Google Gemini 4 Carbon API providers
As of November 14, 2026, Google and Google AI Studio share the highest reported output speed for Google Gemini 4 Carbon, at 59 tokens per second. 2 of 2 listed providers have reported speed measurements. The lowest listed output-token price is $5.00 per million tokens from Google AI Studio.
- Fastest output 59 tok/s Google and Google AI Studio
- Lowest latency 4.4 s Google
Top 5: Google AI Studio 7.5 s
- Lowest price $5.00 / 1M output G Google AI Studio
Top 5: Google $10.00
Output speed by provider
- Google 59 tok/s
- Google AI Studio 59 tok/s
Median output tokens per second reported by OpenRouter, November 14, 2026.
Every provider serving Google Gemini 4 Carbon
| Provider | Output speed | Time to first token | Input price | Output price | Quantization | Context |
|---|---|---|---|---|---|---|
| Google AI StudioFastest measured providergoogle-ai-studio/flex | 59 tok/s | 7.5 s | $1.00 / 1M | $5.00 / 1M | Not published | 1.05M |
| GoogleFastest measured providergoogle-vertex/eu | 59 tok/s | 9.0 s | $2.20 / 1M | $11.00 / 1M | Not published | 1.05M |
| Googlegoogle-vertex/us | 38 tok/s | 4.9 s | $2.20 / 1M | $11.00 / 1M | Not published | 1.05M |
| Google AI Studiogoogle-ai-studio | 32 tok/s | 8.7 s | $2.00 / 1M | $10.00 / 1M | Not published | 1.05M |
| Google AI Studiogoogle-ai-studio/priority | 29 tok/s | 10 s | $3.60 / 1M | $18.00 / 1M | Not published | 1.05M |
| Googlegoogle-vertex/global/priority | 21 tok/s | 9.9 s | $3.60 / 1M | $18.00 / 1M | Not published | 1.05M |
| Googlegoogle-vertex/global | 18 tok/s | 4.4 s | $2.00 / 1M | $10.00 / 1M | Not published | 1.05M |
Provider performance and prices are a snapshot from November 14, 2026. Availability and routing can change.
