Google launches Gemini Decision 1 with multimodal inputs and free tier
Google introduced Gemini Decision 1, a decision model that accepts text, images, audio, video and PDFs, and offers a free API tier for developers.
Google has released its own decision model, Gemini Decision 1. The model looks quite competitive.
Its main advantage over Jev and OpenAI is that it can accept not only text and images, but also audio, video and PDF files.
A single request can contain up to 1000 different questions, as long as they fit within the 262K-token context window.
Pricing per 1M input tokens:
- Jev: $0.042
- Gemini Decision: $0.10
- OpenAI Decisions API: $0.10
Unlike Jev and OpenAI, which require paid API access, Gemini offers a free tier:
- 200 requests per minute
- 50K tokens per minute
- 10K requests per day
API keys can be created in Google AI Studio.
Otherwise, the model is similar to its alternatives, but it is a good, nearly unlimited option for pet projects.
Possible use cases:
- In Gemini Notebook, it already works as a router that selects the appropriate model and effort for each request.
- In Google Labs, it chooses an emoji from more than 200 options for an AI agent.
- In Google Search, it checks queries to MCP tools for attacks and harmful content.
There is also a mention that Gemini 4 Hydrogen may be released later today.
Why it matters
AnalysisThe model reduces costs and complexity for routing, moderation and multimodal decision tasks, especially for small projects.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Google introduces multimodal Gemini Decisions model
Gemini Decisions accepts video, audio, images and text, with input tokens priced at $0.10 per million.
Google AI Studio: Free Gemini API Keys
Official Google sandbox: get free Gemini 2.0/1.5 API keys without a credit card, setup system prompts, and test the 2M token context window. Limits & guide 2026.
Google releases Gemini Decision 1, an AI model for decision-making
Google has introduced Gemini Decision 1, a decision-focused AI model available through the Gemini API with multimodal input support and a 256K-token context window.
Google Gemini Pro (Model with Infinite Context)
The flagship working model from Google DeepMind featuring a record context window of over 2 million tokens. Capable of analyzing entire books, lengthy videos, and massive codebases in a single query.