gpt-oss-20b
openai/gpt-oss-20b
Compare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Comparegpt-oss-20b
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock | Healthy | 100% | 98.30% | 438ms | 1.49s | 316 tps | 131K | $0.070 / $0.150 |
| Healthy | 100% | 99.92% | 547ms | 13.2s | 98 tps | 131K | $0.040 / $0.150 | |
| Healthy | 100% | 98.17% | 1.24s | 22.3s | 29 tps | 131K | $0.040 / $0.180 | |
| Healthy | 99.94% | 99.90% | 258ms | 3.91s | 96 tps | 131K | $0.030 / $0.140 | |
| Healthy | 99.22% | 99.30% | 273ms | 2.06s | 72 tps | 131K | $0.030 / $0.130 | |
Googlegoogle-vertex/us-central1 | Down | 98.53% | 83.56% | 26.0s | 56.8s | 1.5 tps | 131K | $0.070 / $0.250 |
Groqgroq | Healthy | 98.48% | 98.03% | 657ms | 4.68s | 365 tps | 131K | $0.075 / $0.300 |
Fireworksfireworks | Healthy | 97.75% | 97.47% | 311ms | 7.29s | 178 tps | 131K | $0.070 / $0.300 |
| Healthy | 97.18% | 99.14% | 431ms | 7.67s | 62 tps | 131K | $0.030 / $0.150 | |
Phalaphala | Degraded | 90.91% | 91.61% | 662ms | 7.66s | 45 tps | 131K | $0.040 / $0.150 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | — | — | — | — | 131K | $0.070 / $0.150 |
Togethertogether | No data | — | 96.45% | 528ms | 8.73s | 84 tps | 131K | $0.050 / $0.200 |
- Amazon Bedrock100%Healthy24h 98.30%
- p50
- 438ms
- p99
- 1.49s
- Throughput
- 316 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock - Novita100%Healthy24h 99.92%
- p50
- 547ms
- p99
- 13.2s
- Throughput
- 98 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
novita/fp4fp4 - SiliconFlow100%Healthy24h 98.17%
- p50
- 1.24s
- p99
- 22.3s
- Throughput
- 29 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.180
siliconflow/fp8fp8 - DeepInfra99.94%Healthy24h 99.90%
- p50
- 258ms
- p99
- 3.91s
- Throughput
- 96 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - CoreWeave99.22%Healthy24h 99.30%
- p50
- 273ms
- p99
- 2.06s
- Throughput
- 72 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4 - Google98.53%Down24h 83.56%
- p50
- 26.0s
- p99
- 56.8s
- Throughput
- 1.5 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.250
google-vertex/us-central1 - Groq98.48%Healthy24h 98.03%
- p50
- 657ms
- p99
- 4.68s
- Throughput
- 365 tps
- Context
- 131K
- $/Mtok
- $0.075 / $0.300
groq - Fireworks97.75%Healthy24h 97.47%
- p50
- 311ms
- p99
- 7.29s
- Throughput
- 178 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.300
fireworks - Parasail97.18%Healthy24h 99.14%
- p50
- 431ms
- p99
- 7.67s
- Throughput
- 62 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
parasail/fp4fp4 - Phala90.91%Degraded24h 91.61%
- p50
- 662ms
- p99
- 7.66s
- Throughput
- 45 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
phala - No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock/eu-west-1 - No data24h 96.45%
- p50
- 528ms
- p99
- 8.73s
- Throughput
- 84 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.200
together
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are omitted from the charts.
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.