gpt-oss-20b
openai/gpt-oss-20bInputOutput
Compare its 16 providersIncident RSSCompare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Comparegpt-oss-20b
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/us-central1 | Healthy | 100% | 97.16% | 98.03% | 88.89% | 564ms | 2.47s | 84 tps | 131K | $0.070 / $0.250 |
| Healthy | 100% | 94.51% | 96.16% | 96.71% | 1.24s | 7.41s | 22 tps | 131K | $0.040 / $0.180 | |
| Healthy | 99.99% | 99.37% | 99.83% | 99.80% | 342ms | 7.18s | 89 tps | 131K | $0.030 / $0.130 | |
| Healthy | 99.97% | 99.68% | 97.48% | 99.11% | 2.26s | 5.08s | 45 tps | 131K | $0.030 / $0.150 | |
Groqgroq | Healthy | 99.97% | 99.81% | 99.74% | 99.11% | 355ms | 2.56s | 165 tps | 131K | $0.075 / $0.300 |
| Healthy | 99.94% | 99.87% | 99.48% | 98.88% | 875ms | 7.63s | 26 tps | 131K | $0.020 / $0.100 | |
| Healthy | 99.88% | 99.36% | 99.75% | 99.53% | 982ms | 4.70s | 50 tps | 131K | $0.040 / $0.150 | |
Amazon Bedrockamazon-bedrock | Healthy | 99.87% | 98.57% | 99.62% | 99.28% | 347ms | 2.46s | 290 tps | 131K | $0.070 / $0.150 |
| Healthy | 99.66% | 99.77% | 99.48% | 98.55% | 2.59s | 15.3s | 26 tps | 131K | $0.020 / $0.100 | |
| Healthy | 98.29% | 99.71% | 99.44% | 99.44% | 1.03s | 14.2s | 17 tps | 131K | $0.029 / $0.140 | |
| No data | — | — | — | 98.68% | — | — | — | 131K | $0.020 / $0.100 | |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 100% | 99.47% | — | — | — | 131K | $0.070 / $0.150 |
| No data | — | 99.92% | 99.95% | 99.86% | 11.6s | 23.2s | 19 tps | 131K | $0.030 / $0.140 | |
Fireworksfireworks | No data | — | — | — | 43.22% | — | — | — | 131K | $0.070 / $0.300 |
Phalaphala | No data | — | — | 99.78% | 96.62% | — | — | — | 131K | $0.040 / $0.150 |
Togethertogether | No data | — | — | 0.00% | 0.00% | — | — | — | 131K | $0.050 / $0.200 |
- Google100%Healthy24h 97.16%
- 7d
- 98.03%
- 30d
- 88.89%
- p50
- 564ms
- p99
- 2.47s
- Throughput
- 84 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.250
google-vertex/us-central1 - SiliconFlow100%Healthy24h 94.51%
- 7d
- 96.16%
- 30d
- 96.71%
- p50
- 1.24s
- p99
- 7.41s
- Throughput
- 22 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.180
siliconflow/fp8fp8 - CoreWeave99.99%Healthy24h 99.37%
- 7d
- 99.83%
- 30d
- 99.80%
- p50
- 342ms
- p99
- 7.18s
- Throughput
- 89 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4 - Parasail99.97%Healthy24h 99.68%
- 7d
- 97.48%
- 30d
- 99.11%
- p50
- 2.26s
- p99
- 5.08s
- Throughput
- 45 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
parasail/fp4fp4 - Groq99.97%Healthy24h 99.81%
- 7d
- 99.74%
- 30d
- 99.11%
- p50
- 355ms
- p99
- 2.56s
- Throughput
- 165 tps
- Context
- 131K
- $/Mtok
- $0.075 / $0.300
groq - AkashML99.94%Healthy24h 99.87%
- 7d
- 99.48%
- 30d
- 98.88%
- p50
- 875ms
- p99
- 7.63s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
akashml/fp4fp4 - Novita99.88%Healthy24h 99.36%
- 7d
- 99.75%
- 30d
- 99.53%
- p50
- 982ms
- p99
- 4.70s
- Throughput
- 50 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
novita/fp4fp4 - Amazon Bedrock99.87%Healthy24h 98.57%
- 7d
- 99.62%
- 30d
- 99.28%
- p50
- 347ms
- p99
- 2.46s
- Throughput
- 290 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock - Darkbloom99.66%Healthy24h 99.77%
- 7d
- 99.48%
- 30d
- 98.55%
- p50
- 2.59s
- p99
- 15.3s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
darkbloom/fp8fp8 - DekaLLM98.29%Healthy24h 99.71%
- 7d
- 99.44%
- 30d
- 99.44%
- p50
- 1.03s
- p99
- 14.2s
- Throughput
- 17 tps
- Context
- 131K
- $/Mtok
- $0.029 / $0.140
dekallm/bf16bf16 - No data24h —
- 7d
- —
- 30d
- 98.68%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
akashml/bf16bf16 - No data24h 100%
- 7d
- 100%
- 30d
- 99.47%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock/eu-west-1 - No data24h 99.92%
- 7d
- 99.95%
- 30d
- 99.86%
- p50
- 11.6s
- p99
- 23.2s
- Throughput
- 19 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - No data24h —
- 7d
- —
- 30d
- 43.22%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.070 / $0.300
fireworks - No data24h —
- 7d
- 99.78%
- 30d
- 96.62%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
phala - No data24h —
- 7d
- 0.00%
- 30d
- 0.00%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.050 / $0.200
together
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 16 endpoints · 30 days with data, 93 endpoint-days below 90%.
Price changes
- gpt-oss-20bAkashMLakashml/bf16$0.030 → $0.020 / $0.130 → $0.1002026-09-01 23:25 UTC