Pareto 26.10 Preview
Neural Network
Pareto 26.10 Preview is a multimodal composite model for research tasks, programming, and agent scenarios.
Specifications
- Input
- text, images, documents
- Output
- text
- Context size
- 1 048 576 tokens
- Max answer length
- 131 072 tokens
- Capabilities
- 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: 'pareto-26.10-preview',
});
}
// Async - Text generation
async function main() {
const stream = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'pareto-26.10-preview',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works Pareto 26.10 Preview?
Pareto 26.10 Preview is a multimodal composite model designed for research tasks, programming, and agent scenarios, while also performing reliably on a wide range of everyday queries. The 'preview' prefix indicates a pre-release version: you are working with the model before its stable release. Multimodality removes the boundary between text and images within a single task, and the composite architecture helps guide it from the initial question to the final result. In BotHub, the model is available from Russia without a VPN or foreign card, with payment in rubles based on actual token usage, which does not expire. More than 250 models are available in the same window: you can compare answers or switch in a couple of clicks, and the unified OpenAI-compatible API means you don't need to rewrite integrations. Dialogues are encrypted, and companies have access to contracts, invoices, electronic document management (EDO), and an admin panel with limits. Use Pareto 26.10 Preview to analyze an unfamiliar codebase and refactor a module, build an agent for a multi-step process, conduct research and synthesize findings, or analyze a diagram or screenshot along with a problem statement.Frequently asked questions about Pareto 26.10 Preview
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.
This is a text model: it accepts text, images, and documents as input and outputs text. It is suitable for analyzing long materials, working with code and refactoring it, parsing screenshots and PDFs, as well as for analytics and drafting.
Up to 131,072 tokens per response — enough for a voluminous technical document, a large code module, or a detailed analysis. The context window is 1,048,576 tokens, so you can keep an entire project or archive of documents in the dialogue.
A separate reasoning mode is not noted in our data. However, you can ask the model to break down the task step-by-step directly in the prompt: this technique usually helps with math, logic, and code debugging tasks. Test it with your scenario.
Yes, the model supports function calling and structured JSON output. This allows you to connect it to external services, databases, and agent scenarios, obtaining a predictable response format. BotHub uses a unified OpenAI-compatible API, so you won't have to rewrite your integration.
According to our data, the model accepts images and documents: you can send an interface screenshot, diagram, chart, photo, or file and ask it to analyze the content. Input support for audio and video is not noted in the data; the model always returns the response as text.
We have no data on languages, so we cannot promise the quality of Russian — it is better to test it with your own tasks. This is convenient in BotHub: send the same request to several models in one window and compare the results.