gemini-2.5-pro-exp-03-25

Neural Network

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

/

Models

/

Text AI Models

/

gemini-2.5-pro-exp-03-25

Specifications

Input
text, images, documents
Output
text
Context size
1 000 000 tokens
Max answer length
32 000 tokens
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-2.5-pro-exp-03-25We 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-2.5-pro-exp-03-25',
  });
} 

// Async - Text generation 

async function main() {
  const stream = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'gemini-2.5-pro-exp-03-25',
    stream: true
  });

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

How it works gemini-2.5-pro-exp-03-25?

Bothubs gather information...empty

Frequently asked questions about gemini-2.5-pro-exp-03-25

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 Google text model with a one-million token context window. It accepts text, images, and documents as input, reasons before answering, and can call functions. It is suitable for working with code, analyzing large reports, and analytical tasks where context volume is important.

Up to 32,000 tokens in a single response — this is a large code module, a detailed document analysis, or a long analytical report. If the material doesn't fit, just ask for a continuation in the next message: the one-million token context will retain the entire previous conversation.

Yes, the reasoning mode is confirmed. The model builds a chain of intermediate steps before the final answer, so it is more accurate in mathematics, logic, and code debugging. On complex tasks, the result is more accurate, but you will have to wait a little longer than usual for the answer.

Yes, both function calling and structured JSON output are supported, so the model integrates into agent scenarios and data processing. In BotHub, this works via a unified OpenAI-compatible API: you connect once and change the model without rewriting the integration.

According to our data, text, images, and documents are accepted as input: send a screenshot, diagram, PDF, or table and ask to analyze the content. We have no notes regarding audio and video, so such files should be tested with a small example.

The Gemini line is multilingual, and the model works confidently with Russian queries: it maintains meaning and terminology even in long documents. How well it suits your task is easier to check in practice — in BotHub, you pay for the tokens actually consumed, without a subscription.

Support ServiceOpen from 10:00 to 18:00 MSK