We’re thrilled to announce that Gemini 2.5 Pro—Google’s next-generation “thinking model”—is officially available through Requesty at an exclusive, discounted price for high-volume usage. Whether you’re building complex applications, exploring AI research, or integrating a sophisticated coding assistant, Gemini 2.5 Pro delivers state-of-the-art reasoning and extended context capabilities.
Here’s the best part: for tokens above 200,000, you’ll enjoy a special discounted rate that makes large-scale AI deployments more affordable and accessible than ever.
Why Gemini 2.5 Pro?
Gemini 2.5 Pro is Google’s premier large language model, designed for:
Deep Reasoning – It “thinks through” problems, offering step-by-step logical consistency.
Robust Coding – From quick debugging to multi-file project creation, Gemini 2.5 Pro delivers advanced coding assistance.
Massive Context – With up to 1 million tokens of context (and more on the way), large datasets and complex conversation threads are no challenge.
Combined with Requesty’s streamlined routing and billing, you get a powerful AI that can scale with your needs—without the complexity of juggling multiple keys or platforms.
The Requesty Advantage
Requesty is an LLM router that consolidates dozens of models under a single, OpenAI-compatible API. That means one API key, one endpoint, and a user-friendly interface:
Discounted Rates for High Volume: We’ve secured special pricing with Google so that you only pay $1.25 per input token and $10 per output token for usage above 200k tokens.
Simple Setup: Just point your coding tool or CLI at our router endpoint, add your Bearer token, and specify the model ID—no separate signups required.
Unified Dashboard: Track consumption, monitor costs, and generate usage reports all in one place.
Model Fallbacks & Easy Switching: Seamlessly switch or fallback to other models (like Grok 3, GPT-4, etc.) if Gemini 2.5 Pro is unavailable or if you want to optimize for cost or speed.
Model ID & Pricing Details
Model ID:
google/gemini-2.5-pro-preview-03-25Pricing for 200k+ tokens:
Input Tokens: $1.25
Output Tokens: $10
If you’re testing or operating at smaller scales, the standard rate applies—but once you exceed 200k tokens, our discounted pricing kicks in automatically.
Compatible with Popular Coding Assistants
Requesty supports any tool or platform that can speak OpenAI’s protocol. For coding assistance, you can easily integrate Gemini 2.5 Pro into:
Cline – Switch providers in the settings and supply your Requesty API Key.
Roo Code – Paste the
google/gemini-2.5-pro-preview-03-25model ID in your provider configuration.Aider – Update your .aider config or project settings to route requests via Requesty.
Goose – Point your Goose environment to our endpoint, and you’re all set.
Already using openrouter, glama, portkey, or litellm? You can seamlessly migrate your calls to Requesty with minimal friction—gain access to Gemini 2.5 Pro’s discounted high-volume rate and unify your entire AI workflow under a single provider.
How to Get Started
Sign In or Sign Up Head to Requesty and sign in (or create an account if you’re new).
Grab Your API Key In your Requesty dashboard, locate or generate your API Key. This token authenticates your requests.
Set the Endpoint
Endpoint URL:
https://router.requesty.ai/v1Authorization:
Bearer <YOUR_ROUTER_API_KEY>
Specify Gemini 2.5 Pro In your request or tool settings, select
google/gemini-2.5-pro-preview-03-25as your model.Start Coding or Querying Send chat, completion, or code-generation requests just as you would with any other OpenAI-compatible service.
Scale Up with Confidence
Whether you’re building a coding co-pilot, a data-driven research tool, or an advanced conversational agent, Gemini 2.5 Pro offers top-tier performance. With Requesty, you also get:
Flexible Usage & Budgeting – Pay only for what you use, with no hidden fees or separate bills.
World-Class Support – Our dedicated team is here to help, whether you need best practices, code samples, or troubleshooting tips.
Community – Join a community of developers and data scientists who share tips, workflows, and success stories for all models available on Requesty.
Ready to Harness Gemini 2.5 Pro?
Gemini 2.5 Pro sets a new standard for advanced AI reasoning, and we’re proud to bring it to you through Requesty—at a special discounted rate for large volumes. Integrate it into your favorite coding assistant, run massive data analyses, or build the next big AI-powered solution, all while simplifying your infrastructure.
Get started today and experience what the world’s most capable thinking model can do for your projects.
About Requesty Requesty is the leading LLM router, providing a unified platform to access the best AI models from across the industry. With one key and one endpoint, you can switch models on the fly, set up fallback options, and track usage from a single dashboard.