Google Gemini 4 Neon API providers
As of November 22, 2026, Google has the highest reported output speed for Google Gemini 4 Neon, 82 tokens per second, and Google AI Studio has the lowest listed output price, $7.50 per million tokens. 2 providers serve Google Gemini 4 Neon on OpenRouter.
- Fastest output 82 tok/s Google
Top 5: Google AI Studio 69 tok/s
- Lowest latency 3.4 s Google
Top 5: Google AI Studio 5.0 s
- Lowest price $7.50 / 1M output G Google AI Studio
Top 5: Google $15.00
Output speed by provider
- Google 82 tok/s
- Google AI Studio 69 tok/s
Median output tokens per second reported by OpenRouter, November 22, 2026.
Every provider serving Google Gemini 4 Neon
| Provider | Output speed | Time to first token | Input price | Output price | Quantization | Context |
|---|---|---|---|---|---|---|
| GoogleFastest measured providergoogle-vertex/global | 82 tok/s | 3.4 s | $3.00 / 1M | $15.00 / 1M | Not published | 1.05M |
| Googlegoogle-vertex/global/priority | 71 tok/s | 4.9 s | $5.40 / 1M | $27.00 / 1M | Not published | 1.05M |
| Google AI Studiogoogle-ai-studio/flex | 69 tok/s | 5.0 s | $1.50 / 1M | $7.50 / 1M | Not published | 1.05M |
| Google AI Studiogoogle-ai-studio | 48 tok/s | 5.2 s | $3.00 / 1M | $15.00 / 1M | Not published | 1.05M |
| Google AI Studiogoogle-ai-studio/priority | Not reported | Not reported | $5.40 / 1M | $27.00 / 1M | Not published | 1.05M |
Provider performance and prices are a snapshot from November 22, 2026. Availability and routing can change.