Positioning and release
Gemini 2.0 Flash is a multimodal model from Google designed for high efficiency and production applications. gemini-2.0-flash-001 was released as a generally available version on February 5, 2025. (aistudio.google.com)
Capabilities and uses
- Accepts text, image, audio, and video inputs and generates text output; it can be used for tasks such as multimodal content understanding, summarization, information extraction, and dialogue.
- Supports function calling, code execution, structured output, search grounding, and context caching. The input limit is 1,048,576 tokens and the output limit is 8,192 tokens; the knowledge cutoff is August 2024. (ai.google.dev)
Limitations and status
This version does not support image or audio generation, nor does it support the Live API; it should not be confused with other image generation or real-time audio versions in the Gemini 2.0 family. The model may produce errors, and important results should be verified by humans. Official records show that gemini-2.0-flash-001 was shut down on June 1, 2026 and should no longer be considered an available endpoint for new projects. (ai.google.dev)
Pricing
Query date: November 19, 2026. Input and output prices for this shut-down version could not be verified on the current official Gemini API pricing page.
The official Google Cloud pricing page still lists US dollar (USD) prices for the Gemini 2.0 Flash model category, but does not separately identify gemini-2.0-flash-001 in that table, nor does it imply that this version is currently available. Per 1 million tokens: for standard calls, text input costs USD 0.15, audio input costs USD 1.00, and text output costs USD 0.60; for the Batch API, the respective prices are USD 0.075, USD 0.50, and USD 0.30. These are Google Cloud platform prices and cannot be directly treated as Gemini API prices. (cloud.google.com)