Google Gemini 4 Hydrogen API providers
As of November 14, 2026, Google AI Studio has both the highest reported output speed for Google Gemini 4 Hydrogen, 152 tokens per second, and the lowest listed output price, $3.75 per million tokens. 2 providers serve Google Gemini 4 Hydrogen on OpenRouter.
- Fastest output 152 tok/s G Google AI Studio
Top 5: Google 109 tok/s
- Lowest latency 1.5 s Google
Top 5: Google AI Studio 1.7 s
- Lowest price $3.75 / 1M output G Google AI Studio
Top 5: Google $7.50
Output speed by provider
- Google AI Studio 152 tok/s
- Google 109 tok/s
Median output tokens per second reported by OpenRouter, November 14, 2026.
Every provider serving Google Gemini 4 Hydrogen
| Provider | Output speed | Time to first token | Input price | Output price | Quantization | Context |
|---|---|---|---|---|---|---|
| Google AI StudioFastest measured providergoogle-ai-studio/flex | 152 tok/s | 1.7 s | $0.75 / 1M | $3.75 / 1M | Not published | 1.05M |
| Google AI Studiogoogle-ai-studio/priority | 132 tok/s | 3.1 s | $2.70 / 1M | $13.50 / 1M | Not published | 1.05M |
| Googlegoogle-vertex/global | 109 tok/s | 3.1 s | $1.50 / 1M | $7.50 / 1M | Not published | 1.05M |
| Googlegoogle-vertex/global/priority | 107 tok/s | 1.8 s | $2.70 / 1M | $13.50 / 1M | Not published | 1.05M |
| Google AI Studiogoogle-ai-studio | 100 tok/s | 1.9 s | $1.50 / 1M | $7.50 / 1M | Not published | 1.05M |
| Googlegoogle-vertex/us | 100 tok/s | 1.5 s | $1.65 / 1M | $8.25 / 1M | Not published | 1.05M |
| Googlegoogle-vertex/eu | Not reported | Not reported | $1.65 / 1M | $8.25 / 1M | Not published | 1.05M |
Provider performance and prices are a snapshot from November 14, 2026. Availability and routing can change.
