gpt-oss-20b
openai/gpt-oss-20b
Compare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Comparegpt-oss-20b
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/us-central1 | Down | 100% | 83.47% | 15.5s | 42.2s | 2.0 tps | 131K | $0.070 / $0.250 |
| Degraded | 100% | 98.14% | 1.27s | 28.3s | 20 tps | 131K | $0.040 / $0.180 | |
| Healthy | 99.98% | 99.33% | 286ms | 1.85s | 73 tps | 131K | $0.030 / $0.130 | |
| Healthy | 99.91% | 99.90% | 254ms | 6.08s | 97 tps | 131K | $0.030 / $0.140 | |
Amazon Bedrockamazon-bedrock | Healthy | 99.88% | 98.33% | 436ms | 1.40s | 191 tps | 131K | $0.070 / $0.150 |
| Healthy | 99.78% | 99.92% | 583ms | 11.0s | 91 tps | 131K | $0.040 / $0.150 | |
| Healthy | 99.32% | 99.21% | 434ms | 8.84s | 64 tps | 131K | $0.030 / $0.150 | |
Groqgroq | Healthy | 98.90% | 98.00% | 643ms | 4.10s | 343 tps | 131K | $0.075 / $0.300 |
Fireworksfireworks | Healthy | 98.09% | 97.44% | 381ms | 7.86s | 126 tps | 131K | $0.070 / $0.300 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | — | — | — | — | 131K | $0.070 / $0.150 |
Phalaphala | No data | — | 91.73% | 675ms | 5.56s | 49 tps | 131K | $0.040 / $0.150 |
Togethertogether | No data | — | 96.45% | 279ms | 1.12s | 68 tps | 131K | $0.050 / $0.200 |
- Google100%Down24h 83.47%
- p50
- 15.5s
- p99
- 42.2s
- Throughput
- 2.0 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.250
google-vertex/us-central1 - SiliconFlow100%Degraded24h 98.14%
- p50
- 1.27s
- p99
- 28.3s
- Throughput
- 20 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.180
siliconflow/fp8fp8 - CoreWeave99.98%Healthy24h 99.33%
- p50
- 286ms
- p99
- 1.85s
- Throughput
- 73 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4 - DeepInfra99.91%Healthy24h 99.90%
- p50
- 254ms
- p99
- 6.08s
- Throughput
- 97 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - Amazon Bedrock99.88%Healthy24h 98.33%
- p50
- 436ms
- p99
- 1.40s
- Throughput
- 191 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock - Novita99.78%Healthy24h 99.92%
- p50
- 583ms
- p99
- 11.0s
- Throughput
- 91 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
novita/fp4fp4 - Parasail99.32%Healthy24h 99.21%
- p50
- 434ms
- p99
- 8.84s
- Throughput
- 64 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
parasail/fp4fp4 - Groq98.90%Healthy24h 98.00%
- p50
- 643ms
- p99
- 4.10s
- Throughput
- 343 tps
- Context
- 131K
- $/Mtok
- $0.075 / $0.300
groq - Fireworks98.09%Healthy24h 97.44%
- p50
- 381ms
- p99
- 7.86s
- Throughput
- 126 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.300
fireworks - No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock/eu-west-1 - No data24h 91.73%
- p50
- 675ms
- p99
- 5.56s
- Throughput
- 49 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
phala - No data24h 96.45%
- p50
- 279ms
- p99
- 1.12s
- Throughput
- 68 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.200
together
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 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.