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% | 99.10% | 99.10% | 386ms | 1.11s | 381 tps | 131K | $0.070 / $0.150 |
| Healthy | 100% | 99.88% | 99.48% | 99.48% | 327ms | 24.6s | 69 tps | 131K | $0.030 / $0.140 | |
| Healthy | 100% | 97.00% | 99.09% | 99.09% | 581ms | 29.6s | 94 tps | 131K | $0.040 / $0.150 | |
| Healthy | 100% | 97.52% | 98.06% | 98.06% | 1.42s | 82.4s | 50 tps | 131K | $0.040 / $0.180 | |
| Healthy | 99.63% | 98.81% | 98.75% | 98.75% | 475ms | 7.69s | 75 tps | 131K | $0.030 / $0.150 | |
| Healthy | 99.25% | 99.29% | 99.26% | 99.26% | 279ms | 7.64s | 87 tps | 131K | $0.030 / $0.130 | |
Groqgroq | Healthy | 98.83% | 98.06% | 98.07% | 98.07% | 646ms | 3.89s | 437 tps | 131K | $0.075 / $0.300 |
Fireworksfireworks | Degraded | 96.15% | 97.51% | 97.23% | 97.23% | 427ms | 9.33s | 140 tps | 131K | $0.070 / $0.300 |
Phalaphala | Degraded | 93.14% | 91.34% | 92.50% | 92.50% | 853ms | 9.81s | 55 tps | 131K | $0.040 / $0.150 |
Googlegoogle-vertex/us-central1 | Down | 88.93% | 83.06% | 80.08% | 80.08% | 5.34s | 46.1s | 32 tps | 131K | $0.070 / $0.250 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | — | — | — | — | — | — | 131K | $0.070 / $0.150 |
Togethertogether | No data | — | 95.37% | — | — | 736ms | 2.04s | 75 tps | 131K | $0.050 / $0.200 |
- Amazon Bedrock100%Healthy24h 98.31%
- 7d
- 99.10%
- 30d
- 99.10%
- p50
- 386ms
- p99
- 1.11s
- Throughput
- 381 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock - DeepInfra100%Healthy24h 99.88%
- 7d
- 99.48%
- 30d
- 99.48%
- p50
- 327ms
- p99
- 24.6s
- Throughput
- 69 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - Novita100%Healthy24h 97.00%
- 7d
- 99.09%
- 30d
- 99.09%
- p50
- 581ms
- p99
- 29.6s
- Throughput
- 94 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
novita/fp4fp4 - SiliconFlow100%Healthy24h 97.52%
- 7d
- 98.06%
- 30d
- 98.06%
- p50
- 1.42s
- p99
- 82.4s
- Throughput
- 50 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.180
siliconflow/fp8fp8 - Parasail99.63%Healthy24h 98.81%
- 7d
- 98.75%
- 30d
- 98.75%
- p50
- 475ms
- p99
- 7.69s
- Throughput
- 75 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
parasail/fp4fp4 - CoreWeave99.25%Healthy24h 99.29%
- 7d
- 99.26%
- 30d
- 99.26%
- p50
- 279ms
- p99
- 7.64s
- Throughput
- 87 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4 - Groq98.83%Healthy24h 98.06%
- 7d
- 98.07%
- 30d
- 98.07%
- p50
- 646ms
- p99
- 3.89s
- Throughput
- 437 tps
- Context
- 131K
- $/Mtok
- $0.075 / $0.300
groq - Fireworks96.15%Degraded24h 97.51%
- 7d
- 97.23%
- 30d
- 97.23%
- p50
- 427ms
- p99
- 9.33s
- Throughput
- 140 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.300
fireworks - Phala93.14%Degraded24h 91.34%
- 7d
- 92.50%
- 30d
- 92.50%
- p50
- 853ms
- p99
- 9.81s
- Throughput
- 55 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
phala - Google88.93%Down24h 83.06%
- 7d
- 80.08%
- 30d
- 80.08%
- p50
- 5.34s
- p99
- 46.1s
- Throughput
- 32 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 - No data24h 95.37%
- 7d
- —
- 30d
- —
- p50
- 736ms
- p99
- 2.04s
- Throughput
- 75 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.200
together
Measured 1m 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.