Best Large Language Models for Vertex AI
View:
Compare the Top Large Language Models that integrate with Vertex AI as of October 2025
Sort By:
This a list of Large Language Models that integrate with Vertex AI. Use the filters on the left to add additional filters for products that have integrations with Vertex AI. View the products that work with Vertex AI in the table below.
What are Large Language Models for Vertex AI?
Large language models are artificial neural networks used to process and understand natural language. Commonly trained on large datasets, they can be used for a variety of tasks such as text generation, text classification, question answering, and machine translation. Over time, these models have continued to improve, allowing for better accuracy and greater performance on a variety of tasks. Compare and read user reviews of the best Large Language Models for Vertex AI currently available using the table below. This list is updated regularly.
-
1
Google AI Studio
Google
Google AI Studio provides access to large language models (LLMs) that are capable of understanding and generating human-like text. These models are trained on vast amounts of data and are designed to perform a wide range of language tasks, from translation and summarization to question answering and content generation. By leveraging LLMs, businesses can create applications that understand complex language inputs and produce contextually relevant responses. Google AI Studio also allows users to fine-tune these models, making them highly adaptable to specific use cases or industry requirements.Starting Price: Free -
2
Gemini
Google
Gemini is Google's advanced AI chatbot designed to enhance creativity and productivity by engaging in natural language conversations. Accessible via the web and mobile apps, Gemini integrates seamlessly with various Google services, including Docs, Drive, and Gmail, enabling users to draft content, summarize information, and manage tasks efficiently. Its multimodal capabilities allow it to process and generate diverse data types, such as text, images, and audio, providing comprehensive assistance across different contexts. As a continuously learning model, Gemini adapts to user interactions, offering personalized and context-aware responses to meet a wide range of user needs.Starting Price: Free -
3
Gemini Advanced
Google
Gemini Advanced is a cutting-edge AI model designed for unparalleled performance in natural language understanding, generation, and problem-solving across diverse domains. Featuring a revolutionary neural architecture, it delivers exceptional accuracy, nuanced contextual comprehension, and deep reasoning capabilities. Gemini Advanced is engineered to handle complex, multifaceted tasks, from creating detailed technical content and writing code to conducting in-depth data analysis and providing strategic insights. Its adaptability and scalability make it a powerful solution for both individual users and enterprise-level applications. Gemini Advanced sets a new standard for intelligence, innovation, and reliability in AI-powered solutions. You'll also get access to Gemini in Gmail, Docs, and more, 2 TB storage, and other benefits from Google One. Gemini Advanced also offers access to Gemini with Deep Research. You can conduct in-depth and real-time research on almost any subject.Starting Price: $19.99 per month -
4
Claude Sonnet 3.5
Anthropic
Claude Sonnet 3.5 sets new industry benchmarks for graduate-level reasoning (GPQA), undergraduate-level knowledge (MMLU), and coding proficiency (HumanEval). It shows marked improvement in grasping nuance, humor, and complex instructions, and is exceptional at writing high-quality content with a natural, relatable tone. Claude Sonnet 3.5 operates at twice the speed of Claude Opus 3. This performance boost, combined with cost-effective pricing, makes Claude Sonnet 3.5 ideal for complex tasks such as context-sensitive customer support and orchestrating multi-step workflows. Claude Sonnet 3.5 is now available for free on Claude.ai and the Claude iOS app, while Claude Pro and Team plan subscribers can access it with significantly higher rate limits. It is also available via the Anthropic API, Amazon Bedrock, and Google Cloud’s Vertex AI. The model costs $3 per million input tokens and $15 per million output tokens, with a 200K token context window.Starting Price: Free -
5
Claude Opus 3
Anthropic
Opus, our most intelligent model, outperforms its peers on most of the common evaluation benchmarks for AI systems, including undergraduate level expert knowledge (MMLU), graduate level expert reasoning (GPQA), basic mathematics (GSM8K), and more. It exhibits near-human levels of comprehension and fluency on complex tasks, leading the frontier of general intelligence. All Claude 3 models show increased capabilities in analysis and forecasting, nuanced content creation, code generation, and conversing in non-English languages like Spanish, Japanese, and French.Starting Price: Free -
6
Claude Sonnet 3.7
Anthropic
Claude Sonnet 3.7, developed by Anthropic, is a cutting-edge AI model that combines rapid response with deep reflective reasoning. This innovative model allows users to toggle between quick, efficient responses and more thoughtful, reflective answers, making it ideal for complex problem-solving. By allowing Claude to self-reflect before answering, it excels at tasks that require high-level reasoning and nuanced understanding. With its ability to engage in deeper thought processes, Claude Sonnet 3.7 enhances tasks such as coding, natural language processing, and critical thinking applications. Available across various platforms, it offers a powerful tool for professionals and organizations seeking a high-performance, adaptable AI.Starting Price: Free -
7
Claude Opus 4
Anthropic
Claude Opus 4 represents a revolutionary leap in AI model performance, setting a new standard for coding and reasoning capabilities. As the world’s best coding model, Opus 4 excels in handling long-running, complex tasks, and agent workflows. With sustained performance that can run for hours, it outperforms all prior models—including the Sonnet series—making it ideal for demanding coding projects, research, and AI agent applications. It’s the model of choice for organizations looking to enhance their software engineering, streamline workflows, and improve productivity with remarkable precision. Now available on Anthropic API, Amazon Bedrock, and Google Cloud’s Vertex AI, Opus 4 offers unparalleled support for coding, debugging, and collaborative agent tasks.Starting Price: $15 / 1 million tokens (input) -
8
Gemini Flash
Google
Gemini Flash is an advanced large language model (LLM) from Google, specifically designed for high-speed, low-latency language processing tasks. Part of Google DeepMind’s Gemini series, Gemini Flash is tailored to provide real-time responses and handle large-scale applications, making it ideal for interactive AI-driven experiences such as customer support, virtual assistants, and live chat solutions. Despite its speed, Gemini Flash doesn’t compromise on quality; it’s built on sophisticated neural architectures that ensure responses remain contextually relevant, coherent, and precise. Google has incorporated rigorous ethical frameworks and responsible AI practices into Gemini Flash, equipping it with guardrails to manage and mitigate biased outputs, ensuring it aligns with Google’s standards for safe and inclusive AI. With Gemini Flash, Google empowers businesses and developers to deploy responsive, intelligent language tools that can meet the demands of fast-paced environments. -
9
Gemini 2.0
Google
Gemini 2.0 is an advanced AI-powered model developed by Google, designed to offer groundbreaking capabilities in natural language understanding, reasoning, and multimodal interactions. Building on the success of its predecessor, Gemini 2.0 integrates large language processing with enhanced problem-solving and decision-making abilities, enabling it to interpret and generate human-like responses with greater accuracy and nuance. Unlike traditional AI models, Gemini 2.0 is trained to handle multiple data types simultaneously, including text, images, and code, making it a versatile tool for research, business, education, and creative industries. Its core improvements include better contextual understanding, reduced bias, and a more efficient architecture that ensures faster, more reliable outputs. Gemini 2.0 is positioned as a major step forward in the evolution of AI, pushing the boundaries of human-computer interaction.Starting Price: Free -
10
DeepSeek R1
DeepSeek
DeepSeek-R1 is an advanced open-source reasoning model developed by DeepSeek, designed to rival OpenAI's Model o1. Accessible via web, app, and API, it excels in complex tasks such as mathematics and coding, demonstrating superior performance on benchmarks like the American Invitational Mathematics Examination (AIME) and MATH. DeepSeek-R1 employs a mixture of experts (MoE) architecture with 671 billion total parameters, activating 37 billion parameters per token, enabling efficient and accurate reasoning capabilities. This model is part of DeepSeek's commitment to advancing artificial general intelligence (AGI) through open-source innovation.Starting Price: Free -
11
Claude Sonnet 4
Anthropic
Claude Sonnet 4, the latest evolution of Anthropic’s language models, offers a significant upgrade in coding, reasoning, and performance. Designed for diverse use cases, Sonnet 4 builds upon the success of its predecessor, Claude Sonnet 3.7, delivering more precise responses and better task execution. With a state-of-the-art 72.7% performance on the SWE-bench, it stands out in agentic scenarios, offering enhanced steerability and clear reasoning capabilities. Whether handling software development, multi-feature app creation, or complex problem-solving, Claude Sonnet 4 ensures higher code quality, reduced errors, and a smoother development process.Starting Price: $3 / 1 million tokens (input) -
12
Gemini 2.5 Pro
Google
Gemini 2.5 Pro is an advanced AI model designed to handle complex tasks with enhanced reasoning and coding capabilities. Leading common benchmarks, it excels in math, science, and coding, demonstrating strong performance in tasks like web app creation and code transformation. Built on the Gemini 2.5 foundation, it features a 1 million token context window, enabling it to process vast datasets from various sources such as text, images, and code repositories. Available now in Google AI Studio, Gemini 2.5 Pro is optimized for more sophisticated applications and supports advanced users with improved performance for complex problem-solving.Starting Price: $19.99/month -
13
Claude Haiku 3.5
Anthropic
Our fastest model, delivering advanced coding, tool use, and reasoning at an accessible price Claude Haiku 3.5 is the next generation of our fastest model. For a similar speed to Claude Haiku 3, Claude Haiku 3.5 improves across every skill set and surpasses Claude Opus 3, the largest model in our previous generation, on many intelligence benchmarks. Claude Haiku 3.5 is available across our first-party API, Amazon Bedrock, and Google Cloud’s Vertex AI—initially as a text-only model and with image input to follow. -
14
Gemini-Exp-1206
Google
Gemini-Exp-1206 is an experimental AI model now available for preview to Gemini Advanced subscribers. This model significantly enhances performance in complex tasks such as coding, mathematics, reasoning, and following detailed instructions. It's designed to assist users in navigating intricate challenges with greater ease. As an early preview, some features may not function as expected, and it currently lacks access to real-time information. Users can access Gemini-Exp-1206 through the Gemini model drop-down on desktop and mobile web platforms. -
15
Gemini Pro
Google
Gemini is natively multimodal, which gives you the potential to transform any type of input into any type of output. We've built Gemini responsibly from the start, incorporating safeguards and working together with partners to make it safer and more inclusive. Integrate Gemini models into your applications with Google AI Studio and Google Cloud Vertex AI. -
16
Gemini 2.0 Flash
Google
The Gemini 2.0 Flash AI model represents the next generation of high-speed, intelligent computing, designed to set new benchmarks in real-time language processing and decision-making. Building on the robust foundation of its predecessor, it incorporates enhanced neural architecture and breakthrough advancements in optimization, enabling even faster and more accurate responses. Gemini 2.0 Flash is designed for applications requiring instantaneous processing and adaptability, such as live virtual assistants, automated trading systems, and real-time analytics. Its lightweight, efficient design ensures seamless deployment across cloud, edge, and hybrid environments, while its improved contextual understanding and multitasking capabilities make it a versatile tool for tackling complex, dynamic workflows with precision and speed. -
17
Gemini Nano
Google
Gemini Nano from Google is a lightweight, energy-efficient AI model designed for high performance in compact, resource-constrained environments. Tailored for edge computing and mobile applications, Gemini Nano combines Google's advanced AI architecture with cutting-edge optimization techniques to deliver seamless performance without compromising speed or accuracy. Despite its compact size, it excels in tasks like voice recognition, natural language processing, real-time translation, and personalized recommendations. With a focus on privacy and efficiency, Gemini Nano processes data locally, minimizing reliance on cloud infrastructure while maintaining robust security. Its adaptability and low power consumption make it an ideal choice for smart devices, IoT ecosystems, and on-the-go AI solutions. -
18
Gemini 1.5 Pro
Google
The Gemini 1.5 Pro AI model is a state-of-the-art language model designed to deliver highly accurate, context-aware, and human-like responses across a variety of applications. Built with cutting-edge neural architecture, it excels in natural language understanding, generation, and reasoning tasks. The model is fine-tuned for versatility, supporting tasks like content creation, code generation, data analysis, and complex problem-solving. Its advanced algorithms ensure nuanced comprehension, enabling it to adapt to different domains and conversational styles seamlessly. With a focus on scalability and efficiency, the Gemini 1.5 Pro is optimized for both small-scale implementations and enterprise-level integrations, making it a powerful tool for enhancing productivity and innovation. -
19
Gemini 1.5 Flash
Google
The Gemini 1.5 Flash AI model is an advanced, high-speed language model engineered for lightning-fast processing and real-time responsiveness. Designed to excel in dynamic and time-sensitive applications, it combines streamlined neural architecture with cutting-edge optimization techniques to deliver exceptional performance without compromising on accuracy. Gemini 1.5 Flash is tailored for scenarios requiring rapid data processing, instant decision-making, and seamless multitasking, making it ideal for chatbots, customer support systems, and interactive applications. Its lightweight yet powerful design ensures it can be deployed efficiently across a range of platforms, from cloud-based environments to edge devices, enabling businesses to scale their operations with unmatched agility. -
20
Mistral Large
Mistral AI
Mistral Large is Mistral AI's flagship language model, designed for advanced text generation and complex multilingual reasoning tasks, including text comprehension, transformation, and code generation. It supports English, French, Spanish, German, and Italian, offering a nuanced understanding of grammar and cultural contexts. With a 32,000-token context window, it can accurately recall information from extensive documents. The model's precise instruction-following and native function-calling capabilities facilitate application development and tech stack modernization. Mistral Large is accessible through Mistral's platform, Azure AI Studio, and Azure Machine Learning, and can be self-deployed for sensitive use cases. Benchmark evaluations indicate that Mistral Large achieves strong results, making it the world's second-ranked model generally available through an API, next to GPT-4.Starting Price: Free -
21
Mistral Medium 3
Mistral AI
Mistral Medium 3 is a powerful AI model designed to deliver state-of-the-art performance at a fraction of the cost compared to other models. It offers simpler deployment options, allowing for hybrid or on-premises configurations. Mistral Medium 3 excels in professional applications like coding and multimodal understanding, making it ideal for enterprise use. Its low-cost structure makes it highly accessible while maintaining top-tier performance, outperforming many larger models in specific domains.Starting Price: Free -
22
GPT-5
OpenAI
GPT-5 is OpenAI’s most advanced AI model, delivering smarter, faster, and more useful responses across a wide range of topics including math, science, finance, and law. It features built-in thinking capabilities that allow it to provide expert-level answers and perform complex reasoning. GPT-5 can handle long context lengths and generate detailed outputs, making it ideal for coding, research, and creative writing. The model includes a ‘verbosity’ parameter for customizable response length and improved personality control. It integrates with business tools like Google Drive and SharePoint to provide context-aware answers while respecting security permissions. Available to everyone, GPT-5 empowers users to collaborate with an AI assistant that feels like a knowledgeable colleague.Starting Price: $1.25 per 1M tokens -
23
Gemma 3
Google
Gemma 3, introduced by Google, is a new AI model built on the Gemini 2.0 architecture, designed to offer enhanced performance and versatility. This model is capable of running efficiently on a single GPU or TPU, making it accessible for a wide range of developers and researchers. Gemma 3 focuses on improving natural language understanding, generation, and other AI-driven tasks. By offering scalable, powerful AI capabilities, Gemma 3 aims to advance the development of AI systems across various industries and use cases.Starting Price: Free -
24
Gemini 2.5 Pro Preview (I/O Edition) by Google is an advanced AI model designed to streamline coding tasks and enhance web app development. This powerful tool allows developers to efficiently transform and edit code, reducing errors and improving function calling accuracy. With enhanced capabilities in video understanding and web app creation, Gemini 2.5 Pro Preview excels at building aesthetically pleasing and functional web applications. Available through Google’s Gemini API and AI platforms, this model provides a seamless solution for developers to create innovative applications with improved performance and reliability.Starting Price: $19.99/month
-
25
PaLM
Google
PaLM API is an easy and safe way to build on top of our best language models. Today, we’re making an efficient model available, in terms of size and capabilities, and we’ll add other sizes soon. The API also comes with an intuitive tool called MakerSuite, which lets you quickly prototype ideas and, over time, will have features for prompt engineering, synthetic data generation and custom-model tuning — all supported by robust safety tools. Select developers can access the PaLM API and MakerSuite in Private Preview today, and stay tuned for our waitlist soon. -
26
Gemma
Google
Gemma is a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models. Developed by Google DeepMind and other teams across Google, Gemma is inspired by Gemini, and the name reflects the Latin gemma, meaning “precious stone.” Accompanying our model weights, we’re also releasing tools to support developer innovation, foster collaboration, and guide the responsible use of Gemma models. Gemma models share technical and infrastructure components with Gemini, our largest and most capable AI model widely available today. This enables Gemma 2B and 7B to achieve best-in-class performance for their sizes compared to other open models. And Gemma models are capable of running directly on a developer laptop or desktop computer. Notably, Gemma surpasses significantly larger models on key benchmarks while adhering to our rigorous standards for safe and responsible outputs. -
27
Gemma 2
Google
A family of state-of-the-art, light-open models created from the same research and technology that were used to create Gemini models. These models incorporate comprehensive security measures and help ensure responsible and reliable AI solutions through selected data sets and rigorous adjustments. Gemma models achieve exceptional comparative results in their 2B, 7B, 9B, and 27B sizes, even outperforming some larger open models. With Keras 3.0, enjoy seamless compatibility with JAX, TensorFlow, and PyTorch, allowing you to effortlessly choose and change frameworks based on task. Redesigned to deliver outstanding performance and unmatched efficiency, Gemma 2 is optimized for incredibly fast inference on various hardware. The Gemma family of models offers different models that are optimized for specific use cases and adapt to your needs. Gemma models are large text-to-text lightweight language models with a decoder, trained in a huge set of text data, code, and mathematical content. -
28
Gemini 2.0 Flash Thinking
Google
Gemini 2.0 Flash Thinking is an advanced AI model developed by Google DeepMind, designed to enhance reasoning capabilities by explicitly displaying its thought processes. This transparency allows the model to tackle complex problems more effectively and provides users with clear explanations of its decision-making steps. By showcasing its internal reasoning, Gemini 2.0 Flash Thinking not only improves performance but also offers greater explainability, making it a valuable tool for applications requiring deep understanding and trust in AI-driven solutions. -
29
Gemini 2.0 Flash-Lite
Google
Gemini 2.0 Flash-Lite is Google DeepMind's lighter AI model, designed to offer a cost-effective solution without compromising performance. As the most economical model in the Gemini 2.0 lineup, Flash-Lite is tailored for developers and businesses seeking efficient AI capabilities at a lower cost. It supports multimodal inputs and features a context window of one million tokens, making it suitable for a variety of applications. Flash-Lite is currently available in public preview, allowing users to explore its potential in enhancing their AI-driven projects. -
30
Gemini 2.0 Pro
Google
Gemini 2.0 Pro is Google DeepMind's most advanced AI model, designed to excel in complex tasks such as coding and intricate problem-solving. Currently in its experimental phase, it features an extensive context window of two million tokens, enabling it to process and analyze vast amounts of information efficiently. A standout feature of Gemini 2.0 Pro is its seamless integration with external tools like Google Search and code execution environments, enhancing its ability to provide accurate and comprehensive responses. This model represents a significant advancement in AI capabilities, offering developers and users a powerful resource for tackling sophisticated challenges.