Gemini 4 Hydrogen API Pricing & Monthly Cost Simulator
Verified 2026 unit economics for Google Gemini 4 Hydrogen (google/gemini-4-hydrogen): $1.5/1M uncached input, $0.075/1M cached prefix read, and $7.5/1M output across a 1,048,576-token context window (released 2026-11-12).
Uncached Input (/1M)
$1.5
Cached Prompt Read (/1M)
$0.075 (-95%)
Output Completion (/1M)
$7.5
50% Batch API (In / Out)
$0.75 / $3.75
Interactive 30-Day Monthly Spend Simulator
Live Unit-Cost & Prompt Cache Slider (Gemini 4 Hydrogen)
google/gemini-4-hydrogen
Estimated 30-day spend
$274.50/mo
Cost per 1,000 calls
$9.1500
Monthly savings vs 0% cache
$85.50/mo
Technical Limits & API Capabilities
Context window
1,048,576
Max output tokens
943,718
Workload tier
Coding & Agent
Input modalities
text, audio, file, image, video
Tool Calling: Yes
JSON Schema Strict: Yes
Reasoning Tokens: Supported
50% Batch API: Available
Same-Category 2026 Model Alternatives (Coding & Agent)
| Model | Provider | Input / Cached ($/1M) | Output ($/1M) | Context / Max Out |
|---|---|---|---|---|
| Gemini 4 Hydrogen | $1.5 / $0.075 | $7.5 | 1,048,576 / 943,718 | |
| Gemini 4 Carbon | $2 / $0.1 | $10 | 1,048,576 / 943,718 | |
| Muse Ember | Meta | $0.1 / $0.004 | $0.5 | 1,048,576 / 943,718 |
| GPT-6.1 Terra | OpenAI | $1 / $0.05 | $5 | 1,050,000 / 128,000 |
| MiniMax M3.1 Flash | MiniMax | $0.15 / $0.015 | $0.6 | 1,048,576 / 524,288 |
| Muse Spark Open | Meta | $1.25 / $0.15 | $4.25 | 1,048,576 / 943,718 |
| Gemini 4 Argon | $2 / $0.1 | $10 | 1,048,576 / 943,718 |
Head-to-Head Matchups Featuring Gemini 4 Hydrogen
- GPT-6.1 Terra Pro vs Gemini 4 Hydrogen — $1 vs $1.5 / 1M
Frequently Asked Questions
How much does Gemini 4 Hydrogen cost per 1 million tokens in 2026?
Gemini 4 Hydrogen by Google is billed at $1.5 per 1M uncached input tokens, $0.075 per 1M cached input read tokens (95% cache discount), and $7.5 per 1M output tokens.
What are the context window and max output token limits for Gemini 4 Hydrogen?
Gemini 4 Hydrogen supports a 1,048,576-token input context window and up to 943,718 completion output tokens per request, accepting text, audio, file, image, video inputs.
Does Gemini 4 Hydrogen support strict JSON Schema outputs, tool calling, and Batch API?
Gemini 4 Hydrogen capability profile: tool calling = Supported, strict JSON Schema structured outputs = Supported, reasoning mode = Supported, and 50% asynchronous Batch API = Supported.