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% | 98.31% | 99.12% | 99.12% | 396ms | 2.03s | 414 tps | 131K | $0.070 / $0.150 |
| Healthy | 100% | 96.97% | 99.11% | 99.11% | 575ms | 27.8s | 101 tps | 131K | $0.040 / $0.150 | |
| Healthy | 99.83% | 99.89% | 99.49% | 99.49% | 297ms | 23.6s | 77 tps | 131K | $0.030 / $0.140 | |
Groqgroq | Healthy | 99.79% | 98.05% | 98.09% | 98.09% | 402ms | 2.76s | 296 tps | 131K | $0.075 / $0.300 |
| Healthy | 98.35% | 99.30% | 99.26% | 99.26% | 277ms | 7.90s | 90 tps | 131K | $0.030 / $0.130 | |
| Healthy | 98.07% | 98.84% | 98.77% | 98.77% | 484ms | 6.06s | 66 tps | 131K | $0.030 / $0.150 | |
| Healthy | 98.06% | 97.48% | 98.05% | 98.05% | 1.36s | 62.0s | 59 tps | 131K | $0.040 / $0.180 | |
Fireworksfireworks | Healthy | 95.35% | 97.55% | 97.20% | 97.20% | 326ms | 8.32s | 156 tps | 131K | $0.070 / $0.300 |
Googlegoogle-vertex/us-central1 | Degraded | 94.50% | 82.94% | 79.94% | 79.94% | 5.80s | 49.8s | 22 tps | 131K | $0.070 / $0.250 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | — | — | — | — | — | — | 131K | $0.070 / $0.150 |
Phalaphala | Degraded | — | 91.50% | 92.51% | 92.51% | 789ms | 10.2s | 54 tps | 131K | $0.040 / $0.150 |
Togethertogether | No data | — | 95.36% | — | — | 568ms | 3.07s | 84 tps | 131K | $0.050 / $0.200 |
- Amazon Bedrock100%Healthy24h 98.31%
- 7d
- 99.12%
- 30d
- 99.12%
- p50
- 396ms
- p99
- 2.03s
- Throughput
- 414 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock - Novita100%Healthy24h 96.97%
- 7d
- 99.11%
- 30d
- 99.11%
- p50
- 575ms
- p99
- 27.8s
- Throughput
- 101 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
novita/fp4fp4 - DeepInfra99.83%Healthy24h 99.89%
- 7d
- 99.49%
- 30d
- 99.49%
- p50
- 297ms
- p99
- 23.6s
- Throughput
- 77 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - Groq99.79%Healthy24h 98.05%
- 7d
- 98.09%
- 30d
- 98.09%
- p50
- 402ms
- p99
- 2.76s
- Throughput
- 296 tps
- Context
- 131K
- $/Mtok
- $0.075 / $0.300
groq - CoreWeave98.35%Healthy24h 99.30%
- 7d
- 99.26%
- 30d
- 99.26%
- p50
- 277ms
- p99
- 7.90s
- Throughput
- 90 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4 - Parasail98.07%Healthy24h 98.84%
- 7d
- 98.77%
- 30d
- 98.77%
- p50
- 484ms
- p99
- 6.06s
- Throughput
- 66 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
parasail/fp4fp4 - SiliconFlow98.06%Healthy24h 97.48%
- 7d
- 98.05%
- 30d
- 98.05%
- p50
- 1.36s
- p99
- 62.0s
- Throughput
- 59 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.180
siliconflow/fp8fp8 - Fireworks95.35%Healthy24h 97.55%
- 7d
- 97.20%
- 30d
- 97.20%
- p50
- 326ms
- p99
- 8.32s
- Throughput
- 156 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.300
fireworks - Google94.50%Degraded24h 82.94%
- 7d
- 79.94%
- 30d
- 79.94%
- p50
- 5.80s
- p99
- 49.8s
- Throughput
- 22 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.250
google-vertex/us-central1 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock/eu-west-1 - Degraded24h 91.50%
- 7d
- 92.51%
- 30d
- 92.51%
- p50
- 789ms
- p99
- 10.2s
- Throughput
- 54 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
phala - No data24h 95.36%
- 7d
- —
- 30d
- —
- p50
- 568ms
- p99
- 3.07s
- Throughput
- 84 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.200
together
Measured 3m 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.