Gemini 4 Neon
Google's Gemini 4 Neon is a mid-priced model designed specifically for coding tasks and agentic workflows. It features a large one-million token context window and supports multimodal inputs including audio, video, images, and files.
Gemini 4 Neon specs and pricing
- Provider: Google
- Released: November 18, 2026
- Context window: 1M tokens
- Max output: 66K tokens
- Input: audio, files, images, text, video
- Output: text
- Price: $3.00 input / $15 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Gemini 4 Neon is good at
- Analyzing large code repositories
- Automating terminal-based tasks
- Processing complex multimodal data
To-dos to try with Gemini 4 Neon
- Analyze this entire code repository and identify potential security vulnerabilities.
- Watch this video recording of a terminal session and summarize the commands executed.
- Read these technical documentation files and generate a set of unit tests for the functions described.
FAQ
- What types of media can I upload to Gemini 4 Neon? You can provide text, audio, video, image, and file inputs for the model to process.
- What is the primary purpose of this model? Gemini 4 Neon is built by Google to assist with coding projects and agentic work.
- How much does Gemini 4 Neon cost? Gemini 4 Neon costs $3.00 per million input tokens and $15 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 10.5 credits ($1 = 100 credits).
- What is the context window of Gemini 4 Neon? Gemini 4 Neon can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Gemini 4 Neon without coding? Yes. In todo.is you pick Gemini 4 Neon as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.