GGoogle · Released Nov 12, 2026
Gemini 4 Hydrogen
Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...
- Released
- Nov 12 2026
- Context window
- 1M 944K out
- Input / 1M tokens
- $1.50 from $0.75
- Output / 1M tokens
- $7.50 from $3.75
Where to run it
9 providers compared
Cheapest: Google AI Studio, Kilo Gateway at $0.75 / $3.75 per 1M input / output tokens — 72% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Google AI Studio | $0.75 | $3.75 | $0.038 | 1M | 944K | 100%24h | Cheapest |
| Kilo Gateway | $0.75 | $3.75 | $0.038 | 1M | 944K | — | Cheapest |
| Googleglobal | $1.50 | $7.50 | $0.075 | 1M | 944K | 100%24h | +100% |
| Google AI Studio | $1.50 | $7.50 | $0.075 | 1M | 66K | 93.5%24h | +100% |
| NanoGPT | $1.50 | $7.50 | $0.075 | 1M | 66K | — | +100% |
| Merge Gateway | $1.50 | $7.50 | $0.075 | 1M | 66K | — | +100% |
| OpenCode | $1.50 | $7.50 | $0.075 | 1M | 66K | — | +100% |
| Vercel AI Gateway | $1.50 | $7.50 | $0.075 | 1M | 1M | — | +100% |
| Eden AI | $1.50 | $7.50 | $0.075 | 1M | 66K | — | +100% |
| Vertex | $1.50 | $7.50 | $0.075 | 1M | 66K | — | +100% |
| Googleeu | $1.65 | $8.25 | $0.083 | 1M | 66K | 100%24h | +120% |
| Googleus | $1.65 | $8.25 | $0.083 | 1M | 66K | 100%24h | +120% |
| Googleglobal/priority | $2.70 | $13.50 | $0.14 | 1M | 944K | 100%24h | +260% |
| Google AI Studiopriority | $2.70 | $13.50 | $0.14 | 1M | 944K | 100%24h | +260% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Gemini 4 Hydrogen. Scores appear here automatically once it does.
Specs
Details
- Model ID
google/gemini-4-hydrogen- Developer
- Release date
- Nov 12, 2026 ·
- Context window
- 1,048,576 tokens
- Max output
- 943,718 tokens
- API price
- $1.50 / $7.50 per 1M input / output tokens
- Providers
- 9
- Input types
- audio, file, image, text, video
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.