Gemma 4 26B A4B : 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.97% | 99.96% | 99.56% | 348ms | 1.91s | 76 tps | 262K | $0.100 / $0.300 | |
Darkbloomdarkbloom | Healthy | 100%◆ (best) | 99.99% | 99.99%◆ (best) | 99.94%◆ (best) | 1.06s | 5.59s | 43 tps | 131K | $0.042 / $0.220◆ (best) |
| Healthy | 100%◆ (best) | 99.80% | 99.80% | 99.80% | 544ms | 3.20s | 78 tps | 262K | $0.060 / $0.330 | |
Makoramakora | Healthy | 100%◆ (best) | 98.95% | 96.94% | 97.59% | 159ms◆ (best) | 1.27s◆ (best) | 225 tps◆ (best) | 256K | $0.080 / $0.320 |
| Healthy | 100%◆ (best) | 99.07% | 98.89% | 98.86% | 527ms | 3.78s | 95 tps | 262K | $0.130 / $0.400 | |
| Healthy | 99.97% | 99.73% | 98.66% | 98.98% | 468ms | 3.16s | 70 tps | 262K | $0.059 / $0.255 | |
| Healthy | 99.96% | 99.93% | 99.92% | 99.31% | 234ms | 1.57s | 84 tps | 262K | $0.076 / $0.255 | |
| Healthy | 99.89% | 99.77% | 99.61% | 99.41% | 650ms | 5.90s | 29 tps | 262K | $0.070 / $0.340 | |
| Healthy | 99.83% | 99.81% | 99.79% | 99.49% | 917ms | 3.66s | 38 tps | 262K | $0.130 / $0.400 | |
Cloudflarecloudflare | Healthy | 99.80% | 99.86% | 99.81% | 99.55% | 628ms | 12.6s | 48 tps | 256K | $0.100 / $0.300 |
| Healthy | 99.64% | 98.74% | 99.44% | 98.94% | 802ms | 4.30s | 46 tps | 256K | $0.130 / $0.400 | |
Googlegoogle-vertex/global | Healthy | 99.54% | 97.76% | 96.56% | 96.78% | 768ms | 7.51s | 29 tps | 262K | $0.150 / $0.600 |
| Healthy | 99.20% | 95.66% | 93.59% | 96.43% | 1.25s | 4.81s | 58 tps | 262K | $0.140 / $0.400 | |
Rekareka | No data | — | — | 93.26% | 98.59% | — | — | — | 262K | $0.060 / $0.200 |
- CoreWeave100%◆ (best)Healthy24h 99.97%
- 7d
- 99.96%
- 30d
- 99.56%
- p50
- 348ms
- p99
- 1.91s
- Throughput
- 76 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
coreweave/bf16bf16 - Darkbloom100%◆ (best)Healthy24h 99.99%
- 7d
- 99.99%◆ (best)
- 30d
- 99.94%◆ (best)
- p50
- 1.06s
- p99
- 5.59s
- Throughput
- 43 tps
- Context
- 131K
- $/Mtok
- $0.042 / $0.220◆ (best)
darkbloom - DekaLLM100%◆ (best)Healthy24h 99.80%
- 7d
- 99.80%
- 30d
- 99.80%
- p50
- 544ms
- p99
- 3.20s
- Throughput
- 78 tps
- Context
- 262K
- $/Mtok
- $0.060 / $0.330
dekallm/bf16bf16 - Makora100%◆ (best)Healthy24h 98.95%
- 7d
- 96.94%
- 30d
- 97.59%
- p50
- 159ms◆ (best)
- p99
- 1.27s◆ (best)
- Throughput
- 225 tps◆ (best)
- Context
- 256K
- $/Mtok
- $0.080 / $0.320
makora - Parasail100%◆ (best)Healthy24h 99.07%
- 7d
- 98.89%
- 30d
- 98.86%
- p50
- 527ms
- p99
- 3.78s
- Throughput
- 95 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.400
parasail/bf16bf16 - Io Net99.97%Healthy24h 99.73%
- 7d
- 98.66%
- 30d
- 98.98%
- p50
- 468ms
- p99
- 3.16s
- Throughput
- 70 tps
- Context
- 262K
- $/Mtok
- $0.059 / $0.255
io-net/bf16bf16 - NextBit99.96%Healthy24h 99.93%
- 7d
- 99.92%
- 30d
- 99.31%
- p50
- 234ms
- p99
- 1.57s
- Throughput
- 84 tps
- Context
- 262K
- $/Mtok
- $0.076 / $0.255
nextbit/bf16bf16 - DeepInfra99.89%Healthy24h 99.77%
- 7d
- 99.61%
- 30d
- 99.41%
- p50
- 650ms
- p99
- 5.90s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.340
deepinfra/fp8fp8 - Novita99.83%Healthy24h 99.81%
- 7d
- 99.79%
- 30d
- 99.49%
- p50
- 917ms
- p99
- 3.66s
- Throughput
- 38 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.400
novita/bf16bf16 - Cloudflare99.80%Healthy24h 99.86%
- 7d
- 99.81%
- 30d
- 99.55%
- p50
- 628ms
- p99
- 12.6s
- Throughput
- 48 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.300
cloudflare - Venice99.64%Healthy24h 98.74%
- 7d
- 99.44%
- 30d
- 98.94%
- p50
- 802ms
- p99
- 4.30s
- Throughput
- 46 tps
- Context
- 256K
- $/Mtok
- $0.130 / $0.400
venice/bf16bf16 - Google99.54%Healthy24h 97.76%
- 7d
- 96.56%
- 30d
- 96.78%
- p50
- 768ms
- p99
- 7.51s
- Throughput
- 29 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600
google-vertex/global - SiliconFlow99.20%Healthy24h 95.66%
- 7d
- 93.59%
- 30d
- 96.43%
- p50
- 1.25s
- p99
- 4.81s
- Throughput
- 58 tps
- Context
- 262K
- $/Mtok
- $0.140 / $0.400
siliconflow/fp8fp8 - Reka—No data24h —
- 7d
- 93.26%
- 30d
- 98.59%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.060 / $0.200
reka
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, averaged over the hour.
Throughput
Median tokens per second.