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% | 3.15s | 26.7s | 60 tps | 131K | $0.037 / $0.187 | |
Amazon Bedrockamazon-bedrock | Healthy | 100%◆ (best) | 99.40% | 99.91% | 98.18% | 566ms | 17.5s | 171 tps | 131K | $0.150 / $0.600 |
| Healthy | 100%◆ (best) | 99.97% | 99.85% | 99.93% | 266ms | 796ms◆ (best) | 118 tps | 128K | $0.100 / $0.500 | |
| Healthy | 100%◆ (best) | 99.98% | 99.95% | 99.95% | 220ms◆ (best) | 2.93s | 710 tps◆ (best) | 131K | $0.350 / $0.750 | |
| Healthy | 100%◆ (best) | 99.99% | 99.96% | 99.64% | 282ms | 1.49s | 116 tps | 131K | $0.050 / $0.250 | |
| Healthy | 100%◆ (best) | 99.98% | 99.96% | 99.97%◆ (best) | 478ms | 1.79s | 127 tps | 131K | $0.150 / $0.600 | |
DigitalOceandigitalocean | Healthy | 100%◆ (best) | 99.98% | 99.94% | 99.94% | 359ms | 1.75s | 39 tps | 128K | $0.060 / $0.420 |
| Healthy | 100%◆ (best) | 97.43% | 98.96% | 99.06% | 675ms | 7.32s | 34 tps | 131K | $0.045 / $0.250 | |
| Healthy | 100%◆ (best) | 97.66% | 96.46% | 97.77% | 306ms | 5.93s | 182 tps | 131K | $0.150 / $0.600 | |
| Healthy | 100%◆ (best) | 98.44% | 99.07% | 92.15% | 924ms | 7.70s | 128 tps | 131K | $0.050 / $0.250 | |
| Healthy | 100%◆ (best) | 99.97% | 99.89% | 99.35% | 379ms | 1.34s | 109 tps | 131K | $0.100 / $0.750 | |
Phalaphala | Healthy | 100%◆ (best) | 98.91% | 99.26% | 92.30% | 905ms | 4.99s | 98 tps | 131K | $0.150 / $0.600 |
SambaNovasambanova | Healthy | 100%◆ (best) | 99.76% | 99.41% | 96.63% | 477ms | 4.86s | 198 tps | 131K | $0.140 / $0.950 |
| Healthy | 99.99% | 97.03% | 98.61% | 99.02% | 364ms | 10.9s | 42 tps | 131K | $0.037 / $0.170 | |
Groqgroq | Healthy | 99.73% | 99.39% | 99.09% | 99.64% | 319ms | 2.45s | 269 tps | 131K | $0.150 / $0.600 |
| Healthy | 99.72% | 99.52% | 99.47% | 99.43% | 690ms | 38.2s | 24 tps | 131K | $0.030 / $0.180◆ (best) | |
| Healthy | 99.68% | 98.94% | 99.00% | 99.68% | 416ms | 24.1s | 35 tps | 131K | $0.030 / $0.170◆ (best) | |
Maramara | Degraded | 95.24% | 95.71% | 93.50% | 85.83% | 810ms | 13.7s | 121 tps | 131K | $0.150 / $0.750 |
Togethertogether | Down | 78.59% | 88.71% | 92.66% | 92.64% | 248ms | 1.94s | 78 tps | 131K | $0.150 / $0.600 |
Googlegoogle-vertex/global | Down | 78.19% | 67.30% | 54.90% | 78.14% | 447ms | 6.85s | 152 tps | 131K | $0.090 / $0.360 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 99.97% | 98.34% | 99.10% | 429ms | 10.2s | 120 tps | 131K | $0.150 / $0.600 |
| No data | — | — | 69.26% | 85.97% | — | — | — | 131K | $0.200 / $0.950 | |
| Down | — | 90.61% | 86.28% | 88.15% | — | — | — | 131K | $0.150 / $0.600 |
- AkashML100%◆ (best)Healthy24h 99.95%
- 7d
- 99.97%◆ (best)
- 30d
- 99.91%
- p50
- 3.15s
- p99
- 26.7s
- Throughput
- 60 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.187
akashml/bf16bf16 - Amazon Bedrock100%◆ (best)Healthy24h 99.40%
- 7d
- 99.91%
- 30d
- 98.18%
- p50
- 566ms
- p99
- 17.5s
- Throughput
- 171 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - BaseTen100%◆ (best)Healthy24h 99.97%
- 7d
- 99.85%
- 30d
- 99.93%
- p50
- 266ms
- p99
- 796ms◆ (best)
- Throughput
- 118 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4fp4 - Cerebras100%◆ (best)Healthy24h 99.98%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 220ms◆ (best)
- p99
- 2.93s
- Throughput
- 710 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.350 / $0.750
cerebras/fp16fp16 - Crusoe100%◆ (best)Healthy24h 99.99%
- 7d
- 99.96%
- 30d
- 99.64%
- p50
- 282ms
- p99
- 1.49s
- 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
- 478ms
- p99
- 1.79s
- Throughput
- 127 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - DigitalOcean100%◆ (best)Healthy24h 99.98%
- 7d
- 99.94%
- 30d
- 99.94%
- p50
- 359ms
- p99
- 1.75s
- Throughput
- 39 tps
- Context
- 128K
- $/Mtok
- $0.060 / $0.420
digitalocean - Mancer 2100%◆ (best)Healthy24h 97.43%
- 7d
- 98.96%
- 30d
- 99.06%
- p50
- 675ms
- p99
- 7.32s
- Throughput
- 34 tps
- Context
- 131K
- $/Mtok
- $0.045 / $0.250
mancer/fp8fp8 - Nebius100%◆ (best)Healthy24h 97.66%
- 7d
- 96.46%
- 30d
- 97.77%
- p50
- 306ms
- p99
- 5.93s
- Throughput
- 182 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - Novita100%◆ (best)Healthy24h 98.44%
- 7d
- 99.07%
- 30d
- 92.15%
- p50
- 924ms
- p99
- 7.70s
- Throughput
- 128 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
novita/fp4fp4 - Parasail100%◆ (best)Healthy24h 99.97%
- 7d
- 99.89%
- 30d
- 99.35%
- p50
- 379ms
- p99
- 1.34s
- Throughput
- 109 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.750
parasail/fp4fp4 - Phala100%◆ (best)Healthy24h 98.91%
- 7d
- 99.26%
- 30d
- 92.30%
- p50
- 905ms
- p99
- 4.99s
- Throughput
- 98 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - SambaNova100%◆ (best)Healthy24h 99.76%
- 7d
- 99.41%
- 30d
- 96.63%
- p50
- 477ms
- p99
- 4.86s
- Throughput
- 198 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.950
sambanova - DeepInfra99.99%Healthy24h 97.03%
- 7d
- 98.61%
- 30d
- 99.02%
- p50
- 364ms
- p99
- 10.9s
- Throughput
- 42 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - Groq99.73%Healthy24h 99.39%
- 7d
- 99.09%
- 30d
- 99.64%
- p50
- 319ms
- p99
- 2.45s
- Throughput
- 269 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
groq - DekaLLM99.72%Healthy24h 99.52%
- 7d
- 99.47%
- 30d
- 99.43%
- p50
- 690ms
- p99
- 38.2s
- Throughput
- 24 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.180◆ (best)
dekallm/bf16bf16 - CoreWeave99.68%Healthy24h 98.94%
- 7d
- 99.00%
- 30d
- 99.68%
- p50
- 416ms
- p99
- 24.1s
- Throughput
- 35 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170◆ (best)
coreweave/fp4fp4 - Mara95.24%Degraded24h 95.71%
- 7d
- 93.50%
- 30d
- 85.83%
- p50
- 810ms
- p99
- 13.7s
- Throughput
- 121 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.750
mara - Together78.59%Down24h 88.71%
- 7d
- 92.66%
- 30d
- 92.64%
- p50
- 248ms
- p99
- 1.94s
- Throughput
- 78 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
together - Google78.19%Down24h 67.30%
- 7d
- 54.90%
- 30d
- 78.14%
- p50
- 447ms
- p99
- 6.85s
- Throughput
- 152 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.360
google-vertex/global - No data24h 99.97%
- 7d
- 98.34%
- 30d
- 99.10%
- p50
- 429ms
- p99
- 10.2s
- Throughput
- 120 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 90.61%
- 7d
- 86.28%
- 30d
- 88.15%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
siliconflow/fp8fp8
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.