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% | 108ms◆ (best) | 3.62s | 177 tps | 131K | $0.030 / $0.130 | |
| Healthy | 100%◆ (best) | 99.63% | 99.80% | 99.67% | 3.56s | 34.9s | 23 tps | 131K | $0.018 / $0.090◆ (best) | |
| Healthy | 100%◆ (best) | 99.93% | 99.87% | 99.89%◆ (best) | 226ms | 3.60s | 101 tps | 131K | $0.030 / $0.140 | |
Amazon Bedrockamazon-bedrock | Healthy | 99.97% | 99.98% | 99.97% | 99.37% | 431ms | 2.30s◆ (best) | 351 tps◆ (best) | 131K | $0.070 / $0.150 |
| Healthy | 99.94% | 99.88% | 99.73% | 99.24% | 1.44s | 18.1s | 63 tps | 131K | $0.030 / $0.150 | |
| Healthy | 99.86% | 99.33% | 99.43% | 99.51% | 912ms | 30.0s | 24 tps | 131K | $0.029 / $0.140 | |
| Healthy | 99.77% | 99.88% | 99.77% | 99.76% | 682ms | 6.02s | 148 tps | 131K | $0.040 / $0.150 | |
| Healthy | 99.69% | 99.13% | 99.29% | 99.00% | 941ms | 21.8s | 37 tps | 131K | $0.020 / $0.100 | |
Groqgroq | Healthy | 95.87% | 97.71% | 96.54% | 98.50% | 688ms | 5.72s | 329 tps | 131K | $0.075 / $0.300 |
| Down | 79.07% | 85.40% | 93.16% | 95.48% | 1.13s | 14.0s | 39 tps | 131K | $0.040 / $0.180 | |
Googlegoogle-vertex/us-central1 | Down | 0.00% | 96.01% | 94.10% | 96.63% | 326ms | 2.78s | 225 tps | 131K | $0.070 / $0.250 |
| 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 |
Phalaphala | No data | — | — | — | 99.45% | — | — | — | 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
- 108ms◆ (best)
- p99
- 3.62s
- Throughput
- 177 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4 - Darkbloom100%◆ (best)Healthy24h 99.63%
- 7d
- 99.80%
- 30d
- 99.67%
- p50
- 3.56s
- p99
- 34.9s
- Throughput
- 23 tps
- Context
- 131K
- $/Mtok
- $0.018 / $0.090◆ (best)
darkbloom/fp8fp8 - DeepInfra100%◆ (best)Healthy24h 99.93%
- 7d
- 99.87%
- 30d
- 99.89%◆ (best)
- p50
- 226ms
- p99
- 3.60s
- Throughput
- 101 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.140
deepinfra/bf16bf16 - Amazon Bedrock99.97%Healthy24h 99.98%
- 7d
- 99.97%
- 30d
- 99.37%
- p50
- 431ms
- p99
- 2.30s◆ (best)
- Throughput
- 351 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.070 / $0.150
amazon-bedrock - Parasail99.94%Healthy24h 99.88%
- 7d
- 99.73%
- 30d
- 99.24%
- p50
- 1.44s
- p99
- 18.1s
- Throughput
- 63 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
parasail/fp4fp4 - DekaLLM99.86%Healthy24h 99.33%
- 7d
- 99.43%
- 30d
- 99.51%
- p50
- 912ms
- p99
- 30.0s
- Throughput
- 24 tps
- Context
- 131K
- $/Mtok
- $0.029 / $0.140
dekallm/bf16bf16 - Novita99.77%Healthy24h 99.88%
- 7d
- 99.77%
- 30d
- 99.76%
- p50
- 682ms
- p99
- 6.02s
- Throughput
- 148 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
novita/fp4fp4 - AkashML99.69%Healthy24h 99.13%
- 7d
- 99.29%
- 30d
- 99.00%
- p50
- 941ms
- p99
- 21.8s
- Throughput
- 37 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
akashml/fp4fp4 - Groq95.87%Healthy24h 97.71%
- 7d
- 96.54%
- 30d
- 98.50%
- p50
- 688ms
- p99
- 5.72s
- Throughput
- 329 tps
- Context
- 131K
- $/Mtok
- $0.075 / $0.300
groq - SiliconFlow79.07%Down24h 85.40%
- 7d
- 93.16%
- 30d
- 95.48%
- p50
- 1.13s
- p99
- 14.0s
- Throughput
- 39 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.180
siliconflow/fp8fp8 - Google0.00%Down24h 96.01%
- 7d
- 94.10%
- 30d
- 96.63%
- p50
- 326ms
- p99
- 2.78s
- Throughput
- 225 tps
- Context
- 131K
- $/Mtok
- $0.070 / $0.250
google-vertex/us-central1 - 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 - No data24h —
- 7d
- —
- 30d
- 99.45%
- 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 1m 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.
Throughput
Median tokens per second.