Gemma 4 26B A4B (free): 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Darkbloomdarkbloom | No data | — | — | 96.11% | 96.11% | — | — | — | 131K | free / free◆ (best) |
Google AI Studiogoogle-ai-studio | No data | — | 99.62% | 99.71%◆ (best) | 99.71%◆ (best) | 929ms | 6.07s | 42 tps | 262K | free / free◆ (best) |
- No data24h —
- 7d
- 96.11%
- 30d
- 96.11%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- free / free◆ (best)
darkbloom - No data24h 99.62%
- 7d
- 99.71%◆ (best)
- 30d
- 99.71%◆ (best)
- p50
- 929ms
- p99
- 6.07s
- Throughput
- 42 tps
- Context
- 262K
- $/Mtok
- free / free◆ (best)
google-ai-studio
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.