Apodex 1.1 Mini
Neural Network
Apodex 1.1 Mini is an Apodex model for complex research and forecasting: files, data, code, and tools.
Specifications
- Input
- text, documents
- Output
- text
- Context size
- 262 144 tokens
- Max answer length
- 235 929 tokens
- Reasoning effort
- low, medium, high
- Capabilities
- reasoning, function calling
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: 'apodex-1.1-mini:free',
});
}
// Async - Text generation
async function main() {
const stream = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'apodex-1.1-mini:free',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works Apodex 1.1 Mini?
Apodex 1.1 Mini is an Apodex model designed primarily for reasoning. Its profile is long, multi-step tasks: research, analytics, and forecasting, where a verifiable result is needed rather than a quick answer. The model works directly with files, data, code, and tools, making it convenient for research pipelines. Through BotHub, the model is available from Russia without a VPN or foreign card: pay in rubles as you go for tokens that do not expire, and switch between models in one window without rewriting integrations. For teams, there is a unified OpenAI-compatible API and corporate terms: contract, invoice, EDI, admin panel, limits; data is protected by AES-GCM encryption and is not saved. Typical scenarios include reviews and benchmarks of document arrays, forecasts based on tables, code analysis and repository work, and hypothesis testing via calculations. It helps analysts compile reports, developers review third-party code, and researchers build long chains of steps without losing logic.Frequently asked questions about Apodex 1.1 Mini
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 works with text and documents: parsing long files, writing and refactoring code, analytics, drafts, and rewriting materials. The context is 262,144 tokens, so a large project or voluminous documentation fits into a single dialogue. Access in BotHub is without VPN, payment via Russian cards.
The output limit is 235,929 tokens per response. This is enough for a large document, detailed analysis, or an entire voluminous code file without splitting it into parts. If the response cuts off, just ask it to continue — the model will finish from where it stopped.
Yes, the reasoning mode is confirmed: before answering, the model builds a chain of steps. This helps with logic, math, and code debugging tasks where it is important not to guess, but to consistently break down the condition. For complex queries, the response takes a bit longer but is more accurate.
Yes, function calling and structured JSON output are supported. The model can be connected to external services, databases, and custom tools, receiving responses in a specified schema. In BotHub, this works via a unified OpenAI-compatible API, so switching models will not require rewriting the integration.
According to our data, text and documents are accepted as input: you can attach a file and request an analysis, summary, or answers based on its content. For images, audio, and video, BotHub has specialized models — you can switch between them in the same window and via the same API.
We do not have confirmed data on the quality of Russian in this model, so we will not make any promises. The easiest way to check is with your own task: send a typical query and compare it with other models in BotHub — switching takes a couple of seconds, and you only pay for the tokens used.