Gemini 2.5 Pro

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

Text & chatLegacyAvailable

by Google DeepMindgemini-2-5-pro

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

Try it Get API key Compare

Price · 1M in / out: $1.50 / $12.00
Context: 1,000,000 tokens
Max. output: 65,536 tokens
Input → output: Text → Text
Developer: Google DeepMind
Updated: September 23, 2026

This is an older version of the model.

Playground

Try Gemini 2.5 Pro

Chat

$1.50/1M in

Send a message. The answer arrives in full once the model is done (no streaming).

Max. answer length (tokens)

⌘/Ctrl + Enter

This run

at most $0.0123 · 1.23 credits reserved

Billed by the tokens actually used; the unused part of the reservation is refunded.

New here?

10 free credits ($0.10) when you sign up with Google

Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits. Enough for 8 runs of this model.

About Gemini 2.5 Pro

TL;DRAs of September 23, 2026

Gemini 2.5 Pro is a model by Google DeepMind in the Text & chat category. On Railwail, Gemini 2.5 Pro costs $1.50 per 1M input tokens and $12.00 per 1M output tokens. The context window holds 1,000,000 tokens, and one response can be up to 65,536 tokens long.

Background

About Google DeepMind

Founded 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.

Visit Google DeepMind

Architecture

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.

Parameters: Undisclosed (sparse MoE, total parameters in the hundreds of billions, active per-token undisclosed)
Context: 1,048,576 tokens

Capabilities

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.

Training & license

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.

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

Safety testing: 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.

Known limitations

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

Research papers

Pricing

Prices in US dollars. Usage is charged from prepaid credits.

Input	$1.50 / 1M tokens
Output	$12.00 / 1M tokens
Input (prompts over 200,000 tokens)	$3.00 / 1M tokens
Output (prompts over 200,000 tokens)	$18.00 / 1M tokens

Billed by the tokens each request actually uses.
1 credit = $0.01

Cost calculator

Price calculator

Input tokens

/ req.

Output tokens

/ req.

Requests

Total

$0.75

75 credits

Per request

$0.0075 · 0.75 credits

Each request is rounded up to 0.01 credits.

API

Call Gemini 2.5 Pro with your Railwail API key. Use this model ID in the request:

gemini-2-5-proAPI documentation Get an API key

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);

Set your key as RAILWAIL_API_KEYCreate API key

Specifications

Model ID: gemini-2-5-pro
Developer: Google DeepMind
Category: Text & chat
Input: Text
Output: Text
Context window: 1,000,000 tokens
Max. output: 65,536 tokens
Billing: By usage (tokens or GPU time)
Lifecycle: Legacy
Model size: Undisclosed (sparse MoE, total parameters in the hundreds of billions, active per-token undisclosed)
License: Proprietary commercial license via Google AI Studio, Vertex AI and the Gemini app. Commercial use permitted under Google Cloud terms.
Catalog entry updated: September 23, 2026

Example prompts

Examples from the Railwail catalog. They were not generated live on this page.

Scientific Analysis
Explain CRISPR-Cas9 gene editing: how it works, current medical applications, and ethical considerations
Show example answer
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.
Show example answer
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.

Use cases

What it is used for

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

Related guides

Best Large Language Models

All models in Text & chat

Frequently asked questions

What is Gemini 2.5 Pro?

Gemini 2.5 Pro is a model by Google DeepMind in the Text & chat category. On Railwail you can call it with an API key through the Railwail API.

How much does Gemini 2.5 Pro cost on Railwail?

On Railwail, Gemini 2.5 Pro costs $1.50 per 1M input tokens and $12.00 per 1M output tokens. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals $0.01.

What is the context window of Gemini 2.5 Pro?

The context window of Gemini 2.5 Pro holds 1,000,000 tokens. One response can be up to 65,536 tokens long.

How fast is Gemini 2.5 Pro?

There are not enough measured runs of Gemini 2.5 Pro on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.

Is Gemini 2.5 Pro better than Claude Fable 5.1?

That depends on the task. Gemini 2.5 Pro (Google DeepMind) and Claude Fable 5.1 (Anthropic) are both models in the Text & chat category. The comparison page shows their prices and specifications side by side.

Compare Gemini 2.5 Pro and Claude Fable 5.1

How do I use Gemini 2.5 Pro through the API?

Create a Railwail API key and send your request with the model ID gemini-2-5-pro. Code examples for curl, Python and JavaScript are in the API section of this page.

Comparable models

All in this category

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.
$12.00/1M in
700 % more expensive per unit
Compare Gemini 2.5 Pro vs. 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.
$6.00/1M in
300 % more expensive per unit
Compare Gemini 2.5 Pro vs. 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.
$4.80/1M in
220 % more expensive per unit
Compare Gemini 2.5 Pro vs. Claude Opus 5.5

Use Gemini 2.5 Pro via the API

One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = $0.01.

Get API key Browse all models