Gemini 2.5 Pro

Name: Gemini 2.5 Pro
Brand: Google DeepMind
SKU: gemini-2-5-pro
Price: 1.5 USD
Availability: InStock

Tekst i chatStarija verzijaDostupno

od Google DeepMindgemini-2-5-pro

Google's latest thinking model. Excels at reasoning, coding, math, and science with massive context window.

Isprobaj Preuzmi API ključ Usporedi

Cijena · 1M ulaz/izlaz: 1,50 US$ / 12,00 US$
Kontekst: 1.000.000 tokena
Maks. izlaz: 65.536 tokena
Ulaz → izlaz: Tekst → Tekst
Razvojni inženjer: Google DeepMind
Ažurirano: 23. septembar 2026.

Ovo je starija verzija modela.

Playground

Isprobaj Gemini 2.5 Pro

Razgovor

1,50 US$/1M in

Pošalji poruku. Odgovor stigne u cijelosti kada je model gotov (bez streaminga).

Maks. duljina odgovora (tokeni)

⌘/Ctrl + Enter

Ovaj pokus

najviše 0,0123 US$ · 1,23 kredita rezervirano

Naplata se vrši prema stvarno korištenim tokenima; nekorišteni dio rezervacije se vraća.

Novi si ovdje?

10 besplatnih kredita (0,10 US$) kada se registriraš s Googlom

Dostupno 24 sati nakon registracije, do 5 pokusa dnevno i najviše 2 kredita po pokusu. Ostale metode prijave počinju bez kredita. Dovoljno za 8 pokretanja ovog modela.

O Gemini 2.5 Pro

UkratkoStanje: 23. septembar 2026.

Gemini 2.5 Pro je model od Google DeepMind iz kategorije Tekst i chat. Na Railwailu, Gemini 2.5 Pro košta 1,50 US$ po 1M ulaznih tokena i 12,00 US$ po 1M izlaznih tokena. Kontekstni prozor sadrži 1.000.000 tokena, a jedan odgovor može biti dugačak do 65.536 tokena.

Pozadina

O Google DeepMind

Osnovano 2010 · Mountain View, USA / London, UK

Google DeepMind is the merged AI research organisation formed in April 2023 by combining Google Brain (founded inside Google in 2011) with DeepMind (founded in London in 2010 by Demis Hassabis, Shane Legg and Mustafa Suleyman, acquired by Google in 2014). Demis Hassabis leads the unit as CEO. DeepMind authored seminal papers including 'Attention Is All You Need' (Google Brain, 2017), AlphaGo (2016), AlphaFold (2018-2021, awarded the 2024 Nobel Prize in Chemistry), AlphaZero, Chinchilla scaling laws and the Gemini Technical Report. The Gemini family launched in December 2023 (Ultra, Pro, Nano), followed by Gemini 1.5 Pro with 1M+ context and the Mixture-of-Experts architecture in early 2024, Gemini 2.0 Flash (December 2024) and Gemini 2.5 Pro (released March 2025, generally available May 2025) which introduced a built-in 'Deep Think' reasoning mode. Google DeepMind also ships Imagen, Veo, Lyria, NotebookLM and powers AI features across Google Search, Workspace and Android.

Posjetite Google DeepMind

Arhitektura

Sparse Mixture-of-Experts Transformer (natively multimodal, reasoning)

Gemini 2.5 Pro is Google DeepMind's flagship reasoning model released as preview in March 2025 and generally available in May 2025. It is a natively multimodal Sparse Mixture-of-Experts (MoE) Transformer that ingests text, image, audio and video tokens through a shared embedding space, building on the architecture introduced in Gemini 1.5 Pro. Pretraining used Google's TPU v5p infrastructure on a multi-trillion-token corpus mixing web text, code, books, scientific papers, image-text pairs, audio and YouTube video frames, with a knowledge cutoff of January 2025. Post-training combined supervised fine-tuning, RLHF and reinforcement learning against verifiable rewards for math and code, plus a new 'Deep Think' training stage that teaches the model to allocate test-time thinking budgets and emit long internal chains-of-thought before the final answer. Deep Think is exposed to developers as a toggle and was the headline capability at launch, pushing Gemini 2.5 Pro to the top of the Chatbot Arena leaderboard for the first time for Google. The model supports a 1,048,576-token context window with native handling of long PDFs, hour-long videos and full code repositories. Tool use, function calling, structured output and grounding with Google Search are first-class. Safety training included red-teaming under Google's Frontier Safety Framework.

Parametri: Undisclosed (sparse MoE, total parameters in the hundreds of billions, active per-token undisclosed)
Kontekst: 1.048.576 tokena

Mogućnosti

1,048,576 token context window (~1M tokens) with native long-video and long-audio support
Built-in Deep Think reasoning mode with adjustable thinking budget
Natively multimodal: text, image, audio and video in a single pass
Top scores on GPQA Diamond, AIME 2025 and Humanity's Last Exam
Strong coding performance on SWE-bench Verified and LiveCodeBench
Function calling, JSON schema, parallel tool calls
Grounding with Google Search built into the API
Native execution of code via the Code Execution tool
Cross-lingual reasoning across 100+ languages
Available via Vertex AI, AI Studio, and the Gemini app
Best for: scientific reasoning, long-document and long-video analysis, coding, agentic workflows.

Obuka i licenca

Pretrained on a multi-trillion-token mixture of web text, code, books, scientific papers, licensed third-party text, audio waveforms, image-text pairs and video frames. Knowledge cutoff is January 2025. Post-training uses supervised fine-tuning, RLHF, RL against verifiable rewards and Deep Think reasoning training.

Licenca: Proprietary commercial license via Google AI Studio, Vertex AI and the Gemini app. Commercial use permitted under Google Cloud terms.

Testiranje sigurnosti: Evaluated under Google DeepMind's Frontier Safety Framework v2 covering CBRN, cyber, persuasion and ML R&D risks, with internal red teams and external evaluators.

Poznata ograničenja

Deep Think adds significant latency and token cost
Long context recall quality degrades beyond ~500K tokens for some tasks
Vision occasionally misreads dense tables and handwriting
Knowledge cutoff January 2025
Region availability varies and is not yet in all EU regions for some features

Znanstveni članci

Cijene

Cijene u USD-u. Korištenje se naplaćuje iz unaprijed plaćenih kredita.

Ulaz	1,50 US$ / 1M tokena
Izlaz	12,00 US$ / 1M tokena
Ulaz (upiti preko 200.000 tokena)	3,00 US$ / 1M tokena
Izlaz (upiti preko 200.000 tokena)	18,00 US$ / 1M tokena

Naplaćuje se prema tokenima koje svaki zahtjev zapravo koristi.
1 kredit = 0,01 US$

Kalkulator troškova

Kalkulator cijena

Ulazni tokeni

/ zahtjev

Izlazni tokeni

/ zahtjev

Zahtjevi

Ukupno

0,75 US$

75 kredita

Po zahtjevu

0,0075 US$ · 0,75 kredita

Svaki zahtjev se zaokružuje na 0,01 kredita.

API

Pozovi Gemini 2.5 Pro sa svojim Railwail API ključem. Koristi ovaj ID modela u zahtjevu:

gemini-2-5-proPogledaj API dokumentaciju Dobij API ključ

curl https://railwail.com/api/v1/chat/completions \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2-5-pro",
    "messages": [
      {
        "role": "user",
        "content": "Explain what a vector database is in two sentences."
      }
    ],
    "max_tokens": 1024
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RAILWAIL_API_KEY"],
    base_url="https://railwail.com/api/v1",
)

completion = client.chat.completions.create(
    model="gemini-2-5-pro",
    messages=[
        {
            "role": "user",
            "content": "Explain what a vector database is in two sentences.",
        },
    ],
    max_tokens=1024,
)

print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RAILWAIL_API_KEY,
  baseURL: "https://railwail.com/api/v1",
});

const completion = await client.chat.completions.create({
  model: "gemini-2-5-pro",
  messages: [
    {
      role: "user",
      content: "Explain what a vector database is in two sentences."
    }
  ],
  max_tokens: 1024
});

console.log(completion.choices[0].message.content);

// npm install railwail
import railwail from "railwail";

const rw = railwail(process.env.RAILWAIL_API_KEY);

const res = await rw.chat("gemini-2-5-pro", [
  { role: "user", content: "Explain what a vector database is in two sentences." },
], { max_tokens: 1024 });

console.log(res.choices[0].message.content);

Postavite ključ kao RAILWAIL_API_KEYKreiraj API ključ

Specifikacije

ID modela: gemini-2-5-pro
Razvojni inženjer: Google DeepMind
Kategorija: Tekst i chat
Ulaz: Tekst
Izlaz: Tekst
Kontekstni prozor: 1.000.000 tokena
Maks. izlaz: 65.536 tokena
Naplata: Po potrošnji (tokeni ili GPU vrijeme)
Životni ciklus: Starija verzija
Veličina modela: Undisclosed (sparse MoE, total parameters in the hundreds of billions, active per-token undisclosed)
Licenca: Proprietary commercial license via Google AI Studio, Vertex AI and the Gemini app. Commercial use permitted under Google Cloud terms.
Katalog ažuriran: 23. septembar 2026.

Oznake

reasoning
coding
multimodal

Primjer promptova

Primjeri iz Railwail kataloga. Nisu generirani uživo na ovoj stranici.

Scientific Analysis
Explain CRISPR-Cas9 gene editing: how it works, current medical applications, and ethical considerations
Prikaži primjer odgovora
CRISPR-Cas9 works like molecular scissors guided by a GPS. A guide RNA is designed to match a specific DNA sequence; the Cas9 protein then cuts the DNA at that exact location, allowing scientists to delete, repair, or insert genetic material. Current medical applications include sickle cell disease treatment (Casgevy, approved 2023), where patients' stem cells are edited ex vivo to produce functional hemoglobin. Clinical trials are underway for certain cancers, hereditary blindness, and HIV resistance. Ethical considerations center on germline editing (changes passed to future generations), equitable access to expensive therapies, and the slippery slope toward 'designer babies'—most scientists support a moratorium on heritable human genome editing while governance frameworks catch up.
Long Context Analysis
I have a 200-page legal contract. Identify all clauses related to intellectual property ownership, data retention, and termination conditions.
Prikaži primjer odgovora
I can process your entire 200-page contract within my context window. Here's what I would systematically extract: 1) IP Ownership clauses: Look for sections titled 'Intellectual Property,' 'Work Product,' or 'Ownership of Deliverables'—these define who owns code, designs, and inventions created during the engagement. 2) Data Retention: Sections covering 'Data Handling,' 'Confidentiality,' or 'Information Security' typically specify how long each party retains data post-termination, deletion timelines, and compliance with regulations like GDPR. 3) Termination Conditions: Usually in a dedicated 'Termination' section, covering for-cause vs. for-convenience termination, notice periods, cure periods for breaches, and post-termination obligations. Upload the document and I'll provide exact clause references, page numbers, and a summary of each relevant provision with any potential conflicts between sections.

Primjena

Za što se koristi

Long-video and long-PDF analysis
Scientific research and literature review
Coding agents with Deep Think
Search-grounded chatbots
Multimodal data extraction
Enterprise document understanding

Povezani vodiči

Best Large Language Models

Svi modeli: Tekst i chat

Često postavljana pitanja

Što je Gemini 2.5 Pro?

Gemini 2.5 Pro je model od Google DeepMind iz kategorije Tekst i chat. Na Railwailu ga možete pozvati s API ključem kroz Railwail API.

Koliko stoji Gemini 2.5 Pro na Railwailu?

Na Railwailu, Gemini 2.5 Pro košta 1,50 US$ po 1M ulaznih tokena i 12,00 US$ po 1M izlaznih tokena. Naplaćuje se ono što svaki zahtjev zapravo koristi. Korištenje se plaća iz unaprijed kupljenih kredita; 1 kredit jednaka je 0,01 US$.

Koliki je kontekstni prozor od Gemini 2.5 Pro?

Kontekstni prozor od Gemini 2.5 Pro sadrži 1.000.000 tokena. Jedan odgovor može biti dugačak do 65.536 tokena.

Koliko je brz Gemini 2.5 Pro?

Za Gemini 2.5 Pro na Railwailu još nema dovoljno izmjerenih pokretanja da bi se navedlo vrijeme izvršavanja. Ovisi o unošenju, postavkama i opterećenju kod pružatelja.

Je li Gemini 2.5 Pro bolji od Claude Fable 5.1?

To ovisi o zadatku. Gemini 2.5 Pro (Google DeepMind) i Claude Fable 5.1 (Anthropic) su oba modela iz kategorije Tekst i chat. Stranica za usporedbu prikazuje njihove cijene i specifikacije usporedno.

Usporedi Gemini 2.5 Pro i Claude Fable 5.1

Kako koristim Gemini 2.5 Pro kroz API?

Kreiraj Railwail API ključ i pošalji svoj zahtjev s ID-om modela gemini-2-5-pro. Primjeri koda za curl, Python i JavaScript nalaze se u odjeljku API na ovoj stranici.

Usporedivi modeli

Svi u ovoj kategoriji

Claude Fable 5.1Anthropic
Anthropic's model for the most demanding reasoning and long-horizon agentic work. 1M-token context window, up to 128K output tokens, adaptive thinking that is always on.
12,00 US$/1M in
700 % skupnije po jedinici
Usporedi Gemini 2.5 Pro i Claude Fable 5.1
Claude Opus 4.8Anthropic
The most capable model of Anthropic's Opus 4 series. State of the art on long-horizon agentic work, coding and knowledge tasks, with a 1M-token context window at standard pricing.
6,00 US$/1M in
300 % skupnije po jedinici
Usporedi Gemini 2.5 Pro i Claude Opus 4.8
Claude Opus 5.5Anthropic
Anthropic's current Opus model for long-running agentic coding and knowledge work. 1M-token context window, up to 128K output tokens, adaptive thinking that is always on.
4,80 US$/1M in
220 % skupnije po jedinici
Usporedi Gemini 2.5 Pro i Claude Opus 5.5

Koristi Gemini 2.5 Pro preko API-ja

Jedan API ključ za sve modele na Railwailu. Korištenje se naplaćuje iz unaprijed plaćenih kredita, 1 kredit = 0,01 US$.

Dobij API ključ Pogledaj sve modele