Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
Image prompt
(per 1K tokens)
How it works Gemini 2.0 Flash?
Frequently asked questions about Gemini 2.0 Flash
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
Gemini 2.0 Flash works with text: it answers questions, writes and edits, analyzes code, and helps with logic and calculations. It accepts images and documents as input — you can ask it to describe an image, extract data from a PDF, or summarize file content. Batch processing is available for large volumes.
In a single response, the model outputs up to 32,000 tokens — enough for a long analysis, a large article, or a substantial code snippet. The total context window of 200,000 tokens is shared between your request and the response, so a large document and detailed output fit together. Need more? Break the task into parts.
In our data, a separate reasoning mode for Gemini 2.0 Flash is not noted — this doesn't mean it doesn't exist, we just don't confirm it. In practice, it helps to ask in the prompt to break down the task step-by-step: the model will detail the solution process and conclusions.
Our data does not contain notes about function calling or strict JSON, so we cannot guarantee it — please test it in your scenario. Connection is via the unified OpenAI-compatible BotHub API: the request format is the same, so you can test and, if necessary, switch to another model without rewriting the integration.
Images and documents — yes, this is confirmed: send screenshots, photos, PDFs, and ask to describe, compare, or extract data. Audio and video input is not noted in our data, so for such files, it is better to check with a small example beforehand or use a specialized model.
The language of prompts and output is not specified in our data, so we won't promise Russian quality — evaluate it with your own texts, it's quick. Regarding access: the BotHub interface is in Russian, payment is via Russian cards in rubles, no VPN or foreign card needed, pay as you go for tokens.