gpt-oss-120b: 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) | 99.95% | 99.97%◆ (best) | 99.91% | 3.04s | 25.6s | 64 tps | 131K | $0.037 / $0.187 | |
Amazon Bedrockamazon-bedrock | Healthy | 100%◆ (best) | 99.41% | 99.91% | 98.18% | 561ms | 17.6s | 174 tps | 131K | $0.150 / $0.600 |
| Healthy | 100%◆ (best) | 99.97% | 99.85% | 99.93% | 268ms | 789ms◆ (best) | 114 tps | 128K | $0.100 / $0.500 | |
| Healthy | 100%◆ (best) | 99.98% | 99.95% | 99.95% | 217ms◆ (best) | 2.64s | 754 tps◆ (best) | 131K | $0.350 / $0.750 | |
| Healthy | 100%◆ (best) | 99.99% | 99.96% | 99.64% | 280ms | 1.47s | 116 tps | 131K | $0.050 / $0.250 | |
| Healthy | 100%◆ (best) | 99.98% | 99.96% | 99.97%◆ (best) | 480ms | 1.66s | 127 tps | 131K | $0.150 / $0.600 | |
DigitalOceandigitalocean | Healthy | 100%◆ (best) | 99.98% | 99.94% | 99.94% | 375ms | 1.89s | 38 tps | 128K | $0.060 / $0.420 |
| Healthy | 100%◆ (best) | 97.47% | 98.96% | 99.06% | 674ms | 7.74s | 34 tps | 131K | $0.045 / $0.250 | |
| Healthy | 100%◆ (best) | 97.67% | 96.46% | 97.77% | 298ms | 5.92s | 187 tps | 131K | $0.150 / $0.600 | |
| Healthy | 100%◆ (best) | 98.44% | 99.07% | 92.15% | 954ms | 7.63s | 130 tps | 131K | $0.050 / $0.250 | |
| Healthy | 100%◆ (best) | 99.97% | 99.89% | 99.35% | 387ms | 1.47s | 110 tps | 131K | $0.100 / $0.750 | |
Phalaphala | Healthy | 100%◆ (best) | 98.91% | 99.26% | 92.30% | 902ms | 4.51s | 102 tps | 131K | $0.150 / $0.600 |
| Healthy | 99.99% | 97.04% | 98.61% | 99.02% | 368ms | 10.0s | 42 tps | 131K | $0.037 / $0.170 | |
Groqgroq | Healthy | 99.72% | 99.39% | 99.09% | 99.64% | 316ms | 2.45s | 270 tps | 131K | $0.150 / $0.600 |
| Healthy | 99.65% | 99.52% | 99.47% | 99.43% | 673ms | 30.8s | 25 tps | 131K | $0.030 / $0.180◆ (best) | |
Togethertogether | Degraded | 99.51% | 88.79% | 92.66% | 92.64% | 254ms | 1.44s | 79 tps | 131K | $0.150 / $0.600 |
SambaNovasambanova | Healthy | 99.49% | 99.76% | 99.41% | 96.63% | 492ms | 5.37s | 214 tps | 131K | $0.140 / $0.950 |
| Healthy | 99.20% | 98.94% | 99.00% | 99.68% | 414ms | 21.4s | 35 tps | 131K | $0.030 / $0.170◆ (best) | |
Maramara | Degraded | 93.85% | 95.63% | 93.50% | 85.83% | 775ms | 13.2s | 129 tps | 131K | $0.150 / $0.750 |
Googlegoogle-vertex/global | Down | 79.19% | 67.27% | 54.90% | 78.14% | 447ms | 6.03s | 157 tps | 131K | $0.090 / $0.360 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 99.97% | 98.34% | 99.10% | 438ms | 10.1s | 123 tps | 131K | $0.150 / $0.600 |
| No data | — | — | 69.26% | 85.97% | — | — | — | 131K | $0.200 / $0.950 | |
| Down | — | 90.76% | 86.28% | 88.15% | — | — | — | 131K | $0.150 / $0.600 |
- AkashML100%◆ (best)Healthy24h 99.95%
- 7d
- 99.97%◆ (best)
- 30d
- 99.91%
- p50
- 3.04s
- p99
- 25.6s
- Throughput
- 64 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.187
akashml/bf16bf16 - Amazon Bedrock100%◆ (best)Healthy24h 99.41%
- 7d
- 99.91%
- 30d
- 98.18%
- p50
- 561ms
- p99
- 17.6s
- Throughput
- 174 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - BaseTen100%◆ (best)Healthy24h 99.97%
- 7d
- 99.85%
- 30d
- 99.93%
- p50
- 268ms
- p99
- 789ms◆ (best)
- Throughput
- 114 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4fp4 - Cerebras100%◆ (best)Healthy24h 99.98%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 217ms◆ (best)
- p99
- 2.64s
- Throughput
- 754 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.350 / $0.750
cerebras/fp16fp16 - Crusoe100%◆ (best)Healthy24h 99.99%
- 7d
- 99.96%
- 30d
- 99.64%
- p50
- 280ms
- p99
- 1.47s
- Throughput
- 116 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
crusoe/bf16bf16 - DeepInfra100%◆ (best)Healthy24h 99.98%
- 7d
- 99.96%
- 30d
- 99.97%◆ (best)
- p50
- 480ms
- p99
- 1.66s
- Throughput
- 127 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - DigitalOcean100%◆ (best)Healthy24h 99.98%
- 7d
- 99.94%
- 30d
- 99.94%
- p50
- 375ms
- p99
- 1.89s
- Throughput
- 38 tps
- Context
- 128K
- $/Mtok
- $0.060 / $0.420
digitalocean - Mancer 2100%◆ (best)Healthy24h 97.47%
- 7d
- 98.96%
- 30d
- 99.06%
- p50
- 674ms
- p99
- 7.74s
- Throughput
- 34 tps
- Context
- 131K
- $/Mtok
- $0.045 / $0.250
mancer/fp8fp8 - Nebius100%◆ (best)Healthy24h 97.67%
- 7d
- 96.46%
- 30d
- 97.77%
- p50
- 298ms
- p99
- 5.92s
- Throughput
- 187 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - Novita100%◆ (best)Healthy24h 98.44%
- 7d
- 99.07%
- 30d
- 92.15%
- p50
- 954ms
- p99
- 7.63s
- Throughput
- 130 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
novita/fp4fp4 - Parasail100%◆ (best)Healthy24h 99.97%
- 7d
- 99.89%
- 30d
- 99.35%
- p50
- 387ms
- p99
- 1.47s
- Throughput
- 110 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.750
parasail/fp4fp4 - Phala100%◆ (best)Healthy24h 98.91%
- 7d
- 99.26%
- 30d
- 92.30%
- p50
- 902ms
- p99
- 4.51s
- Throughput
- 102 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - DeepInfra99.99%Healthy24h 97.04%
- 7d
- 98.61%
- 30d
- 99.02%
- p50
- 368ms
- p99
- 10.0s
- Throughput
- 42 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - Groq99.72%Healthy24h 99.39%
- 7d
- 99.09%
- 30d
- 99.64%
- p50
- 316ms
- p99
- 2.45s
- Throughput
- 270 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
groq - DekaLLM99.65%Healthy24h 99.52%
- 7d
- 99.47%
- 30d
- 99.43%
- p50
- 673ms
- p99
- 30.8s
- Throughput
- 25 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.180◆ (best)
dekallm/bf16bf16 - Together99.51%Degraded24h 88.79%
- 7d
- 92.66%
- 30d
- 92.64%
- p50
- 254ms
- p99
- 1.44s
- Throughput
- 79 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
together - SambaNova99.49%Healthy24h 99.76%
- 7d
- 99.41%
- 30d
- 96.63%
- p50
- 492ms
- p99
- 5.37s
- Throughput
- 214 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.950
sambanova - CoreWeave99.20%Healthy24h 98.94%
- 7d
- 99.00%
- 30d
- 99.68%
- p50
- 414ms
- p99
- 21.4s
- Throughput
- 35 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170◆ (best)
coreweave/fp4fp4 - Mara93.85%Degraded24h 95.63%
- 7d
- 93.50%
- 30d
- 85.83%
- p50
- 775ms
- p99
- 13.2s
- Throughput
- 129 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.750
mara - Google79.19%Down24h 67.27%
- 7d
- 54.90%
- 30d
- 78.14%
- p50
- 447ms
- p99
- 6.03s
- Throughput
- 157 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.360
google-vertex/global - No data24h 99.97%
- 7d
- 98.34%
- 30d
- 99.10%
- p50
- 438ms
- p99
- 10.1s
- Throughput
- 123 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock/eu-west-1 - No data24h —
- 7d
- 69.26%
- 30d
- 85.97%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.200 / $0.950
deepinfra/fp8fp8 - Down24h 90.76%
- 7d
- 86.28%
- 30d
- 88.15%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
siliconflow/fp8fp8
Measured 5m 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.