so you should not rely on them. If you need to recognize speech or analyze a video recording, it is better to use a separate model for that task.
There is no separate quality assessment for Russian in our data, so we cannot promise record-breaking accuracy. The model works with text in various languages, but for complex tasks—legal, technical, stylistic—you should test it with your own examples and compare the result with another model in the same window.