Gemini 4 Carbon
Google's Gemini 4 Carbon is a frontier model designed for complex reasoning, coding, and agentic workflows. It accepts a wide variety of inputs including text, images, audio, video, and files, and supports a large context window of over one million tokens.
Gemini 4 Carbon specs and pricing
- Provider: Google
- Released: November 10, 2026
- Context window: 1M tokens
- Max output: 944K tokens
- Input: audio, files, images, text, video
- Output: text
- Price: $2.00 input / $10 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Gemini 4 Carbon is good at
- Complex programming and software development tasks
- Analyzing multi-modal data like long videos or audio recordings
- Executing agentic workflows that require multi-step reasoning
To-dos to try with Gemini 4 Carbon
- Analyze this 45-minute video recording of a meeting and summarize the key technical decisions made.
- Review this entire codebase and identify potential security vulnerabilities or optimization opportunities.
- Process these five PDF documents and extract all project deadlines into a structured table.
FAQ
- What types of media can Gemini 4 Carbon process? This model supports input from text, images, audio, video, and various file formats.
- What is the primary purpose of this model? Gemini 4 Carbon is built by Google to handle complex reasoning tasks, coding projects, and agentic operations.
- How much does Gemini 4 Carbon cost? Gemini 4 Carbon costs $2.00 per million input tokens and $10 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 7 credits ($1 = 100 credits).
- What is the context window of Gemini 4 Carbon? Gemini 4 Carbon can read up to 1M tokens at once and write up to 944K tokens in one reply.
- Can I use Gemini 4 Carbon without coding? Yes. In todo.is you pick Gemini 4 Carbon 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.