gemini-3.5-live-translate-preview

Neural Network

Beep-boop, writing text for you...
pc1pc2pc3pc4
Main

/

Models

/

Audio AI Models

/

gemini-3.5-live-translate-preview

Specifications

Input
text, images, documents
Output
text, audio
Reasoning effort
low, medium, high
Capabilities
reasoning, function calling
160 $

Prompt cost

(per 1M tokens)

160 $

Answer cost

(per 1M tokens)

0,16 $

Image prompt

(per 1K tokens)

*Prices are shown for API usage via ECO providers.
bothub
BotHub: Try neural networks for freebot

Caps remaining: 0 CAPS
Code example and API for gemini-3.5-live-translate-previewWe offer full access to the OpenAI API through our service. All our endpoints fully comply with OpenAI endpoints and can be used both with plugins and when developing your own software through the SDK.Create API key
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: 'gemini-3.5-live-translate-preview',
  });
} 

// Async - Text generation 

async function main() {
  const stream = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'gemini-3.5-live-translate-preview',
    stream: true
  });

  for await (const chunk of stream) {
    const part: string | null = chunk.choices[0].delta?.content ?? null;
  }
} 
main();

How it works gemini-3.5-live-translate-preview?

Bothubs gather information...empty

Frequently asked questions about gemini-3.5-live-translate-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.

The model works with text, accepts documents and images as input, reasons before answering, and can voice the result. The context window is 65,536 tokens, with up to 32,000 in the response. It is suitable for file analysis, screenshot analytics, dialogue scenarios, and agents with external tool calling.

The output is text and audio: according to our data, the model can generate sound in addition to a standard response. The limit for a single response is 32,000 tokens, which is enough for a long analysis, translation of a large fragment, or a voiceover script. Structured JSON output is also supported.

Yes, reasoning before answering is confirmed in our data. The model first analyzes the condition and then provides the result — this is noticeable in multi-step tasks: matching data from a document, logic, calculations, and parsing contradictory formulations. For simple queries, the difference will be smaller.

Yes, the model supports function calling and structured JSON output — you can connect it to your services, databases, and external APIs, receiving predictable fields instead of free text. In BotHub, this works via a unified OpenAI-compatible API, so changing the model does not break the integration.

Images and documents — yes, this is confirmed: you can send a screenshot, diagram, photo of a page, or file and ask for an analysis. Audio and video input is not noted in our data, so such formats should be tested on your own. The context is 65,536 tokens for everything combined.

The language of prompts and responses is not described in our data, so we will not promise specific quality for Russian — it is easier to send a couple of your typical queries and compare. The BotHub interface is in Russian, payment is in rubles with Russian cards, and access is available without a VPN or foreign card.

Support ServiceOpen from 10:00 to 18:00 MSK