gpt-oss-20b
openai/gpt-oss-20bInputOutput
Compare its 17 providersIncident RSSCompare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Comparegpt-oss-20b
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock | Healthy | 100% | 99.97% | 99.96% | 99.37% | 370ms | 1.64s | 372 tps | 131K | $0.070 / $0.150 |
| Healthy | 100% | 100% | 99.91% | 99.88% | 101ms | 3.10s | 199 tps | 131K | $0.030 / $0.130 | |
| Healthy | 100% | 99.96% | 99.87% | 99.89% | 218ms | 2.48s | 91 tps | 131K | $0.030 / $0.140 | |
Googlegoogle-vertex/us-central1 | Healthy | 100% | 97.18% | 94.36% | 97.01% | 407ms | 2.17s | 248 tps | 131K | $0.070 / $0.250 |
| Healthy | 100% | 99.94% | 99.78% | 99.77% | 811ms | 8.42s | 63 tps | 131K | $0.040 / $0.150 | |
| Healthy | 100% | 99.61% | 99.71% | 99.24% | 921ms | 7.06s | 79 tps | 131K | $0.030 / $0.150 | |
PrimeIntellectprimeintellect | Healthy | 100% | 99.51% | 99.59% | 99.59% | 581ms | 5.49s | 137 tps | 131K | $0.070 / $0.300 |
| Healthy | 100% | 96.92% | 95.39% | 96.15% | 1.02s | 8.84s | 62 tps | 131K | $0.040 / $0.180 | |
| Healthy | 99.97% | 99.88% | 99.82% | 99.68% | 2.02s | 27.2s | 24 tps | 131K | $0.018 / $0.090 | |
| Healthy | 99.21% | 99.22% | 99.32% | 99.01% | 809ms | 15.2s | 50 tps | 131K | $0.020 / $0.100 | |
| Healthy | 98.84% | 99.22% | 99.40% | 99.50% | 785ms | 11.8s | 25 tps | 131K | $0.029 / $0.140 | |
Groqgroq | Healthy | 98.24% | 96.31% | 96.51% | 98.58% | 317ms | 2.44s | 476 tps | 131K | $0.075 / $0.300 |
| No data | — | — | — | — | — | — | — | 131K | $0.020 / $0.100 | |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 99.94% | 99.75% | 99.62% | 667ms | 975ms | 176 tps | 131K | $0.070 / $0.150 |
Fireworksfireworks | No data | — | — | — | 0.00% | — | — | — | 131K | $0.070 / $0.300 |
Phalaphala | No data | — | — | — | 98.49% | — | — | — | 131K | $0.040 / $0.150 |
Togethertogether | No data | — | — | — | 0.00% | — | — | — | 131K | $0.050 / $0.200 |
- Amazon Bedrock100%Healthy24h 99.97%
- 7d
- 99.96%
- 30d
- 99.37%
- p50
- 370ms
- p99
- 1.64s
- Throughput
- 372 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock - CoreWeave100%Healthy24h 100%
- 7d
- 99.91%
- 30d
- 99.88%
- p50
- 101ms
- p99
- 3.10s
- Throughput
- 199 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4 - DeepInfra100%Healthy24h 99.96%
- 7d
- 99.87%
- 30d
- 99.89%
- p50
- 218ms
- p99
- 2.48s
- Throughput
- 91 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - Google100%Healthy24h 97.18%
- 7d
- 94.36%
- 30d
- 97.01%
- p50
- 407ms
- p99
- 2.17s
- Throughput
- 248 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.250
google-vertex/us-central1 - Novita100%Healthy24h 99.94%
- 7d
- 99.78%
- 30d
- 99.77%
- p50
- 811ms
- p99
- 8.42s
- Throughput
- 63 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
novita/fp4fp4 - Parasail100%Healthy24h 99.61%
- 7d
- 99.71%
- 30d
- 99.24%
- p50
- 921ms
- p99
- 7.06s
- Throughput
- 79 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
parasail/fp4fp4 - PrimeIntellect100%Healthy24h 99.51%
- 7d
- 99.59%
- 30d
- 99.59%
- p50
- 581ms
- p99
- 5.49s
- Throughput
- 137 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.300
primeintellect - SiliconFlow100%Healthy24h 96.92%
- 7d
- 95.39%
- 30d
- 96.15%
- p50
- 1.02s
- p99
- 8.84s
- Throughput
- 62 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.180
siliconflow/fp8fp8 - Darkbloom99.97%Healthy24h 99.88%
- 7d
- 99.82%
- 30d
- 99.68%
- p50
- 2.02s
- p99
- 27.2s
- Throughput
- 24 tps
- Context
- 131K
- $/Mtok
- $0.018 / $0.090
darkbloom/fp8fp8 - AkashML99.21%Healthy24h 99.22%
- 7d
- 99.32%
- 30d
- 99.01%
- p50
- 809ms
- p99
- 15.2s
- Throughput
- 50 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
akashml/fp4fp4 - DekaLLM98.84%Healthy24h 99.22%
- 7d
- 99.40%
- 30d
- 99.50%
- p50
- 785ms
- p99
- 11.8s
- Throughput
- 25 tps
- Context
- 131K
- $/Mtok
- $0.029 / $0.140
dekallm/bf16bf16 - Groq98.24%Healthy24h 96.31%
- 7d
- 96.51%
- 30d
- 98.58%
- p50
- 317ms
- p99
- 2.44s
- Throughput
- 476 tps
- Context
- 131K
- $/Mtok
- $0.075 / $0.300
groq - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
akashml/bf16bf16 - No data24h 99.94%
- 7d
- 99.75%
- 30d
- 99.62%
- p50
- 667ms
- p99
- 975ms
- Throughput
- 176 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock/eu-west-1 - No data24h —
- 7d
- —
- 30d
- 0.00%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.070 / $0.300
fireworks - No data24h —
- 7d
- —
- 30d
- 98.49%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
phala - No data24h —
- 7d
- —
- 30d
- 0.00%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.050 / $0.200
together
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint has no chartable data in this range.
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 · 17 endpoints · 47 days with data, 129 endpoint-days below 90%.
Price changes
- gpt-oss-20bDekaLLMdekallm/bf16$0.029 / $0.140cache read — → $0.0292026-10-02 13:40 UTC
- gpt-oss-20bDarkbloomdarkbloom/fp8$0.018 / $0.090cache read — → $0.0092026-09-28 20:56 UTC
- gpt-oss-20bDarkbloomdarkbloom/fp8$0.020 → $0.018 / $0.100 → $0.0902026-09-19 02:55 UTC
- gpt-oss-20bAkashMLakashml/bf16$0.030 → $0.020 / $0.130 → $0.1002026-09-01 23:25 UTC