Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsGoogle removed the waitlist for Gemini 1.5 Pro’s 2-million-token context window on June 27, 2024, opening access to all developers. The milestone later became generally available on Vertex AI, but it is historical: Google’s Gemini API changelog lists Gemini 1.5 Pro as shut down on September 29, 2025.
What the 2-million-token context window meant
A context window is the amount of information a model can take into account in a request and its surrounding conversation. Gemini 1.5 Pro’s 2-million-token window described the model’s maximum context capacity; it was not a guarantee that every application, interface, or user had that limit, or that every large request would meet a particular cost, speed, or accuracy target.
Google had introduced Gemini 1.5 Pro with a standard 128,000-token context window in February 2024. At that point, access to up to 1 million tokens was a private preview for a limited group of developers and enterprise customers through AI Studio and Vertex AI. Google later said it had announced the 2-million-token window at I/O behind a waitlist. Its June announcement removed that waitlist for developers.
When access changed
| Date | What Google said |
|---|---|
| February 2024 | Gemini 1.5 Pro had a standard 128,000-token context window; up to 1 million tokens was in private preview for a limited group of developers and enterprise customers. Google’s February announcement |
| June 27, 2024 | Google opened the 2-million-token context window to all developers after its waitlist phase. Google Developers Blog announcement |
| September 24, 2024 | Vertex AI release notes marked the 2M context window generally available and listed stable Gemini 1.5 Pro and Flash versions. Vertex AI release notes |
| September 29, 2025 | The Gemini API changelog lists Gemini 1.5 Pro, Gemini 1.5 Flash, and Gemini 1.5 Flash-8B as shut down. Gemini API changelog |
What changed for developers in June 2024
The June 27 post stated: “Today, we’re opening up access to the 2 million token context window on Gemini 1.5 Pro for all developers.” In practical terms, developers no longer needed to wait for the announced 2M capability through the waitlist. The statement was about developer access, not a promise that every consumer-facing Gemini product had a 2-million-token limit.
Recommended Free Tools
Google also said that longer contexts can increase input costs. It announced context caching for Gemini 1.5 Pro and Gemini 1.5 Flash as a way to reuse repeated tokens across prompts. That was the mitigation described at launch; it should not be read as current pricing or as a guarantee that caching makes large-context use inexpensive.
How to interpret the platform announcements
The rollout happened across different points in time and channels. Google’s June 2024 post announced developer access, while Vertex AI’s September release notes later marked the 2M window generally available there. Those historical availability statements do not establish that Gemini 1.5 Pro remains usable on Vertex AI today. Google’s cited API changelog specifically records the Gemini API shutdown, so current access should not be inferred from the 2024 announcements.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Other features in the same announcement
The June post also covered code execution for Gemini 1.5 Pro and Flash, as well as Gemma 2 in Google AI Studio. Code execution let a model generate and run Python iteratively. Google described its sandbox as disconnected from the internet, with a few numerical libraries, and said billing for the feature was based on output tokens. It was offered through the Gemini API and AI Studio’s advanced settings at that time.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
