gpt-oss-20b: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.95% | 99.99%◆ (best) | 99.88% | 114ms◆ (best) | 4.56s | 158 tps | 131K | $0.030 / $0.130 | |
| Healthy | 100%◆ (best) | 99.93% | 99.88% | 99.89%◆ (best) | 246ms | 4.52s | 99 tps | 131K | $0.030 / $0.140 | |
| Healthy | 100%◆ (best) | 99.89% | 99.77% | 99.76% | 691ms | 5.10s | 142 tps | 131K | $0.040 / $0.150 | |
Amazon Bedrockamazon-bedrock | Healthy | 99.97% | 99.98% | 99.97% | 99.37% | 560ms | 4.39s◆ (best) | 240 tps | 131K | $0.070 / $0.150 |
| Healthy | 99.78% | 99.88% | 99.73% | 99.24% | 1.05s | 6.04s | 83 tps | 131K | $0.030 / $0.150 | |
| Healthy | 99.34% | 99.11% | 99.29% | 99.00% | 772ms | 23.1s | 30 tps | 131K | $0.020 / $0.100 | |
| Healthy | 99.33% | 99.62% | 99.80% | 99.67% | 2.70s | 27.4s | 24 tps | 131K | $0.018 / $0.090◆ (best) | |
| Healthy | 98.92% | 99.35% | 99.43% | 99.51% | 778ms | 28.6s | 22 tps | 131K | $0.029 / $0.140 | |
Groqgroq | Healthy | 98.83% | 97.73% | 96.55% | 98.50% | 898ms | 4.51s | 242 tps◆ (best) | 131K | $0.075 / $0.300 |
| Down | 72.07% | 85.67% | 93.09% | 95.46% | 1.17s | 11.4s | 30 tps | 131K | $0.040 / $0.180 | |
| No data | — | — | — | — | — | — | — | 131K | $0.020 / $0.100 | |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 99.72% | 99.62% | — | — | — | 131K | $0.070 / $0.150 |
Fireworksfireworks | No data | — | — | — | 0.00% | — | — | — | 131K | $0.070 / $0.300 |
Googlegoogle-vertex/us-central1 | Down | — | 95.99% | 93.78% | 96.55% | 774ms | 9.76s | 146 tps | 131K | $0.070 / $0.250 |
Phalaphala | No data | — | — | — | 99.44% | — | — | — | 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 |
- CoreWeave100%◆ (best)Healthy24h 99.95%
- 7d
- 99.99%◆ (best)
- 30d
- 99.88%
- p50
- 114ms◆ (best)
- p99
- 4.56s
- Throughput
- 158 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4 - DeepInfra100%◆ (best)Healthy24h 99.93%
- 7d
- 99.88%
- 30d
- 99.89%◆ (best)
- p50
- 246ms
- p99
- 4.52s
- Throughput
- 99 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - Novita100%◆ (best)Healthy24h 99.89%
- 7d
- 99.77%
- 30d
- 99.76%
- p50
- 691ms
- p99
- 5.10s
- Throughput
- 142 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
novita/fp4fp4 - Amazon Bedrock99.97%Healthy24h 99.98%
- 7d
- 99.97%
- 30d
- 99.37%
- p50
- 560ms
- p99
- 4.39s◆ (best)
- Throughput
- 240 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock - Parasail99.78%Healthy24h 99.88%
- 7d
- 99.73%
- 30d
- 99.24%
- p50
- 1.05s
- p99
- 6.04s
- Throughput
- 83 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
parasail/fp4fp4 - AkashML99.34%Healthy24h 99.11%
- 7d
- 99.29%
- 30d
- 99.00%
- p50
- 772ms
- p99
- 23.1s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
akashml/fp4fp4 - Darkbloom99.33%Healthy24h 99.62%
- 7d
- 99.80%
- 30d
- 99.67%
- p50
- 2.70s
- p99
- 27.4s
- Throughput
- 24 tps
- Context
- 131K
- $/Mtok
- $0.018 / $0.090◆ (best)
darkbloom/fp8fp8 - DekaLLM98.92%Healthy24h 99.35%
- 7d
- 99.43%
- 30d
- 99.51%
- p50
- 778ms
- p99
- 28.6s
- Throughput
- 22 tps
- Context
- 131K
- $/Mtok
- $0.029 / $0.140
dekallm/bf16bf16 - Groq98.83%Healthy24h 97.73%
- 7d
- 96.55%
- 30d
- 98.50%
- p50
- 898ms
- p99
- 4.51s
- Throughput
- 242 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.075 / $0.300
groq - SiliconFlow72.07%Down24h 85.67%
- 7d
- 93.09%
- 30d
- 95.46%
- p50
- 1.17s
- p99
- 11.4s
- Throughput
- 30 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 100%
- 7d
- 99.72%
- 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 - Down24h 95.99%
- 7d
- 93.78%
- 30d
- 96.55%
- p50
- 774ms
- p99
- 9.76s
- Throughput
- 146 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.250
google-vertex/us-central1 - No data24h —
- 7d
- —
- 30d
- 99.44%
- 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. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.