Google Gemini API Pricing Calculator
Wondering about how the Google gemini-1.5-pro API pricing works? Here's a pricing calculator.
Google gemini-1.5-pro
1M context
Calculated by
Pricing calculation
| Provider | Model | Context | Input/1k Tokens | Output/1k Tokens | Per Call | Total |
|---|---|---|---|---|---|---|
| gemini-1.5-pro | 1M | $0.0018 | $0.0105 | $0.012 | $1.237 |
Need more detailed calculations for each model?Click on the model to get more details
OpenAI gpt-4o
OpenAI gpt-3.5-turbo
Anthropic claude-3.5-sonnet
Mistral AI mistral-largeIntroducing Gemini 1.5 Pro: Next-Generation AI Model
Overview
Gemini 1.5 Pro was introduced on February 15, 2024, as a part of Google DeepMind's next-generation model. This model demonstrates dramatic enhancements in performance, including a breakthrough in long-context understanding across various modalities.
Enhanced Performance
Gemini 1.5 Pro is a mid-size multimodal model optimized for scalability across a wide range of tasks, achieving performance levels similar to the preceding Gemini 1.0 Ultra model. It features a new Mixture-of-Experts (MoE) architecture, enhancing efficiency in training and service.
Advanced Context Understanding
The model boasts a standard 128,000 token context window, extendable up to 1 million tokens. This allows Gemini 1.5 Pro to process vast amounts of information in a single prompt, enhancing capabilities such as understanding a 402-page transcript or analyzing an hour-long video.
Sophisticated Reasoning Across Modalities
Capable of complex reasoning across text, audio, and video, Gemini 1.5 Pro excels in understanding and interpreting intricate details. For example, it can analyze plot points in a 44-minute silent film or provide insights on 100,000 lines of code.
In-Context Learning Abilities
This model demonstrates impressive in-context learning skills, able to acquire new skills based on information presented in long prompts without additional fine-tuning. It has been tested effectively on benchmarks like Machine Translation from One Book (MTOB).
Rigorous Ethics and Safety Testing
Gemini 1.5 Pro undergoes extensive ethics and safety testing to ensure it meets robust AI principles and safety policies. External experts have tested the model to identify potential risks and integrate safety measures, ensuring responsible deployment.