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% | 400ms | 2.22s | 368 tps | 131K | $0.070 / $0.150 |
| Healthy | 100% | 99.99% | 99.96% | 99.88% | 181ms | 4.68s | 171 tps | 131K | $0.030 / $0.130 | |
| Healthy | 100% | 99.95% | 99.87% | 99.89% | 334ms | 12.3s | 67 tps | 131K | $0.030 / $0.140 | |
Googlegoogle-vertex/us-central1 | Healthy | 100% | 96.58% | 94.37% | 97.01% | 380ms | 2.24s | 198 tps | 131K | $0.070 / $0.250 |
| Healthy | 100% | 99.64% | 99.71% | 99.24% | 866ms | 7.38s | 91 tps | 131K | $0.030 / $0.150 | |
| Healthy | 99.77% | 99.86% | 99.82% | 99.68% | 3.70s | 36.4s | 25 tps | 131K | $0.018 / $0.090 | |
| Healthy | 99.66% | 99.94% | 99.77% | 99.77% | 697ms | 4.81s | 134 tps | 131K | $0.040 / $0.150 | |
| Healthy | 99.41% | 99.21% | 99.40% | 99.50% | 776ms | 16.9s | 25 tps | 131K | $0.029 / $0.140 | |
| Healthy | 98.05% | 99.26% | 99.33% | 99.01% | 856ms | 13.4s | 46 tps | 131K | $0.020 / $0.100 | |
Groqgroq | Healthy | 95.83% | 96.86% | 96.53% | 98.57% | 383ms | 2.42s | 366 tps | 131K | $0.075 / $0.300 |
| Down | 53.97% | 95.99% | 95.18% | 96.08% | 1.14s | 8.28s | 28 tps | 131K | $0.040 / $0.180 | |
| No data | — | — | — | — | — | — | — | 131K | $0.020 / $0.100 | |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 99.94% | 99.76% | 99.62% | — | — | — | 131K | $0.070 / $0.150 |
Fireworksfireworks | No data | — | — | — | 0.00% | — | — | — | 131K | $0.070 / $0.300 |
Phalaphala | No data | — | — | — | 98.48% | — | — | — | 131K | $0.040 / $0.150 |
PrimeIntellectprimeintellect | No data | — | — | 99.61% | 99.61% | — | — | — | 131K | $0.070 / $0.300 |
Togethertogether | No data | — | — | — | 0.00% | — | — | — | 131K | $0.050 / $0.200 |
- Amazon Bedrock100%Healthy24h 99.97%
- 7d
- 99.96%
- 30d
- 99.37%
- p50
- 400ms
- p99
- 2.22s
- Throughput
- 368 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock - CoreWeave100%Healthy24h 99.99%
- 7d
- 99.96%
- 30d
- 99.88%
- p50
- 181ms
- p99
- 4.68s
- Throughput
- 171 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4 - DeepInfra100%Healthy24h 99.95%
- 7d
- 99.87%
- 30d
- 99.89%
- p50
- 334ms
- p99
- 12.3s
- Throughput
- 67 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - Google100%Healthy24h 96.58%
- 7d
- 94.37%
- 30d
- 97.01%
- p50
- 380ms
- p99
- 2.24s
- Throughput
- 198 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.250
google-vertex/us-central1 - Parasail100%Healthy24h 99.64%
- 7d
- 99.71%
- 30d
- 99.24%
- p50
- 866ms
- p99
- 7.38s
- Throughput
- 91 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
parasail/fp4fp4 - Darkbloom99.77%Healthy24h 99.86%
- 7d
- 99.82%
- 30d
- 99.68%
- p50
- 3.70s
- p99
- 36.4s
- Throughput
- 25 tps
- Context
- 131K
- $/Mtok
- $0.018 / $0.090
darkbloom/fp8fp8 - Novita99.66%Healthy24h 99.94%
- 7d
- 99.77%
- 30d
- 99.77%
- p50
- 697ms
- p99
- 4.81s
- Throughput
- 134 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
novita/fp4fp4 - DekaLLM99.41%Healthy24h 99.21%
- 7d
- 99.40%
- 30d
- 99.50%
- p50
- 776ms
- p99
- 16.9s
- Throughput
- 25 tps
- Context
- 131K
- $/Mtok
- $0.029 / $0.140
dekallm/bf16bf16 - AkashML98.05%Healthy24h 99.26%
- 7d
- 99.33%
- 30d
- 99.01%
- p50
- 856ms
- p99
- 13.4s
- Throughput
- 46 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
akashml/fp4fp4 - Groq95.83%Healthy24h 96.86%
- 7d
- 96.53%
- 30d
- 98.57%
- p50
- 383ms
- p99
- 2.42s
- Throughput
- 366 tps
- Context
- 131K
- $/Mtok
- $0.075 / $0.300
groq - SiliconFlow53.97%Down24h 95.99%
- 7d
- 95.18%
- 30d
- 96.08%
- p50
- 1.14s
- p99
- 8.28s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.180
siliconflow/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
akashml/bf16bf16 - No data24h 99.94%
- 7d
- 99.76%
- 30d
- 99.62%
- p50
- —
- p99
- —
- Throughput
- —
- 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
- 98.48%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
phala - No data24h —
- 7d
- 99.61%
- 30d
- 99.61%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.070 / $0.300
primeintellect - No data24h —
- 7d
- —
- 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
4 endpoints have 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.
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 · 48 days with data, 125 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