gpt-oss-120b
openai/gpt-oss-120b
Compare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Comparegpt-oss-120b
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock | Healthy | 100% | 99.52% | 404ms | 2.46s | 300 tps | 131K | $0.150 / $0.600 |
BaseTenbaseten/fp4fp4 | Healthy | 100% | 98.76% | 230ms | 1.10s | 165 tps | 128K | $0.100 / $0.500 |
Cerebrascerebras/fp16fp16 | Healthy | 100% | 99.99% | 249ms | 2.86s | 662 tps | 131K | $0.350 / $0.750 |
DeepInfradeepinfra/bf16bf16 | Healthy | 100% | 98.72% | 460ms | 16.6s | 42 tps | 131K | $0.037 / $0.170 |
DeepInfradeepinfra/turbobf16 | Healthy | 100% | 94.54% | 453ms | 1.26s | 114 tps | 131K | $0.150 / $0.600 |
Maramara | Healthy | 100% | 97.61% | 1.09s | 8.91s | 127 tps | 131K | $0.150 / $0.750 |
Nebiusnebius/fp4fp4 | Healthy | 100% | 98.50% | 311ms | 3.52s | 202 tps | 131K | $0.150 / $0.600 |
Phalaphala | Healthy | 100% | 99.70% | 865ms | 7.12s | 70 tps | 131K | $0.150 / $0.600 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 100% | 92.14% | 1.71s | 16.5s | 21 tps | 131K | $0.050 / $0.450 |
Parasailparasail/fp4fp4 | Healthy | 99.96% | 99.94% | 396ms | 1.76s | 106 tps | 131K | $0.100 / $0.750 |
Groqgroq | Healthy | 99.94% | 99.90% | 287ms | 2.34s | 311 tps | 131K | $0.150 / $0.600 |
Novitanovita/fp4fp4 | Healthy | 99.93% | 97.42% | 546ms | 7.30s | 95 tps | 131K | $0.050 / $0.250 |
DigitalOceandigitalocean | Healthy | 99.93% | 99.77% | 549ms | 3.63s | 48 tps | 128K | $0.055 / $0.385 |
AkashMLakashml/bf16bf16 | Healthy | 99.85% | 99.60% | 579ms | 7.48s | 82 tps | 131K | $0.037 / $0.490 |
Mancer 2mancer/fp8fp8 | Healthy | 99.50% | 99.83% | 715ms | 7.61s | 68 tps | 131K | $0.085 / $0.500 |
CoreWeavecoreweave/fp4fp4 | Healthy | 99.41% | 96.30% | 514ms | 12.2s | 30 tps | 131K | $0.030 / $0.170 |
Togethertogether | Healthy | 95.24% | 98.41% | 273ms | 3.45s | 81 tps | 131K | $0.150 / $0.600 |
Googlegoogle-vertex/global | Down | 87.19% | 89.88% | 481ms | 3.95s | 77 tps | 131K | $0.090 / $0.360 |
SambaNovasambanova | Down | 73.03% | 97.83% | 874ms | 23.0s | 337 tps | 131K | $0.140 / $0.950 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | — | — | — | 131K | $0.150 / $0.600 |
- Amazon Bedrock100%Healthy24h 99.52%
- p50
- 404ms
- p99
- 2.46s
- Throughput
- 300 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - BaseTen100%Healthy24h 98.76%
- p50
- 230ms
- p99
- 1.10s
- Throughput
- 165 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4fp4 - Cerebras100%Healthy24h 99.99%
- p50
- 249ms
- p99
- 2.86s
- Throughput
- 662 tps
- Context
- 131K
- $/Mtok
- $0.350 / $0.750
cerebras/fp16fp16 - DeepInfra100%Healthy24h 98.72%
- p50
- 460ms
- p99
- 16.6s
- Throughput
- 42 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - DeepInfra100%Healthy24h 94.54%
- p50
- 453ms
- p99
- 1.26s
- Throughput
- 114 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - Mara100%Healthy24h 97.61%
- p50
- 1.09s
- p99
- 8.91s
- Throughput
- 127 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.750
mara - Nebius100%Healthy24h 98.50%
- p50
- 311ms
- p99
- 3.52s
- Throughput
- 202 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - Phala100%Healthy24h 99.70%
- p50
- 865ms
- p99
- 7.12s
- Throughput
- 70 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - SiliconFlow100%Healthy24h 92.14%
- p50
- 1.71s
- p99
- 16.5s
- Throughput
- 21 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.450
siliconflow/fp8fp8 - Parasail99.96%Healthy24h 99.94%
- p50
- 396ms
- p99
- 1.76s
- Throughput
- 106 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.750
parasail/fp4fp4 - Groq99.94%Healthy24h 99.90%
- p50
- 287ms
- p99
- 2.34s
- Throughput
- 311 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
groq - Novita99.93%Healthy24h 97.42%
- p50
- 546ms
- p99
- 7.30s
- Throughput
- 95 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
novita/fp4fp4 - DigitalOcean99.93%Healthy24h 99.77%
- p50
- 549ms
- p99
- 3.63s
- Throughput
- 48 tps
- Context
- 128K
- $/Mtok
- $0.055 / $0.385
digitalocean - AkashML99.85%Healthy24h 99.60%
- p50
- 579ms
- p99
- 7.48s
- Throughput
- 82 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.490
akashml/bf16bf16 - Mancer 299.50%Healthy24h 99.83%
- p50
- 715ms
- p99
- 7.61s
- Throughput
- 68 tps
- Context
- 131K
- $/Mtok
- $0.085 / $0.500
mancer/fp8fp8 - CoreWeave99.41%Healthy24h 96.30%
- p50
- 514ms
- p99
- 12.2s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170
coreweave/fp4fp4 - Together95.24%Healthy24h 98.41%
- p50
- 273ms
- p99
- 3.45s
- Throughput
- 81 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
together - Google87.19%Down24h 89.88%
- p50
- 481ms
- p99
- 3.95s
- Throughput
- 77 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.360
google-vertex/global - SambaNova73.03%Down24h 97.83%
- p50
- 874ms
- p99
- 23.0s
- Throughput
- 337 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.950
sambanova - Amazon Bedrock—No data24h 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock/eu-west-1
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.