Gemini 4 Carbon: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/us | Healthy | 100%◆ (best) | 87.72% | 50.00% | 50.00% | 37.8s | 222s | 34 tps | 1.0M | $2.20 / $11.00 |
Google AI Studiogoogle-ai-studio | Healthy | 100%◆ (best) | 78.46% | 95.44% | 95.44% | 5.60s◆ (best) | 60.4s | 69 tps◆ (best) | 1.0M | $2.00 / $10.00 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100%◆ (best) | 99.70% | 99.43% | 99.43% | 8.62s | 50.8s | 60 tps | 1.0M | $1.00 / $5.00◆ (best) |
Googlegoogle-vertex/global | Down | 0.00% | 82.15% | 61.27% | 61.27% | 9.85s | 248s | 44 tps | 1.0M | $2.00 / $10.00 |
Googlegoogle-vertex/eu | Degraded | — | 88.12% | 66.67% | 66.67% | 8.96s | 50.2s◆ (best) | 31 tps | 1.0M | $2.20 / $11.00 |
Googlegoogle-vertex/global/priority | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 15.5s | 203s | 24 tps | 1.0M | $3.60 / $18.00 |
Google AI Studiogoogle-ai-studio/priority | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 15.9s | 51.4s | 28 tps | 1.0M | $3.60 / $18.00 |
- Google100%◆ (best)Healthy24h 87.72%
- 7d
- 50.00%
- 30d
- 50.00%
- p50
- 37.8s
- p99
- 222s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
google-vertex/us - Google AI Studio100%◆ (best)Healthy24h 78.46%
- 7d
- 95.44%
- 30d
- 95.44%
- p50
- 5.60s◆ (best)
- p99
- 60.4s
- Throughput
- 69 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00
google-ai-studio - Google AI Studio100%◆ (best)Healthy24h 99.70%
- 7d
- 99.43%
- 30d
- 99.43%
- p50
- 8.62s
- p99
- 50.8s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $5.00◆ (best)
google-ai-studio/flex - Google0.00%Down24h 82.15%
- 7d
- 61.27%
- 30d
- 61.27%
- p50
- 9.85s
- p99
- 248s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00
google-vertex/global - Degraded24h 88.12%
- 7d
- 66.67%
- 30d
- 66.67%
- p50
- 8.96s
- p99
- 50.2s◆ (best)
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
google-vertex/eu - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 15.5s
- p99
- 203s
- Throughput
- 24 tps
- Context
- 1.0M
- $/Mtok
- $3.60 / $18.00
google-vertex/global/priority - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 15.9s
- p99
- 51.4s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $3.60 / $18.00
google-ai-studio/priority
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.