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% | 99.58% | 411ms | 2.39s | 290 tps | 131K | $0.150 / $0.600 |
BaseTenbaseten/fp4fp4 | Healthy | 100% | 98.85% | 243ms | 1.07s | 172 tps | 128K | $0.100 / $0.500 |
Cerebrascerebras/fp16fp16 | Healthy | 100% | 99.99% | 259ms | 2.72s | 658 tps | 131K | $0.350 / $0.750 |
DeepInfradeepinfra/turbobf16 | Healthy | 100% | 94.91% | 457ms | 1.53s | 120 tps | 131K | $0.150 / $0.600 |
Mancer 2mancer/fp8fp8 | Healthy | 100% | 99.84% | 797ms | 6.06s | 47 tps | 131K | $0.085 / $0.500 |
Maramara | Healthy | 100% | 97.28% | 1.54s | 7.72s | 129 tps | 131K | $0.150 / $0.750 |
Nebiusnebius/fp4fp4 | Healthy | 100% | 98.53% | 364ms | 5.00s | 161 tps | 131K | $0.150 / $0.600 |
Parasailparasail/fp4fp4 | Healthy | 100% | 99.94% | 390ms | 1.45s | 113 tps | 131K | $0.100 / $0.750 |
Phalaphala | Healthy | 100% | 99.71% | 886ms | 6.98s | 65 tps | 131K | $0.150 / $0.600 |
Togethertogether | Healthy | 100% | 98.87% | 306ms | 2.32s | 35 tps | 131K | $0.150 / $0.600 |
Groqgroq | Healthy | 99.99% | 99.90% | 271ms | 2.44s | 305 tps | 131K | $0.150 / $0.600 |
DeepInfradeepinfra/bf16bf16 | Healthy | 99.98% | 98.74% | 468ms | 15.8s | 40 tps | 131K | $0.037 / $0.170 |
DigitalOceandigitalocean | Healthy | 99.91% | 99.78% | 752ms | 4.60s | 29 tps | 128K | $0.055 / $0.385 |
AkashMLakashml/bf16bf16 | Healthy | 99.90% | 99.56% | 738ms | 5.23s | 62 tps | 131K | $0.037 / $0.490 |
Novitanovita/fp4fp4 | Healthy | 99.81% | 96.74% | 545ms | 7.58s | 65 tps | 131K | $0.050 / $0.250 |
CoreWeavecoreweave/fp4fp4 | Healthy | 99.35% | 96.00% | 535ms | 11.2s | 29 tps | 131K | $0.030 / $0.170 |
SiliconFlowsiliconflow/fp8fp8 | Degraded | 97.28% | 91.74% | 1.97s | 18.7s | 13 tps | 131K | $0.050 / $0.450 |
SambaNovasambanova | Down | 89.14% | 98.20% | 892ms | 21.2s | 351 tps | 131K | $0.140 / $0.950 |
Googlegoogle-vertex/global | Down | 86.00% | 89.89% | 562ms | 5.63s | 70 tps | 131K | $0.090 / $0.360 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | — | — | — | 131K | $0.150 / $0.600 |
- Amazon Bedrock100%Healthy24h 99.58%
- p50
- 411ms
- p99
- 2.39s
- Throughput
- 290 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - BaseTen100%Healthy24h 98.85%
- p50
- 243ms
- p99
- 1.07s
- Throughput
- 172 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4fp4 - Cerebras100%Healthy24h 99.99%
- p50
- 259ms
- p99
- 2.72s
- Throughput
- 658 tps
- Context
- 131K
- $/Mtok
- $0.350 / $0.750
cerebras/fp16fp16 - DeepInfra100%Healthy24h 94.91%
- p50
- 457ms
- p99
- 1.53s
- Throughput
- 120 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - Mancer 2100%Healthy24h 99.84%
- p50
- 797ms
- p99
- 6.06s
- Throughput
- 47 tps
- Context
- 131K
- $/Mtok
- $0.085 / $0.500
mancer/fp8fp8 - Mara100%Healthy24h 97.28%
- p50
- 1.54s
- p99
- 7.72s
- Throughput
- 129 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.750
mara - Nebius100%Healthy24h 98.53%
- p50
- 364ms
- p99
- 5.00s
- Throughput
- 161 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - Parasail100%Healthy24h 99.94%
- p50
- 390ms
- p99
- 1.45s
- Throughput
- 113 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.750
parasail/fp4fp4 - Phala100%Healthy24h 99.71%
- p50
- 886ms
- p99
- 6.98s
- Throughput
- 65 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - Together100%Healthy24h 98.87%
- p50
- 306ms
- p99
- 2.32s
- Throughput
- 35 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
together - Groq99.99%Healthy24h 99.90%
- p50
- 271ms
- p99
- 2.44s
- Throughput
- 305 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
groq - DeepInfra99.98%Healthy24h 98.74%
- p50
- 468ms
- p99
- 15.8s
- Throughput
- 40 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - DigitalOcean99.91%Healthy24h 99.78%
- p50
- 752ms
- p99
- 4.60s
- Throughput
- 29 tps
- Context
- 128K
- $/Mtok
- $0.055 / $0.385
digitalocean - AkashML99.90%Healthy24h 99.56%
- p50
- 738ms
- p99
- 5.23s
- Throughput
- 62 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.490
akashml/bf16bf16 - Novita99.81%Healthy24h 96.74%
- p50
- 545ms
- p99
- 7.58s
- Throughput
- 65 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
novita/fp4fp4 - CoreWeave99.35%Healthy24h 96.00%
- p50
- 535ms
- p99
- 11.2s
- Throughput
- 29 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170
coreweave/fp4fp4 - SiliconFlow97.28%Degraded24h 91.74%
- p50
- 1.97s
- p99
- 18.7s
- Throughput
- 13 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.450
siliconflow/fp8fp8 - SambaNova89.14%Down24h 98.20%
- p50
- 892ms
- p99
- 21.2s
- Throughput
- 351 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.950
sambanova - Google86.00%Down24h 89.89%
- p50
- 562ms
- p99
- 5.63s
- Throughput
- 70 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.360
google-vertex/global - Amazon Bedrock—No data24h 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock/eu-west-1
Measured 2m 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.