# Gemini 4 Hydrogen

> Gemini 4 Hydrogen is the speed and efficiency model of Google's Gemini 4 family, built for everyday coding and agentic workflows. It reads text, images, video, audio, and PDFs, answers in text, and has a 1,048,576-token context window with adjustable thinking levels.

**ID**: `google/gemini-4-hydrogen`  
**Creator**: Google  
**Category**: text  
**Context**: 1M tokens  
**Pricing**: $1.50 / $7.50 per 1M · billed by your provider (BYOK)  
**Released**: 2026-11-12  
**Web page**: https://anyrouter.dev/model/google/gemini-4-hydrogen

**Input modalities**: text, image, video, audio  
**Output modalities**: text  

**Tokenizer**: Gemini

**Capabilities**: chat, coding, vision, reasoning

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-4-hydrogen",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| openrouter-byok | $1.50/M (list) | $7.50/M (list) |
| vercel-byok | $1.50/M (list) | $7.50/M (list) |
| nousresearch-byok | $1.50/M (list) | $7.50/M (list) |
| llmgateway-byok | $1.50/M (list) | $7.50/M (list) |
| ofox-byok | $1.50/M (list) | $7.50/M (list) |
| opencode-zen-byok | $1.50/M (list) | $7.50/M (list) |
| zenmux-byok | $1.50/M (list) | $7.50/M (list) |
| aihubmix-byok | $1.50/M (list) | $7.50/M (list) |
| edenai-byok | $1.50/M (list) | $7.50/M (list) |
| nano-gpt-byok | $1.50/M (list) | $7.50/M (list) |
| abacus-byok | $1.50/M (list) | $7.50/M (list) |
| cortecs-byok | $1.50/M (list) | $7.50/M (list) |
| infron-byok | $1.50/M (list) | $7.50/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Model card


### Strengths [1]

- Designed for everyday coding and agentic workflows, with a focus on speed and efficiency (vendor-stated).
- Supports function calling, structured outputs, code execution, computer use, and thinking levels low to xhigh (vendor-stated).

### Known limits [1]

- Output is text only; no audio or image generation and no Live API (vendor-stated).

### Use cases [1]

- Everyday coding and agentic workflows
- Video, image and audio understanding

### Links

- docs: https://aistudio.google.com/docs/models/gemini-4-hydrogen
- Previous version: https://anyrouter.dev/model/google/gemini-4-argon

### Sources

1. [Gemini 4 Hydrogen (Gemini API docs)](https://aistudio.google.com/docs/models/gemini-4-hydrogen) (accessed 2026-11-13)

## Source

- Upstream docs: https://aistudio.google.com/docs/models/gemini-4-hydrogen