2026-06-22 BREAKTHROUGHS☾ PM

Gemini 1.5 Flash Opens a Two-Million-Token Context Window at No Cost

📰 THE BRIEF

Google enabled the 2 million token context window in Gemini 1.5 Flash inside AI Studio. Users paste full code repositories or multi-year chat histories and receive single-pass summaries or refactors. The feature is free for all accounts with rate limits of 32 requests per minute.

💡 WHY IT MATTERS

Long context removes the need to chunk documents into smaller segments. Analysts can now query an entire earnings history or legal docket in one request instead of stitching partial answers. The technique shifts workflows from retrieval-augmented generation toward direct context ingestion.

👥 WHO'S DOING IT

Google DeepMind activated the window at ai.google.dev/gemini-api/docs/models/gemini. Internal teams report processing 1.8 million token legal archives in under 45 seconds with 94 percent recall on citation accuracy.

⚡ TRY IT

Step 1: Navigate to aistudio.google.com and sign in with a Google account. Step 2: Select Gemini 1.5 Flash, set the context slider to 2 000 000 tokens, and paste your full dataset. Step 3: Submit the prompt and receive a single coherent response without manual chunking.

→ Read original source