Gemini 2.5 Flash: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Google AI Studiogoogle-ai-studio | Healthy | 100%◆ (best) | 99.92% | 99.89%◆ (best) | 99.89%◆ (best) | 608ms◆ (best) | 13.0s | 80 tps | 1.0M | $0.300 / $2.50 |
Google AI Studiogoogle-ai-studio/flex | Healthy | 100%◆ (best) | 99.92% | 99.89%◆ (best) | 99.89%◆ (best) | 2.47s | 6.16s | 3.0 tps | 1.0M | $0.150 / $1.25◆ (best) |
Google AI Studiogoogle-ai-studio/priority | Healthy | 100%◆ (best) | 99.92% | 99.89%◆ (best) | 99.89%◆ (best) | — | — | — | 1.0M | $0.540 / $4.50 |
Googlegoogle-vertex/global | Healthy | 99.97% | 99.75% | 99.55% | 99.55% | 740ms | 4.59s | 94 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex/global/priority | Healthy | 99.97% | 99.75% | 99.55% | 99.55% | 1.22s | 1.67s◆ (best) | 43 tps | 1.0M | $0.540 / $4.50 |
Googlegoogle-vertex/eu | Healthy | 99.87% | 98.84% | 90.32% | 90.32% | 693ms | 3.17s | 80 tps | 1.0M | $0.300 / $2.50 |
Googlegoogle-vertex | Down | — | 90.00% | 78.29% | 78.29% | 3.81s | 11.0s | 128 tps◆ (best) | 1.0M | $0.300 / $2.50 |
- Google AI Studio100%◆ (best)Healthy24h 99.92%
- 7d
- 99.89%◆ (best)
- 30d
- 99.89%◆ (best)
- p50
- 608ms◆ (best)
- p99
- 13.0s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-ai-studio - Google AI Studio100%◆ (best)Healthy24h 99.92%
- 7d
- 99.89%◆ (best)
- 30d
- 99.89%◆ (best)
- p50
- 2.47s
- p99
- 6.16s
- Throughput
- 3.0 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $1.25◆ (best)
google-ai-studio/flex - Google AI Studio100%◆ (best)Healthy24h 99.92%
- 7d
- 99.89%◆ (best)
- 30d
- 99.89%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-ai-studio/priority - Google99.97%Healthy24h 99.75%
- 7d
- 99.55%
- 30d
- 99.55%
- p50
- 740ms
- p99
- 4.59s
- Throughput
- 94 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/global - Google99.97%Healthy24h 99.75%
- 7d
- 99.55%
- 30d
- 99.55%
- p50
- 1.22s
- p99
- 1.67s◆ (best)
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $0.540 / $4.50
google-vertex/global/priority - Google99.87%Healthy24h 98.84%
- 7d
- 90.32%
- 30d
- 90.32%
- p50
- 693ms
- p99
- 3.17s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex/eu - Down24h 90.00%
- 7d
- 78.29%
- 30d
- 78.29%
- p50
- 3.81s
- p99
- 11.0s
- Throughput
- 128 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50
google-vertex
Measured 2m 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.