Gemini 4 Hydrogen - Free Flagship Gemini Model, 1M Context
gemini-4-hydrogen
Model Information
| Attribute | Value |
|---|---|
| Context length | 1,048,576 tokens |
| Max output | 65,536 tokens (up to 1M with long decode) |
| Input price | $0 (free tier) |
| Output price | $0 (free tier) |
| Provider | Google DeepMind |
| Status | Available on the free tier |
| Input modalities | Text, image, video, audio, PDF |
Description
Gemini 4 Hydrogen is Google’s flagship model for everyday coding and agentic workflows, offering a unified 1-million-token context on the free tier, long decode generation of up to 1 million tokens, and a default max output of 65,536 tokens. The model accepts text, image, video, audio, and PDF input, making it suitable for long-document analysis, codebase understanding, multimodal Q&A, and multi-step agents.
On the free tier, input, output, and context caching are all billed at $0; on the paid tier, input is $1.50 and output is $7.50 per million tokens (including thinking tokens). The free tier only supports implicit caching, and advanced capabilities such as Batch are limited.
Usage Example
curl https://generativelanguage.googleapis.com/v1beta/openai/chat/completions \
-H "Authorization: Bearer $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-hydrogen",
"messages": [{"role": "user", "content": "Analyze the key conclusions in this long document"}]
}'Notes
- Data usage: Free-tier inputs and outputs are used to improve Google products; do not submit sensitive data
- Rate limits: Google does not publish unified numbers in its docs; sign in to the AI Studio console to check
- Feature limits: The free tier only supports implicit context caching; capabilities such as Batch are limited
- Network:
generativelanguage.googleapis.comis not directly reachable from mainland China
Related Links
📚 Related Free Models
These models are also available for $0 on Gemini. Choose by context length and modality.
| Model | Context | Description |
|---|---|---|
| Gemini 3.5 Flash-Lite | 1M | Google’s low-latency, high-throughput multimodal model |
| Gemini 3.6 Flash | 1M | Google’s previous-generation Flash multimodal model |
| Gemini 3.8 Flash | 1M | Google’s latest Flash multimodal model, built for |
📋 View all Gemini free models →